{ "schema": "cchp.pricing-table/v1", "version": "bf0c58c98222be0a", "refreshed_at": "2026-08-14T18:31:11.169Z", "currency": "USD", "providers": { "alibaba": { "name": "Alibaba (China)", "doc": "https://www.alibabacloud.com/help/en/model-studio/models", "icon": "alibaba-color.svg" }, "amazon-bedrock": { "name": "Amazon Bedrock", "doc": "https://docs.aws.amazon.com/bedrock/", "icon": "bedrock-color.svg" }, "anthropic": { "name": "Anthropic", "doc": "https://docs.anthropic.com", "icon": "anthropic.svg", "icon_mono": true }, "cohere": { "name": "Cohere", "doc": "https://docs.cohere.com/docs/models", "icon": "cohere-color.svg" }, "deepseek": { "name": "DeepSeek", "doc": "https://api-docs.deepseek.com/quick_start/pricing", "icon": "deepseek-color.svg" }, "google": { "name": "Google", "doc": "https://ai.google.dev/docs", "icon": "google-color.svg" }, "google-vertex": { "name": "Google Vertex AI", "doc": "https://cloud.google.com/vertex-ai/docs", "icon": "vertexai-color.svg" }, "inception": { "name": "Inception", "doc": "https://platform.inceptionlabs.ai/docs", "icon": "inception.svg", "icon_mono": true }, "llama": { "name": "Llama", "doc": "https://llama.developer.meta.com/docs/models", "icon": "meta-color.svg" }, "longcat": { "name": "LongCat", "doc": "https://longcat.chat/platform/docs/", "icon": "longcat-color.svg" }, "meta": { "name": "Meta", "doc": "https://dev.meta.ai/docs", "icon": "meta-color.svg" }, "minimax": { "name": "MiniMax (minimaxi.com)", "doc": "https://platform.minimaxi.com/docs/guides/quickstart", "icon": "minimax-color.svg" }, "mistral": { "name": "Mistral", "doc": "https://docs.mistral.ai/getting-started/models/", "icon": "mistral-color.svg" }, "moonshotai": { "name": "Moonshot AI (China)", "doc": "https://platform.moonshot.cn/docs/api/chat", "icon": "moonshot.svg", "icon_mono": true }, "morph": { "name": "Morph", "doc": "https://docs.morphllm.com/api-reference/introduction", "icon": "morph-color.svg" }, "nvidia": { "name": "Nvidia", "doc": "https://docs.api.nvidia.com/nim/", "icon": "nvidia-color.svg" }, "openai": { "name": "OpenAI", "doc": "https://openai.com", "icon": "openai.svg", "icon_mono": true }, "perplexity": { "name": "Perplexity", "doc": "https://docs.perplexity.ai", "icon": "perplexity-color.svg" }, "stepfun": { "name": "StepFun", "doc": "https://platform.stepfun.com/docs/zh/overview/concept", "icon": "stepfun-color.svg" }, "upstage": { "name": "Upstage", "doc": "https://developers.upstage.ai/docs/apis/chat", "icon": "upstage-color.svg" }, "xai": { "name": "xAI", "doc": "https://x.ai", "icon": "xai.svg", "icon_mono": true }, "xiaomi": { "name": "Xiaomi", "doc": "https://platform.xiaomimimo.com/#/docs", "icon": "xiaomimimo.svg", "icon_mono": true }, "zhipuai": { "name": "Zhipu AI", "doc": "https://docs.z.ai/guides/overview/pricing", "icon": "zhipu-color.svg" }, "ai21": { "name": "ai21", "icon": "ai21.svg", "icon_mono": true }, "bytedance": { "name": "bytedance", "icon": "bytedance-color.svg" }, "amazon": { "name": "amazon", "icon": "aws-color.svg" }, "antgroup": { "name": "antgroup", "icon": "antgroup-color.svg" }, "baichuan": { "name": "baichuan", "icon": "baichuan-color.svg" }, "bfl": { "name": "bfl", "icon": "bfl.svg", "icon_mono": true }, "volcengine": { "name": "volcengine", "icon": "volcengine-color.svg" }, "sensenova": { "name": "sensenova", "icon": "sensenova-color.svg" }, "jina": { "name": "jina", "icon": "jina.svg", "icon_mono": true } }, "models": [ { "slug": "ai21/j2-light", "model_name": "j2-light", "display_name": "j2-light", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 8192, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "ai21/j2-mid", "model_name": "j2-mid", "display_name": "j2-mid", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 8192, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "ai21/j2-ultra", "model_name": "j2-ultra", "display_name": "j2-ultra", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 8192, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "ai21/jamba-1.5", "model_name": "jamba-1.5", "display_name": "jamba-1.5", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "ai21/jamba-1.5-large", "model_name": "jamba-1.5-large", "display_name": "jamba-1.5-large", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "8" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": { "function_calling": true, "stream": true, "open_weights": true }, "deprecation_date": "2026-11-26", "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2024-08-15", "knowledge_cutoff": "2024-08", "family": "jamba", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "ai21.jamba-1-5-large-v1:0", "ai21/jamba-1-5-large" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "ai21/jamba-1.5-large@001", "model_name": "jamba-1.5-large@001", "display_name": "jamba-1.5-large@001", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "8" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "ai21/jamba-1.5-mini", "model_name": "jamba-1.5-mini", "display_name": "jamba-1.5-mini", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry+pricetoken", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": { "function_calling": true, "stream": true, "open_weights": true }, "released_at": "2025-06-01", "deprecation_date": "2026-11-26", "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2024-08", "family": "jamba", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "ai21.jamba-1-5-mini-v1:0", "ai21/jamba-1-5-mini" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "ai21/jamba-1.5-mini@001", "model_name": "jamba-1.5-mini@001", "display_name": "jamba-1.5-mini@001", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "ai21/jamba-large", "model_name": "jamba-large", "display_name": "Jamba Large", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "8" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-03-06", "knowledge_cutoff": "2024-08", "max_input_tokens": 256000, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "jamba", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "我们最强大、最先进的模型，专为复杂企业任务设计，性能卓越。", "zh-TW": "我們最強大、最先進的模型，專為複雜企業任務設計，具備卓越效能。", "ja-JP": "Jamba Large は、複雑な企業向けタスクに対応する最も強力で高度なモデルです。", "ru-RU": "Наша самая мощная и продвинутая модель, предназначенная для сложных корпоративных задач с выдающейся производительностью." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Jamba Large" } ] }, { "slug": "ai21/jamba-large-1.6", "model_name": "jamba-large-1.6", "display_name": "jamba-large-1.6", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "8" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": { "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-03-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "jamba", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "ai21/jamba-large-1.7", "model_name": "jamba-large-1.7", "display_name": "jamba-large-1.7", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry+pricetoken", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "8" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2025-08-01", "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "family": "jamba", "knowledge_cutoff": "2024-08", "parameters": { "supported": [ "max_tokens", "response_format", "stop", "temperature", "tool_choice", "tools", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "ai21/jamba-large-1.7", "jamba-large-1-7" ], "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "ai21/jamba-mini", "model_name": "jamba-mini", "display_name": "Jamba Mini", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-03-06", "knowledge_cutoff": "2024-08", "max_input_tokens": 256000, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "jamba", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "同类中效率最高的模型，在速度与质量之间实现平衡，占用资源更少。", "zh-TW": "同級中最具效率的模型，在速度與品質之間取得平衡，佔用資源更少。", "ja-JP": "Jamba Mini は、速度と品質のバランスに優れた、同クラスで最も効率的なモデルです。", "ru-RU": "Самая эффективная модель в своем классе, обеспечивающая баланс между скоростью и качеством при минимальных ресурсах." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Jamba Mini" } ] }, { "slug": "ai21/jamba-mini-1.6", "model_name": "jamba-mini-1.6", "display_name": "jamba-mini-1.6", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": { "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2024-01-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "jamba", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "ai21/jamba-mini-1.7", "model_name": "jamba-mini-1.7", "display_name": "jamba-mini-1.7", "vendor": "ai21", "pricing": [ { "provider": "ai21", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": { "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-07-09", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "jamba", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "alibaba/deepseek-v4-flash-0731", "model_name": "deepseek-v4-flash-0731", "display_name": "DeepSeek V4 Flash 0731", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.04" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "released_at": "2026-07-31", "knowledge_cutoff": "2025-05", "max_input_tokens": 1000000, "max_output_tokens": 384000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "deepseek-flash", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true }, "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models", "model_type": "deep_thinking", "status": "beta", "reasoning_config": { "budget_min": 1 }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "DeepSeek-V4-Flash-0731", "accounts/fireworks/models/deepseek-v4-flash-0731", "deepinfra/deepseek-v4-flash-0731", "deepseek-ai/DeepSeek-V4-Flash-0731", "deepseek/deepseek-v4-flash-0731", "deepseek/deepseek-v4-flash-0731:thinking", "fireworks/deepseek-v4-flash-0731", "novita/deepseek/deepseek-v4-flash-0731", "sference/deepseek-v4-flash-0731", "tensorx/deepseek-v4-flash-0731" ], "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.2964683", "new": "0.29656322" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14823415", "new": "0.14828161" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.016", "new": "0.028" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "0.18", "new": "0.28" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.08", "new": "0.14" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "cache_read", "old": "0.032664", "new": "0.04" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "completion", "old": "0.304864", "new": "0.4" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "prompt", "old": "0.152432", "new": "0.2" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.29651466", "new": "0.2964683" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14825733", "new": "0.14823415" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.29649056", "new": "0.29651466" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14824528", "new": "0.14825733" }, { "date": "2026-08-11", "kind": "price", "provider": "cortecs", "charge": "cache_read", "old": "0.062", "new": "0.03" }, { "date": "2026-08-11", "kind": "price", "provider": "cortecs", "charge": "completion", "old": "0.3", "new": "0.28" }, { "date": "2026-08-11", "kind": "price", "provider": "cortecs", "charge": "prompt", "old": "0.25", "new": "0.13" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.29640078", "new": "0.29649056" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820039", "new": "0.14824528" }, { "date": "2026-08-10", "kind": "price", "provider": "deepinfra", "charge": "cache_read", "old": "0.018", "new": "0.016" }, { "date": "2026-08-10", "kind": "price", "provider": "deepinfra", "charge": "prompt", "old": "0.09", "new": "0.08" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.29637926", "new": "0.29640078" } ] }, { "slug": "alibaba/glm-5.2", "model_name": "glm-5.2", "display_name": "GLM-5.2", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+litellm+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.4" }, "completion": { "unit": "per_M_tokens", "price": "4.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.28" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "28", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Open flagship GLM for long-horizon coding agents and million-token context work", "released_at": "2026-06-13", "max_input_tokens": 1000000, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "web_search": true }, "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models", "model_type": "deep_thinking", "reasoning_config": { "budget_min": 1 }, "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "@cf/zai-org/glm-5.2", "GLM-5.2", "TEE/glm-5.2", "TEE/glm-5.2:thinking", "cline-pass/glm-5.2", "doubleword/glm-5.2", "fireworks/glm-5.2", "glm-5-2", "glm-5.2:free", "hf:zai-org/GLM-5.2", "inceptron/glm-5.2", "nebius/glm-5.2", "sference/glm-5.2", "subconscious/glm-5.2", "tensorx/glm-5.2", "workers-ai/@cf/zai-org/glm-5.2", "z-ai/glm-5.2", "z-ai/glm-5.2-free", "zai-org/GLM-5.2", "zai-org/glm-5.2", "zai-org/glm-5.2:thinking", "zai/GLM-5.2", "zai/glm-5.2" ], "intro_i18n": { "zh-CN": "GLM-5.2 是智谱 AI 在火山方舟平台上推出的旗舰模型，针对长时任务在编码、长上下文理解、规划和工具协作方面有重大改进。支持 1M-token 上下文窗口，并可灵活控制推理力度，适用于复杂开发、移动全栈工作、代码迁移和研究复现。", "zh-TW": "GLM-5.2 是智譜 AI 在火山方舟上的旗艦模型，針對編碼、長期上下文理解、規劃和工具協作方面進行了重大改進。它支持 1M-token 的上下文窗口以及靈活的推理努力控制，適用於複雜開發、移動全棧工作、代碼遷移和研究復現。", "ja-JP": "GLM-5.2は、Zhipu AIのVolcano Ark向けの旗艦モデルで、コーディング、長コンテキスト理解、計画、ツールコラボレーションにおいて大幅な改善を実現しています。1Mトークンのコンテキストウィンドウをサポートし、複雑な開発、モバイルフルスタック作業、コード移行、研究再現に柔軟な推論努力制御を提供します。", "ru-RU": "GLM-5.2 — флагманская модель Zhipu AI для задач с длинным горизонтом на платформе Volcano Ark, с существенными улучшениями в области кодирования, понимания длинного контекста, планирования и взаимодействия с инструментами. Она поддерживает контекстное окно на 1M токенов и гибкое управление усилиями рассуждений для сложной разработки, мобильной работы полного цикла, миграции кода и воспроизведения исследований." }, "price_history": [ { "date": "2026-08-14", "kind": "delisted", "note": "GLM-5.2" }, { "date": "2026-08-14", "kind": "listed", "note": "GLM-5.2" }, { "date": "2026-08-13", "kind": "delisted", "note": "GLM-5.2" }, { "date": "2026-08-13", "kind": "listed", "note": "GLM-5.2" }, { "date": "2026-08-12", "kind": "delisted", "note": "GLM-5.2" }, { "date": "2026-08-12", "kind": "listed", "note": "GLM-5.2" }, { "date": "2026-08-11", "kind": "delisted", "note": "GLM-5.2" }, { "date": "2026-08-11", "kind": "listed", "note": "GLM-5.2" } ] }, { "slug": "alibaba/happyhorse-1.0-i2v", "model_name": "happyhorse-1.0-i2v", "display_name": "HappyHorse-1.0-I2V", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.235294" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-04-22", "model_type": "video_generation", "capabilities": { "vision": true, "video_input": true, "pdf_input": true, "audio_output": true, "prompt_caching": true }, "modalities": { "input": [ "text", "image" ], "output": [ "video", "audio" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "alibaba/happyhorse-1.0-i2v" ], "intro_i18n": { "zh-CN": "HappyHorse-1.0-I2V 支持图生视频，能够生成高度逼真的动态画面。它能准确理解文本语义，生成流畅自然、细节丰富的高质量视频。", "zh-TW": "HappyHorse-1.0-I2V 支援圖像轉影片生成，呈現高度真實的動態畫面。能精準理解文字語意，生成流暢、自然且細節豐富的高品質影片。", "ja-JP": "HappyHorse-1.0-I2Vは、テキストから動画生成をサポートし、非常に忠実な動的ビジュアルを提供します。テキストの意味を正確に理解し、滑らかで自然で詳細に富んだ高品質な動画を生成します。", "ru-RU": "HappyHorse-1.0-I2V поддерживает генерацию видео по изображению, создавая высококачественные динамические сцены. Модель точно понимает текстовые описания и создаёт реалистичные, плавные и детализированные видеоролики." }, "price_history": [ { "date": "2026-07-17", "kind": "capability", "note": "audio_output: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "HappyHorse-1.0-I2V" } ] }, { "slug": "alibaba/happyhorse-1.0-r2v", "model_name": "happyhorse-1.0-r2v", "display_name": "HappyHorse-1.0-R2V", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.235294" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-04-26", "model_type": "video_generation", "capabilities": { "vision": true, "prompt_caching": true }, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "alibaba/happyhorse-1.0-r2v" ], "intro_i18n": { "zh-CN": "HappyHorse-1.0-R2V 支持基于参考图的视频生成，主体与场景稳定性更强。支持最多 9 张参考图，在忠实呈现创意意图的同时增强表现力。", "zh-TW": "HappyHorse-1.0-R2V 支援基於參考圖像的影片生成，主體與場景一致性更強。支持最多 9 張參考圖像，準確保留創意意圖並呈現更高的表現力。", "ja-JP": "HappyHorse-1.0-R2Vは、参照ベースの動画生成をサポートし、より安定した被写体とシーンの一貫性を提供します。最大9枚の参照画像をサポートし、創造的な意図を正確に保持し、表現力を強化します。", "ru-RU": "HappyHorse-1.0-R2V поддерживает генерацию видео на основе референсов, обеспечивая более стабильную передачу внешнего вида объектов и сцены. Поддерживает до 9 референсных изображений, точно сохраняет творческий замысел и обладает усиленной выразительностью." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "HappyHorse-1.0-R2V" } ] }, { "slug": "alibaba/happyhorse-1.0-t2v", "model_name": "happyhorse-1.0-t2v", "display_name": "HappyHorse-1.0-T2V", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.235294" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-04-21", "model_type": "video_generation", "capabilities": { "video_input": true, "pdf_input": true, "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "alibaba/happyhorse-1.0-t2v" ], "intro_i18n": { "zh-CN": "HappyHorse-1.0-T2V 支持文生视频，能够生成高度逼真的动态画面。它能准确理解文本语义，生成流畅自然、细节丰富的高质量视频。", "zh-TW": "HappyHorse-1.0-T2V 支援文本轉影片生成，呈現高度真實的動態畫面。能精準理解文字語意，生成流暢、自然且細節豐富的高品質影片。", "ja-JP": "HappyHorse-1.0-T2Vは、テキストから動画生成をサポートし、非常に忠実な動的ビジュアルを提供します。テキストの意味を正確に理解し、滑らかで自然で詳細に富んだ高品質な動画を生成します。", "ru-RU": "HappyHorse-1.0-T2V поддерживает генерацию видео по тексту, создавая реалистичные динамические сцены. Она точно интерпретирует текстовую семантику и генерирует высококачественные плавные и детализированные видеоролики." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "HappyHorse-1.0-T2V" } ] }, { "slug": "alibaba/QVQ-72B-Preview", "model_name": "QVQ-72B-Preview", "display_name": "QVQ 72B Preview", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.764706" }, "completion": { "unit": "per_M_tokens", "price": "5.294118" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qvq-72b-preview" } ], "released_at": "2024-12-25", "max_input_tokens": 32768, "max_output_tokens": 16384, "model_type": "vision_understanding", "capabilities": { "reasoning": true, "vision": true, "image_output": true, "pdf_input": true }, "modalities": { "input": [ "file", "image", "text" ], "output": [ "image", "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/QVQ-72B-Preview", "qvq-72b-preview" ], "intro_i18n": { "zh-CN": "QVQ-72B-Preview 是 Qwen 推出的实验性研究模型，专注于提升视觉推理能力。", "zh-TW": "QVQ-72B-Preview 是 Qwen 推出的實驗性研究模型，專注於提升視覺推理能力。", "ja-JP": "QVQ-72B-Previewは、視覚的推論の向上を目的としたQwenの実験的研究モデルです。", "ru-RU": "QVQ-72B-Preview — это экспериментальная исследовательская модель от Qwen, направленная на улучшение визуального рассуждения." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "QVQ 72B Preview" } ] }, { "slug": "alibaba/qvq-max", "model_name": "qvq-max", "display_name": "QVQ Max", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.2" }, "completion": { "unit": "per_M_tokens", "price": "4.8" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.147" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4.588" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "32", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2025-03-25", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qvq", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "open_weights": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qvq-max-2025-03-25", "qvq-max-2025-05-15" ], "intro_i18n": { "zh-CN": "Qwen QVQ 视觉推理模型支持视觉输入与链式思维输出，在数学、编程、视觉分析、创意及通用任务中表现出色。", "zh-TW": "Qwen QVQ 視覺推理模型支援視覺輸入與思維鏈式輸出，在數學、程式碼、視覺分析、創意與通用任務中表現更強。", "ja-JP": "Qwen QVQ視覚推論モデルは、視覚入力と連想的思考出力に対応し、数学、コーディング、視覚分析、創造的タスク、一般タスクにおいて高い性能を発揮します。", "ru-RU": "Модель визуального рассуждения Qwen QVQ поддерживает ввод изображений и вывод в виде цепочки рассуждений, демонстрируя высокую производительность в математике, программировании, визуальном анализе, творческих и общих задачах." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-03", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qvq-plus", "model_name": "qvq-plus", "display_name": "QVQ Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.294118" }, "completion": { "unit": "per_M_tokens", "price": "0.735294" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-05-15", "max_input_tokens": 131072, "max_output_tokens": 8192, "model_type": "vision_understanding", "capabilities": { "reasoning": true, "vision": true, "image_output": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "modalities": { "input": [ "file", "image", "text", "video" ], "output": [ "image", "text", "video" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qvq-plus-2025-05-15" ], "intro_i18n": { "zh-CN": "视觉推理模型，支持视觉输入与链式思维输出。qvq-plus 系列延续 qvq-max，推理更快，质量与成本更优平衡。", "zh-TW": "具備視覺輸入與思維鏈式輸出的視覺推理模型。qvq-plus 系列延續 qvq-max，提供更快速的推理能力與更佳的品質成本平衡。", "ja-JP": "視覚入力と連想的思考出力に対応する視覚推論モデル。qvq-plusシリーズはqvq-maxの後継で、より高速な推論と優れたコストパフォーマンスを実現します。", "ru-RU": "Модель визуального рассуждения с вводом изображений и выводом в виде цепочки рассуждений. Серия qvq-plus следует за qvq-max и обеспечивает более быстрое рассуждение с лучшим соотношением качества и стоимости." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "QVQ Plus" } ] }, { "slug": "alibaba/qwen-coder", "model_name": "qwen-coder", "display_name": "qwen-coder", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models", "max_input_tokens": 1000000, "max_output_tokens": 16384, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "alibaba/qwen-coder-plus", "model_name": "qwen-coder-plus", "display_name": "Qwen Coder Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.514706" }, "completion": { "unit": "per_M_tokens", "price": "1.029412" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true }, "intro": "Qwen coding model for software agents, repository edits, and code reasoning", "released_at": "2024-09-18", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen-coder-plus-2024-11-06" ], "intro_i18n": { "zh-CN": "Qwen 编程模型。", "zh-TW": "Qwen 程式碼模型。", "ja-JP": "Qwenコードモデル。", "ru-RU": "Модель программирования Qwen." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen Coder Plus" } ] }, { "slug": "alibaba/qwen-coder-turbo", "model_name": "qwen-coder-turbo", "display_name": "Qwen Coder Turbo", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.294118" }, "completion": { "unit": "per_M_tokens", "price": "0.882353" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true }, "released_at": "2025-12-30", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen-coder-turbo-2024-09-19" ], "intro_i18n": { "zh-CN": "Qwen 编程模型。", "zh-TW": "Qwen 程式碼模型。", "ja-JP": "Qwenコードモデル。", "ru-RU": "Модель программирования Qwen." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Coder Turbo" } ] }, { "slug": "alibaba/qwen-deep-research", "model_name": "qwen-deep-research", "display_name": "Qwen Deep Research", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "7.742" }, "completion": { "unit": "per_M_tokens", "price": "23.367" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "verification_status": "aggregator_only" } } ], "released_at": "2024-01", "knowledge_cutoff": "2024-04", "max_input_tokens": 1000000, "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "deep_thinking", "family": "qwen", "capabilities": { "function_calling": true, "stream": true }, "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen Deep Research" } ] }, { "slug": "alibaba/qwen-doc-turbo", "model_name": "qwen-doc-turbo", "display_name": "Qwen Doc Turbo", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.087" }, "completion": { "unit": "per_M_tokens", "price": "0.144" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "verification_status": "aggregator_only" } } ], "released_at": "2024-01", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "qwen", "capabilities": { "function_calling": true, "stream": true }, "intro": "Efficient Qwen model for fast chat, extraction, and high-volume workloads", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen Doc Turbo" } ] }, { "slug": "alibaba/qwen-flash", "model_name": "qwen-flash", "display_name": "Qwen Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.05" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.004412" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "lobehub-modelbank" }, "tracks": [ { "label": "Context >256K", "source": "lobehub-modelbank", "charge_sources": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank" } }, { "label": "Context >128K", "source": "lobehub-modelbank", "charge_sources": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank" } }, { "label": "Base pricing", "source": "models-dev+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.05" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.022" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.216" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.05" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >256K", "factor": "1", "charge_factors": { "cache_read": "8" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 256000, "inclusive": false } ] }, { "label": "Context >128K", "factor": "1", "charge_factors": { "cache_read": "4" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Efficient Qwen model for fast chat, extraction, and high-volume workloads", "released_at": "2025-07-28", "knowledge_cutoff": "2024-04", "max_input_tokens": 1000000, "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true, "web_search": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bailian/qwen-flash", "qwen-flash-2025-07-28", "qwen/qwen-flash", "qwen/qwen-flash-2025-07-28" ], "intro_i18n": { "zh-CN": "Qwen Flash 是最快、成本最低的模型，适合处理简单任务。", "zh-TW": "Qwen 最快且成本最低的模型，適用於簡單任務。", "ja-JP": "Qwenモデルの中で最速かつ最も低コスト。シンプルなタスクに最適です。", "ru-RU": "Самая быстрая и недорогая модель Qwen, идеально подходит для простых задач." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "alibaba/Qwen-Image", "model_name": "Qwen-Image", "display_name": "Qwen Image", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.036765" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen-image" } ], "released_at": "2025-08-13", "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true, "pdf_input": true, "prompt_caching": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "max_input_tokens": 0, "max_output_tokens": 0, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "family": "qwen", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen-Image", "fal-ai/qwen-image", "qwen-image", "qwen/qwen-image" ], "intro_i18n": { "zh-CN": "Qwen-Image 是 Qwen 团队推出的 200 亿参数图像生成基础模型，在复杂文本渲染和精确图像编辑方面取得重大突破，尤其擅长高保真中英文文本渲染。支持多行及段落排版，保持排版一致性。除文本渲染外，还支持从写实风格到动漫风格的多种图像风格，以及风格迁移、对象添加/删除、细节增强、文本编辑和姿态控制等高级编辑功能，致力于打造全面的视觉创作基础模型。", "zh-TW": "Qwen-Image 是 Qwen 團隊推出的 20B 參數圖像生成基礎模型，在複雜文字渲染與精準圖像編輯方面取得重大突破，特別擅長中英文高保真文字處理。支援多行與段落排版，保持排版一致性。除文字渲染外，還支援從寫實風格到動漫風格的多樣圖像風格，以及進階編輯功能，如風格轉換、物件新增/刪除、細節增強、文字編輯與姿勢控制，致力於成為全面的視覺創作基礎模型。", "ja-JP": "Qwen-Image は、Qwen チームによる 20B パラメータの画像生成基盤モデルです。複雑なテキスト描画や精密な画像編集において大きな進歩を遂げており、特に中国語／英語の高忠実度テキストに強みを持ちます。複数行や段落レイアウトをサポートし、タイポグラフィの一貫性を保ちます。テキスト描画にとどまらず、写実的スタイルからアニメ風まで幅広いスタイルに対応し、スタイル変換、オブジェクトの追加／削除、ディテール強調、テキスト編集、ポーズ制御などの高度な編集も可能で、包括的なビジュアル創作基盤を目指しています。", "ru-RU": "Qwen-Image — базовая модель генерации изображений с 20 млрд параметров от команды Qwen. Обеспечивает значительный прогресс в сложной визуализации текста и точном редактировании изображений, особенно для китайского и английского языков. Поддерживает многострочные и абзацные макеты с сохранением типографики. Помимо визуализации текста, поддерживает широкий спектр стилей — от фотореализма до аниме, а также продвинутые функции редактирования: перенос стиля, добавление/удаление объектов, улучшение деталей, редактирование текста и управление позой. Стремится стать универсальной основой для визуального творчества." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-15", "kind": "limit", "old": "8192", "new": "0", "note": "max_input_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "4096", "new": "0", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Image" } ] }, { "slug": "alibaba/Qwen-Image-2.0", "model_name": "Qwen-Image-2.0", "display_name": "Qwen Image 2.0", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.029412" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen-image-2.0" } ], "released_at": "2026-03-03", "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true, "prompt_caching": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "max_input_tokens": 8192, "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "family": "qwen", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen-Image-2.0", "qwen-image-2.0" ], "intro_i18n": { "zh-CN": "Qwen-Image-2.0 系列加速版模型将图像生成和图像编辑整合为一体。它支持更专业的文本渲染，指令容量高达 1k token，提供更精细和逼真的视觉纹理，能够对真实场景进行细致入微的描绘，并展现出与提示更强的语义契合度。加速版在模型质量和性能之间实现了最佳平衡。", "zh-TW": "Qwen-Image-2.0 系列加速版模型將圖像生成與圖像編輯整合為一體。它支持更專業的文本渲染，指令容量高達 1k 字元，提供更精緻且逼真的視覺紋理，實現對真實場景的細緻描繪，並展現出與提示語更強的語義貼合性。加速版有效實現了模型質量與性能的最佳平衡。", "ja-JP": "Qwen-Image-2.0シリーズの高速版モデルは、画像生成と画像編集を統合した機能を備えています。最大1kトークンの指示容量で、より専門的なテキストレンダリングをサポートし、洗練されたリアルな視覚テクスチャを提供します。現実的なシーンの詳細な描写を可能にし、プロンプトとの意味的な整合性を強化します。この高速版モデルは、モデルの品質とパフォーマンスの最適なバランスを効果的に実現します。", "ru-RU": "Ускоренная версия модели серии Qwen-Image-2.0 объединяет генерацию изображений и их редактирование в единую функцию. Она поддерживает более профессиональную обработку текста с емкостью до 1k токенов, обеспечивает более утонченные и реалистичные визуальные текстуры, позволяет точно описывать реалистичные сцены и демонстрирует более сильное семантическое соответствие запросам. Ускоренная версия эффективно достигает оптимального баланса между качеством модели и производительностью." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Image 2.0" } ] }, { "slug": "alibaba/qwen-image-2.0-pro-2026-04-22", "model_name": "qwen-image-2.0-pro-2026-04-22", "display_name": "Qwen Image 2.0 Pro", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.073529" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen-image-2.0-pro" } ], "released_at": "2026-03-03", "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true, "prompt_caching": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "max_input_tokens": 8192, "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "family": "qwen", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen-Image-2.0-Pro", "qwen-image-2.0-pro", "qwen-image-2.0-pro-2026-03-03" ], "intro_i18n": { "zh-CN": "Qwen-Image-2.0 系列完整版模型将图像生成与图像编辑能力融合一体。支持更专业的文字渲染，指令容量达 1k tokens；在视觉真实感、细节刻画与语义对齐方面整体大幅增强。完整版在 2.0 系列中提供最强文字呈现与最高真实度。", "zh-TW": "Qwen-Image-2.0 系列完整版將影像生成與影像編輯整合於同一模型，支援更專業的文字呈現（最高可處理 1000 token 指令），提供更細膩真實的視覺質感、精準寫實場景刻畫，並展現與提示詞更強的語意對齊能力。完整版提供 2.0 系列中最強的文字呈現能力及最高的寫實度。", "ja-JP": "Qwen-Image-2.0シリーズのフルバージョンモデルは、画像生成と画像編集を統合した能力を備えています。最大1kトークンの指示容量で、よりプロフェッショナルなテキストレンダリングをサポートし、より繊細でリアルな視覚テクスチャを提供します。リアルなシーンの細かい描写を可能にし、プロンプトとのセマンティックな整合性を強化します。フルバージョンモデルは、2.0シリーズ内で最も強力なテキストレンダリング能力と最高レベルのリアリズムを提供します。", "ru-RU": "Полноценная модель серии Qwen-Image-2.0 объединяет генерацию и редактирование изображений в единой системе. Поддерживает улучшенный рендеринг текста (до 1k токенов), создаёт более реалистичные и детализированные текстуры, обеспечивает точную передачу сцен и более сильное семантическое соответствие подсказкам. Полная версия модели обладает наилучшими возможностями рендеринга текста и реалистичностью в серии 2.0." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Image 2.0 Pro" } ] }, { "slug": "alibaba/Qwen-Image-Edit", "model_name": "Qwen-Image-Edit", "display_name": "Qwen Image Edit", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.044118" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen-image-edit" } ], "released_at": "2025-09-18", "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true, "pdf_input": true, "prompt_caching": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "max_input_tokens": 0, "max_output_tokens": 0, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "family": "qwen", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen-Image-Edit", "fal-ai/qwen-image-edit", "qwen-image-edit", "qwen/qwen-image-edit" ], "intro_i18n": { "zh-CN": "Qwen 团队推出的专业图像编辑模型，支持语义和外观编辑，能够精准编辑中英文文本，并实现高质量的编辑效果，如风格迁移和物体旋转。", "zh-TW": "Qwen 團隊推出的專業圖像編輯模型，支持語義和外觀編輯，精確編輯中英文文本，並能進行高品質的編輯，例如風格轉換和物體旋轉。", "ja-JP": "Qwenチームが提供するプロフェッショナルな画像編集モデルで、意味的および外観的な編集をサポートし、中国語と英語のテキストを正確に編集します。スタイル変換やオブジェクトの回転など、高品質な編集が可能です。", "ru-RU": "Профессиональная модель редактирования изображений от команды Qwen, поддерживающая семантические и визуальные правки, точное редактирование текста на китайском и английском языках, а также высококачественные правки, такие как перенос стиля и вращение объектов." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Image Edit" } ] }, { "slug": "alibaba/Qwen-Image-Edit-Max", "model_name": "Qwen-Image-Edit-Max", "display_name": "Qwen Image Edit Max", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.073529" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen-image-edit-max" } ], "released_at": "2026-01-17", "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen-Image-Edit-Max", "qwen-image-edit-max" ], "intro_i18n": { "zh-CN": "Qwen图像编辑模型支持多图输入和多图输出，能够精确进行图像内文字编辑、对象添加、移除或重新定位、主体动作修改、图像风格转换以及视觉细节增强。", "zh-TW": "Qwen 圖像編輯模型支持多圖輸入和多圖輸出，實現精確的圖像內文本編輯、物體添加、移除或重新定位、主體動作修改、圖像風格轉換以及增強視覺細節。", "ja-JP": "Qwen画像編集モデルは、複数画像の入力と出力をサポートし、画像内のテキスト編集、オブジェクトの追加、削除、移動、被写体のアクション変更、画像スタイルの転送、視覚的な詳細の強化を可能にします。", "ru-RU": "Модель редактирования изображений Qwen поддерживает ввод и вывод нескольких изображений, позволяя точно редактировать текст в изображениях, добавлять, удалять или перемещать объекты, изменять действия субъектов, переносить стили изображений и улучшать визуальные детали." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen Image Edit Max" } ] }, { "slug": "alibaba/qwen-image-edit-plus", "model_name": "qwen-image-edit-plus", "display_name": "Qwen Image Edit Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.029412" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-12-23", "model_type": "image_generation", "capabilities": { "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen-image-edit-plus-2025-10-30", "qwen-image-edit-plus-2025-12-15" ], "intro_i18n": { "zh-CN": "Qwen图像编辑模型支持多图输入和多图输出，能够精确进行图像内文字编辑、对象添加、移除或重新定位、主体动作修改、图像风格转换以及视觉细节增强。", "zh-TW": "Qwen 圖像編輯模型支持多圖輸入和多圖輸出，實現精確的圖像內文本編輯、物體添加、移除或重新定位、主體動作修改、圖像風格轉換以及增強視覺細節。", "ja-JP": "Qwen画像編集モデルは、複数画像の入力と出力をサポートし、画像内のテキスト編集、オブジェクトの追加、削除、移動、被写体のアクション変更、画像スタイルの転送、視覚的な詳細の強化を可能にします。", "ru-RU": "Модель редактирования изображений Qwen поддерживает ввод и вывод нескольких изображений, позволяя точно редактировать текст в изображениях, добавлять, удалять или перемещать объекты, изменять действия субъектов, переносить стили изображений и улучшать визуальные детали." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Image Edit Plus" } ] }, { "slug": "alibaba/Qwen-Image-Max", "model_name": "Qwen-Image-Max", "display_name": "Qwen Image Max", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.073529" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen-image-max" } ], "released_at": "2025-12-31", "model_type": "image_generation", "capabilities": { "image_output": true, "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen-Image-Max", "qwen-image-max", "qwen-image-max-2025-12-30" ], "intro_i18n": { "zh-CN": "Qwen图像生成模型（Max系列）在视觉真实感和自然性方面相比Plus系列有显著提升，有效减少AI生成伪影，并在人物外观、纹理细节和文字渲染方面表现卓越。", "zh-TW": "Qwen 圖像生成模型（Max 系列）在真實感和視覺自然性方面相比 Plus 系列有顯著提升，有效減少 AI 生成的瑕疵，並在人物外觀、紋理細節和文本渲染方面表現出色。", "ja-JP": "Qwen画像生成モデル（Maxシリーズ）は、Plusシリーズと比較してリアリズムと視覚的自然さを強化し、AI生成アーティファクトを効果的に削減します。人間の外見、テクスチャの詳細、テキストレンダリングにおいて優れた性能を示します。", "ru-RU": "Модель генерации изображений Qwen (серия Max) обеспечивает улучшенный реализм и визуальную естественность по сравнению с серией Plus, эффективно снижая артефакты, создаваемые ИИ, и демонстрируя выдающиеся результаты в отображении внешности человека, текстурных деталей и рендеринге текста." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Image Max" } ] }, { "slug": "alibaba/qwen-image-plus", "model_name": "qwen-image-plus", "display_name": "Qwen Image Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.029412" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-01-12", "model_type": "image_generation", "capabilities": { "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen-image-plus-2026-01-09" ], "intro_i18n": { "zh-CN": "支持广泛的艺术风格，特别擅长在图像中渲染复杂文字，能够实现图像与文字的集成布局设计。", "zh-TW": "支持多種藝術風格，特別擅長在圖像中渲染複雜文本，實現圖文一體化的佈局設計。", "ja-JP": "幅広い芸術的スタイルをサポートし、特に画像内の複雑なテキストのレンダリングに優れ、統合された画像とテキストのレイアウトデザインを可能にします。", "ru-RU": "Поддерживает широкий спектр художественных стилей и особенно хорошо справляется с рендерингом сложного текста в изображениях, позволяя интегрированное проектирование макета изображений и текста." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Image Plus" } ] }, { "slug": "alibaba/qwen-long", "model_name": "qwen-long", "display_name": "Qwen Long", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.072" }, "completion": { "unit": "per_M_tokens", "price": "0.287" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.072" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.287" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "released_at": "2025-01-25", "knowledge_cutoff": "2024-04", "max_input_tokens": 10000000, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "qwen", "capabilities": { "function_calling": true, "prompt_caching": true, "stream": true, "pdf_input": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen-long-2025-01-25" ], "intro_i18n": { "zh-CN": "超大规模 Qwen 模型，支持长上下文与跨多文档场景的对话。", "zh-TW": "超大型 Qwen 模型，具備長上下文處理能力，適用於長篇與多文件對話場景。", "ja-JP": "超大規模なQwenモデルで、長文や複数文書にまたがるチャットに対応します。", "ru-RU": "Ультра-крупная модель Qwen с поддержкой длинного контекста и диалогов в рамках одного или нескольких документов." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Long" } ] }, { "slug": "alibaba/qwen-math-plus", "model_name": "qwen-math-plus", "display_name": "Qwen Math Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.574" }, "completion": { "unit": "per_M_tokens", "price": "1.721" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.574" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.721" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "released_at": "2024-08-16", "knowledge_cutoff": "2024-04", "max_input_tokens": 4096, "max_output_tokens": 3072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "qwen", "capabilities": { "function_calling": true, "prompt_caching": true, "stream": true }, "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Qwen Math 是一款专注于数学问题求解的语言模型。", "zh-TW": "Qwen Math 是一款專門用於解決數學問題的語言模型。", "ja-JP": "Qwen Mathは、数学問題の解決に特化した言語モデルです。", "ru-RU": "Qwen Math — языковая модель, специализирующаяся на решении математических задач." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Math Plus" } ] }, { "slug": "alibaba/qwen-math-turbo", "model_name": "qwen-math-turbo", "display_name": "Qwen Math Turbo", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.287" }, "completion": { "unit": "per_M_tokens", "price": "0.861" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.287" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.861" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "released_at": "2024-09-19", "knowledge_cutoff": "2024-04", "max_input_tokens": 4096, "max_output_tokens": 3072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "qwen", "capabilities": { "function_calling": true, "prompt_caching": true, "stream": true }, "intro": "Efficient Qwen model for fast chat, extraction, and high-volume workloads", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Qwen Math 是一款专注于数学问题求解的语言模型。", "zh-TW": "Qwen Math 是一款專門用於解決數學問題的語言模型。", "ja-JP": "Qwen Mathは、数学問題の解決に特化した言語モデルです。", "ru-RU": "Qwen Math — языковая модель, специализирующаяся на решении математических задач." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Math Turbo" } ] }, { "slug": "alibaba/qwen-max", "model_name": "qwen-max", "display_name": "Qwen Max", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+litellm+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.6" }, "completion": { "unit": "per_M_tokens", "price": "6.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.070588" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.345" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.377" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.4", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "9.6", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "released_at": "2024-04-03", "knowledge_cutoff": "2024-04", "max_input_tokens": 32768, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "stream": true, "web_search": true }, "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models", "model_type": "text_generation", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "alibaba/qwen-max", "bailian/qwen-max", "qwen-max-2024-04-03", "qwen-max-2024-04-28", "qwen-max-2024-09-19", "qwen-max-2025-01-25", "qwen/qwen-max" ], "intro_i18n": { "zh-CN": "千亿级超大 Qwen 模型，支持中文、英文等多语言，是当前 Qwen2.5 产品背后的 API 模型。", "zh-TW": "千億級超大型 Qwen 模型，支援中文、英文及其他語言；為目前 Qwen2.5 系列產品背後的 API 模型。", "ja-JP": "千億規模の超大規模Qwenモデルで、中国語、英語など多言語に対応。現在のQwen2.5製品のAPIモデルです。", "ru-RU": "Ультра-крупная модель Qwen с сотнями миллиардов параметров, поддерживающая китайский, английский и другие языки; API-модель, лежащая в основе текущих продуктов Qwen2.5." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "alibaba/qwen-mt-plus", "model_name": "qwen-mt-plus", "display_name": "Qwen-MT Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.46" }, "completion": { "unit": "per_M_tokens", "price": "7.37" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.46" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.259" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "7.37" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.775" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Translation model for multilingual conversion, localization, and cross-language workflows", "released_at": "2025-01", "knowledge_cutoff": "2024-04", "max_input_tokens": 16384, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "prompt_caching": true, "open_weights": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen/qwen-mt-plus" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-06", "kind": "capability", "note": "function_calling: false→true" } ] }, { "slug": "alibaba/qwen-mt-turbo", "model_name": "qwen-mt-turbo", "display_name": "Qwen-MT Turbo", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.16" }, "completion": { "unit": "per_M_tokens", "price": "0.49" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.16" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.101" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.49" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.28" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Translation model for multilingual conversion, localization, and cross-language workflows", "released_at": "2025-01", "knowledge_cutoff": "2024-04", "max_input_tokens": 16384, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "prompt_caching": true, "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen/qwen-mt-turbo" ], "model_type": "text_generation", "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" } ] }, { "slug": "alibaba/qwen-omni-turbo", "model_name": "qwen-omni-turbo", "display_name": "Qwen-Omni Turbo", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.07" }, "completion": { "unit": "per_M_tokens", "price": "0.27" }, "audio_input": { "unit": "per_M_tokens", "price": "4.44" }, "audio_output": { "unit": "per_M_tokens", "price": "8.89" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev", "audio_output": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.07" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.058" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.27" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.23" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.07" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.27" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4.5", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks", "released_at": "2025-01-19", "knowledge_cutoff": "2024-04", "max_input_tokens": 32768, "max_output_tokens": 2048, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "omni", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Qwen-Omni 模型支持多模态输入（视频、音频、图像、文本）并输出音频与文本。", "zh-TW": "Qwen-Omni 模型支援多模態輸入（影片、音訊、圖片、文字）並輸出語音與文字。", "ja-JP": "Qwen-Omniモデルは、動画、音声、画像、テキストなどのマルチモーダル入力に対応し、音声とテキストを出力します。", "ru-RU": "Модели Qwen-Omni поддерживают мультимодальный ввод (видео, аудио, изображения, текст) и вывод в виде аудио и текста." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen-omni-turbo-realtime", "model_name": "qwen-omni-turbo-realtime", "display_name": "Qwen-Omni Turbo Realtime", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.27" }, "completion": { "unit": "per_M_tokens", "price": "1.07" }, "audio_input": { "unit": "per_M_tokens", "price": "4.44" }, "audio_output": { "unit": "per_M_tokens", "price": "8.89" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev", "audio_output": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.27" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.23" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.07" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.918" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks", "released_at": "2025-05-08", "knowledge_cutoff": "2024-04", "max_input_tokens": 32768, "max_output_tokens": 2048, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text", "audio" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "audio_input": true, "audio_output": true, "stream": true }, "model_type": "realtime_omni", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen-plus", "model_name": "qwen-plus", "display_name": "Qwen Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+litellm+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "1.2" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "4" }, "cache_read_0_0_128": { "unit": "per_M_tokens", "price": "0.023529" }, "cache_read_0_128_0_256": { "unit": "per_M_tokens", "price": "0.070588" }, "cache_read_0_256_infinity": { "unit": "per_M_tokens", "price": "0.141176" }, "prompt_0_0_128": { "unit": "per_M_tokens", "price": "0.117647" }, "prompt_0_128_0_256": { "unit": "per_M_tokens", "price": "0.352941" }, "prompt_0_256_infinity": { "unit": "per_M_tokens", "price": "0.705882" }, "completion_0_0_128_false": { "unit": "per_M_tokens", "price": "0.294118" }, "completion_0_0_128_true": { "unit": "per_M_tokens", "price": "1.176471" }, "completion_0_128_0_256_false": { "unit": "per_M_tokens", "price": "2.941176" }, "completion_0_128_0_256_true": { "unit": "per_M_tokens", "price": "3.529412" }, "completion_0_256_infinity_false": { "unit": "per_M_tokens", "price": "7.058824" }, "completion_0_256_infinity_true": { "unit": "per_M_tokens", "price": "9.411765" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "models-dev", "cache_read_0_0_128": "lobehub-modelbank", "cache_read_0_128_0_256": "lobehub-modelbank", "cache_read_0_256_infinity": "lobehub-modelbank", "prompt_0_0_128": "lobehub-modelbank", "prompt_0_128_0_256": "lobehub-modelbank", "prompt_0_256_infinity": "lobehub-modelbank", "completion_0_0_128_false": "lobehub-modelbank", "completion_0_0_128_true": "lobehub-modelbank", "completion_0_128_0_256_false": "lobehub-modelbank", "completion_0_128_0_256_true": "lobehub-modelbank", "completion_0_256_infinity_false": "lobehub-modelbank", "completion_0_256_infinity_true": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.115" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.287" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen-plus-2025-01-25" } ], "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "released_at": "2024-01-25", "knowledge_cutoff": "2024-04", "max_input_tokens": 1000000, "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true, "web_search": true }, "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models", "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "alibaba/qwen-plus", "bailian/qwen-plus", "qwen-plus-2024-07-23", "qwen-plus-2024-08-06", "qwen-plus-2024-09-19", "qwen-plus-2024-11-25", "qwen-plus-2024-11-27", "qwen-plus-2024-12-20", "qwen-plus-2025-01-12", "qwen-plus-2025-01-25", "qwen-plus-2025-04-28", "qwen-plus-2025-07-14", "qwen-plus-2025-07-28", "qwen-plus-2025-09-11", "qwen-plus-2025-12-01", "qwen/qwen-plus", "qwen/qwen-plus-2025-01-25", "qwen/qwen-plus-2025-04-28", "qwen/qwen-plus-2025-07-14", "qwen/qwen-plus-2025-07-28", "qwen/qwen-plus-2025-07-28:thinking", "qwen/qwen-plus-2025-09-11", "qwen/qwen-plus-2025-12-01" ], "intro_i18n": { "zh-CN": "增强版超大 Qwen 模型，支持中文、英文等多语言。", "zh-TW": "增強版超大型 Qwen 模型，支援中文、英文及其他語言。", "ja-JP": "中国語、英語など多言語に対応した強化型超大規模Qwenモデルです。", "ru-RU": "Улучшенная ультра-крупная модель Qwen с поддержкой китайского, английского и других языков." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-08-03", "kind": "capability", "note": "open_weights: true→false" }, { "date": "2026-07-03", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "alibaba/qwen-plus-character", "model_name": "qwen-plus-character", "display_name": "Qwen Plus Character", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.115" }, "completion": { "unit": "per_M_tokens", "price": "0.287" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "verification_status": "aggregator_only" } } ], "released_at": "2024-01", "knowledge_cutoff": "2024-04", "max_input_tokens": 32768, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "qwen", "capabilities": { "function_calling": true, "prompt_caching": true, "stream": true, "structured_output": true, "open_weights": true }, "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen/qwen-plus-character" ], "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-22", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-22", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen Plus Character" } ] }, { "slug": "alibaba/qwen-plus-character-ja", "model_name": "qwen-plus-character-ja", "display_name": "Qwen Plus Character (Japanese)", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.4" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "released_at": "2024-01", "knowledge_cutoff": "2024-04", "max_input_tokens": 8192, "max_output_tokens": 512, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "stream": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen/qwen-plus-character-ja" ], "price_history": [ { "date": "2026-07-25", "kind": "capability", "note": "pdf_input: true→false" }, { "date": "2026-07-06", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-06", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-06", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen-turbo", "model_name": "qwen-turbo", "display_name": "Qwen Turbo", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+litellm+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.05" }, "completion": { "unit": "per_M_tokens", "price": "0.2" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.008824" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "models-dev", "cache_read": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.05" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.044" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.087" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.05" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen-turbo-2024-11-01" } ], "intro": "Efficient Qwen model for fast chat, extraction, and high-volume workloads", "released_at": "2024-11-01", "knowledge_cutoff": "2024-04", "max_input_tokens": 1000000, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "stream": true, "web_search": true }, "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models", "model_type": "text_generation", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "alibaba/qwen-turbo", "bailian/qwen-turbo", "qwen-turbo-2024-06-24", "qwen-turbo-2024-09-19", "qwen-turbo-2024-11-01", "qwen-turbo-2025-02-11", "qwen-turbo-2025-04-28", "qwen-turbo-2025-07-15", "qwen/qwen-turbo" ], "intro_i18n": { "zh-CN": "Qwen Turbo 将不再更新，建议替换为 Qwen Flash。超大 Qwen 模型，支持中文、英文等多语言。", "zh-TW": "Qwen Turbo 將不再更新，請改用 Qwen Flash。超大型 Qwen 模型，支援中文、英文及其他語言。", "ja-JP": "Qwen Turboは今後更新されません。Qwen Flashへの置き換えを推奨します。中国語、英語など多言語に対応した超大規模Qwenモデルです。", "ru-RU": "Qwen Turbo больше не обновляется; рекомендуется заменить на Qwen Flash. Ультра-крупная модель Qwen с поддержкой китайского, английского и других языков." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "alibaba/qwen-turbo-latest", "model_name": "qwen-turbo-latest", "display_name": "qwen-turbo-latest", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.05" }, "completion": { "unit": "per_M_tokens", "price": "0.2" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "internal_reasoning": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models", "max_input_tokens": 1000000, "max_output_tokens": 16384, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true }, "released_at": "2025-08-08", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "alibaba/qwen-vl-max", "model_name": "qwen-vl-max", "display_name": "Qwen-VL Max", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.047059" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.23" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.574" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.6", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2024-04-08", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "vision_understanding", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bailian/qwen-vl-max", "qwen-vl-max-2024-08-09", "qwen-vl-max-2024-10-30", "qwen-vl-max-2024-11-19", "qwen-vl-max-2024-12-30", "qwen-vl-max-2025-01-25", "qwen-vl-max-2025-04-02", "qwen-vl-max-2025-04-08", "qwen-vl-max-2025-08-13", "qwen/qwen-vl-max" ], "intro_i18n": { "zh-CN": "超大 Qwen 视觉语言模型。相比增强版，进一步提升视觉推理与指令跟随能力，具备更强视觉感知与认知能力。", "zh-TW": "超大型 Qwen 視覺語言模型。相較於增強版，進一步提升視覺推理與指令遵循能力，具備更強的視覺感知與認知能力。", "ja-JP": "超大規模Qwenビジョン・ランゲージモデル。強化版と比較して、視覚的推論と指示追従能力がさらに向上し、視覚的知覚と認知が強化されています。", "ru-RU": "Ультра-крупная мультимодальная модель Qwen. По сравнению с улучшенной версией, она еще больше усиливает визуальное рассуждение и следование инструкциям, обеспечивая более сильное визуальное восприятие и когнитивные способности." }, "price_history": [ { "date": "2026-08-07", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-13", "kind": "capability", "note": "prompt_caching: true→false" }, { "date": "2026-07-03", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "alibaba/qwen-vl-ocr", "model_name": "qwen-vl-ocr", "display_name": "Qwen-VL OCR", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.72" }, "completion": { "unit": "per_M_tokens", "price": "0.72" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.72" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.717" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.72" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.717" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.72" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.72" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "OCR model for extracting structured text from documents and screenshots", "released_at": "2024-10-28", "knowledge_cutoff": "2024-04", "max_input_tokens": 34096, "max_output_tokens": 4096, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "prompt_caching": true, "open_weights": true, "pdf_input": true, "image_output": true }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen-vl-ocr-2025-11-20", "qwen/qwen-vl-ocr", "qwen/qwen-vl-ocr-2025-11-20" ], "intro_i18n": { "zh-CN": "Qwen OCR 是一款用于文档、表格、考试图片和手写文字的文本提取模型，支持中文、英文、法语、日语、韩语、德语、俄语、意大利语、越南语和阿拉伯语。", "zh-TW": "Qwen OCR 是一款文字擷取模型，適用於文件、表格、考卷圖片與手寫文字。支援中文、英文、法文、日文、韓文、德文、俄文、義大利文、越南文與阿拉伯文。", "ja-JP": "Qwen OCRは、文書、表、試験画像、手書き文字からのテキスト抽出モデルです。中国語、英語、フランス語、日本語、韓国語、ドイツ語、ロシア語、イタリア語、ベトナム語、アラビア語に対応します。", "ru-RU": "Qwen OCR — это модель извлечения текста из документов, таблиц, экзаменационных изображений и рукописного текста. Поддерживает китайский, английский, французский, японский, корейский, немецкий, русский, итальянский, вьетнамский и арабский языки." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "alibaba/qwen-vl-plus", "model_name": "qwen-vl-plus", "display_name": "Qwen-VL Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.21" }, "completion": { "unit": "per_M_tokens", "price": "0.63" }, "cache_read": { "unit": "per_M_tokens", "price": "0.023529" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.21" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.115" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.63" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.287" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.21" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.8", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.63" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2024-01-25", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "vision_understanding", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen-vl-plus-2024-08-09", "qwen-vl-plus-2025-01-02", "qwen-vl-plus-2025-01-25", "qwen-vl-plus-2025-05-07", "qwen-vl-plus-2025-07-10", "qwen-vl-plus-2025-08-15", "qwen/qwen-vl-plus" ], "intro_i18n": { "zh-CN": "增强版大规模 Qwen 视觉语言模型，在细节和文本识别方面有显著提升，支持超过百万像素分辨率和任意宽高比。", "zh-TW": "增強版大型 Qwen 視覺語言模型，在細節與文字識別方面有重大提升，支援超過百萬像素解析度與任意長寬比。", "ja-JP": "詳細とテキスト認識において大幅な性能向上を実現した強化型大規模Qwenビジョン・ランゲージモデル。100万画素以上の解像度と任意のアスペクト比に対応します。", "ru-RU": "Улучшенная крупномасштабная мультимодальная модель Qwen с заметным улучшением детализации и распознавания текста, поддерживающая разрешение более одного мегапикселя и произвольные соотношения сторон." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "alibaba/qwen2-5-14b-instruct", "model_name": "qwen2-5-14b-instruct", "display_name": "Qwen2.5 14B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.35" }, "completion": { "unit": "per_M_tokens", "price": "1.4" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.35" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.144" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.431" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.35" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen2.5-14b-instruct" } ], "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "released_at": "2024-09", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "open_weights": true, "stream": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen2.5-14B-Instruct", "qwen2.5-14b-instruct" ], "intro_i18n": { "zh-CN": "Qwen2.5-14B-Instruct 是阿里云最新大语言模型系列的一部分。该 14B 模型在编程和数学方面有显著提升，支持 29 种以上语言，并在指令理解、结构化数据理解和结构化输出（尤其是 JSON）方面表现更优。", "zh-TW": "Qwen2.5-14B-Instruct 是阿里雲最新 LLM 系列的一部分。此 14B 模型在程式碼與數學方面有顯著提升，支援超過 29 種語言，並強化指令遵循、結構化資料理解與結構化輸出（特別是 JSON）。", "ja-JP": "Qwen2.5-14B-Instruct は、Alibaba Cloud の最新 LLM シリーズの一部です。14B モデルはコーディングと数学において顕著な向上を示し、29 以上の言語をサポートし、命令追従、構造化データの理解、構造化出力（特に JSON）を改善しています。", "ru-RU": "Qwen2.5-14B-Instruct — часть последней серии LLM от Alibaba Cloud. Модель с 14 млрд параметров демонстрирует значительный прогресс в программировании и математике, поддерживает более 29 языков и улучшает выполнение инструкций, понимание структурированных данных и генерацию структурированного вывода (особенно JSON)." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen2-5-14b-instruct-1m", "model_name": "qwen2-5-14b-instruct-1m", "display_name": "Qwen2.5 14B 1M", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.147059" }, "completion": { "unit": "per_M_tokens", "price": "0.441176" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen2.5-14b-instruct-1m" } ], "released_at": "2025-01-27", "max_input_tokens": 1000000, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen2.5-14b-instruct-1m" ], "intro_i18n": { "zh-CN": "Qwen2.5 开源 72B 模型。", "zh-TW": "Qwen2.5 開源 72B 模型。", "ja-JP": "Qwen2.5のオープンソース72Bモデルです。", "ru-RU": "Открытая модель Qwen2.5 с 72 миллиардами параметров." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen2.5 14B 1M" } ] }, { "slug": "alibaba/qwen2-5-32b-instruct", "model_name": "qwen2-5-32b-instruct", "display_name": "Qwen2.5 32B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.7" }, "completion": { "unit": "per_M_tokens", "price": "2.8" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.287" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.861" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen2.5-32b-instruct" } ], "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "released_at": "2024-09", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "open_weights": true, "stream": true }, "model_type": "text_generation", "docs_url": "https://nebius.com/prices-ai-studio", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen2.5-32B-Instruct", "Qwen2.5-32B-Instruct", "qwen/qwen2.5-32b-instruct", "qwen2.5-32b-instruct" ], "intro_i18n": { "zh-CN": "Qwen2.5-32B-Instruct 是阿里云最新大语言模型系列的一部分。该 32B 模型在编程和数学方面有显著提升，支持 29 种以上语言，并在指令理解、结构化数据理解和结构化输出（尤其是 JSON）方面表现更优。", "zh-TW": "Qwen2.5-32B-Instruct 是阿里雲最新 LLM 系列的一部分。此 32B 模型在程式碼與數學方面有顯著提升，支援超過 29 種語言，並強化指令遵循、結構化資料理解與結構化輸出（特別是 JSON）。", "ja-JP": "Qwen2.5-32B-Instruct は、Alibaba Cloud の最新 LLM シリーズの一部です。32B モデルはコーディングと数学において顕著な向上を示し、29 以上の言語をサポートし、命令追従、構造化データの理解、構造化出力（特に JSON）を改善しています。", "ru-RU": "Qwen2.5-32B-Instruct — часть последней серии LLM от Alibaba Cloud. Модель с 32 млрд параметров демонстрирует значительный прогресс в программировании и математике, поддерживает более 29 языков и улучшает выполнение инструкций, понимание структурированных данных и генерацию структурированного вывода (особенно JSON)." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen2-5-72b-instruct", "model_name": "qwen2-5-72b-instruct", "display_name": "Qwen2.5 72B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.4" }, "completion": { "unit": "per_M_tokens", "price": "5.6" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.574" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "5.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.721" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "5.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen2.5-72b-instruct" } ], "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "released_at": "2024-09", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true, "parallel_function_calling": true }, "model_type": "text_generation", "docs_url": "https://nebius.com/prices-ai-studio", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen2.5-72B-Instruct", "Qwen2.5-72B-Instruct", "deepinfra/Qwen/Qwen2.5-72B-Instruct", "qwen/qwen2.5-72b-instruct", "qwen2.5-72b-instruct" ], "intro_i18n": { "zh-CN": "Qwen2.5-72B-Instruct 是阿里云最新大语言模型系列的一部分。该 72B 模型在编程和数学方面有显著提升，支持 29 种以上语言，并在指令理解、结构化数据理解和结构化输出（尤其是 JSON）方面表现更优。", "zh-TW": "Qwen2.5-72B-Instruct 是阿里雲最新 LLM 系列的一部分。此 72B 模型在程式碼與數學方面有顯著提升，支援超過 29 種語言，並強化指令遵循、結構化資料理解與結構化輸出（特別是 JSON）。", "ja-JP": "Qwen2.5-72B-Instruct は、Alibaba Cloud の最新 LLM シリーズの一部です。72B モデルはコーディングと数学において顕著な向上を示し、29 以上の言語をサポートし、命令追従、構造化データの理解、構造化出力（特に JSON）を改善しています。", "ru-RU": "Qwen2.5-72B-Instruct — часть последней серии LLM от Alibaba Cloud. Модель с 72 млрд параметров демонстрирует значительный прогресс в программировании и математике, поддерживает более 29 языков и улучшает выполнение инструкций, понимание структурированных данных и генерацию структурированного вывода (особенно JSON)." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59302932", "new": "0.5929366" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59302932", "new": "0.5929366" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59298112", "new": "0.59302932" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59298112", "new": "0.59302932" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59280156", "new": "0.59298112" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59280156", "new": "0.59298112" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59275852", "new": "0.59280156" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59275852", "new": "0.59280156" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59282352", "new": "0.59275852" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59282352", "new": "0.59275852" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59283312", "new": "0.59282352" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59283312", "new": "0.59282352" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59278692", "new": "0.59283312" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59278692", "new": "0.59283312" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59193576", "new": "0.59278692" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59193576", "new": "0.59278692" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.5923134", "new": "0.59193576" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.5923134", "new": "0.59193576" } ] }, { "slug": "alibaba/qwen2-5-7b-instruct", "model_name": "qwen2-5-7b-instruct", "display_name": "Qwen2.5 7B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.175" }, "completion": { "unit": "per_M_tokens", "price": "0.7" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.175" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.072" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.144" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.175" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen2.5-7b-instruct" } ], "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "released_at": "2024-09", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "open_weights": true, "stream": true, "parallel_function_calling": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Pro/Qwen/Qwen2.5-7B-Instruct", "Qwen/Qwen2.5-7B-Instruct", "Qwen2.5-7B-Instruct", "qwen/qwen2.5-7b-instruct", "qwen2.5-7b-instruct" ], "intro_i18n": { "zh-CN": "Qwen2.5-7B-Instruct 是阿里云最新大模型系列的一部分。该 70 亿参数模型在编程和数学方面有显著提升，支持 29+ 种语言，增强了指令理解、结构化数据处理和结构化输出（特别是 JSON）。", "zh-TW": "Qwen2.5-7B-Instruct 是阿里雲最新大型語言模型系列的一部分。此 70 億參數模型在程式碼與數學方面有顯著提升，支援超過 29 種語言，並加強了指令遵循、結構化資料理解與結構化輸出（特別是 JSON）能力。", "ja-JP": "Qwen2.5-7B-Instructは、Alibaba Cloudの最新LLMシリーズの一部です。7Bモデルは、コーディングと数学で顕著な向上を示し、29以上の言語をサポート。命令追従、構造化データの理解、構造化出力（特にJSON）を改善しています。", "ru-RU": "Qwen2.5-7B-Instruct входит в последнюю серию LLM от Alibaba Cloud. Модель на 7B параметров демонстрирует значительный прогресс в программировании и математике, поддерживает более 29 языков и улучшает следование инструкциям, понимание структурированных данных и структурированный вывод (особенно JSON)." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen2-5-coder-14b-instruct", "model_name": "qwen2-5-coder-14b-instruct", "display_name": "Qwen2.5 Coder 14B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.294118" }, "completion": { "unit": "per_M_tokens", "price": "0.882353" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen2.5-coder-14b-instruct" } ], "max_input_tokens": 131072, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true }, "released_at": "2025-12-30", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen2.5-coder-14b-instruct" ], "intro_i18n": { "zh-CN": "Qwen2.5-Coder-14B-Instruct 是一款大规模预训练的编程指令模型，具备强大的代码理解与生成能力，能够高效处理多种编程任务，适用于智能编程、自动脚本生成与编程问答。", "zh-TW": "Qwen2.5-Coder-14B-Instruct 是一款大型預訓練程式指令模型，具備強大的程式理解與生成能力。能高效處理各類程式任務，適用於智慧編碼、自動腳本生成與程式問答。", "ja-JP": "Qwen2.5-Coder-14B-Instructは、大規模な事前学習済みのコーディング指示モデルで、コードの理解と生成に優れています。幅広いプログラミングタスクを効率的に処理でき、スマートコーディング、自動スクリプト生成、プログラミングQ&Aに最適です。", "ru-RU": "Qwen2.5-Coder-14B-Instruct — это крупномасштабная предварительно обученная модель для программирования, обладающая высокой способностью к пониманию и генерации кода. Она эффективно справляется с широким спектром задач программирования, идеально подходит для интеллектуального кодирования, автоматической генерации скриптов и вопросов по программированию." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen2.5 Coder 14B" } ] }, { "slug": "alibaba/qwen2-5-coder-32b-instruct", "model_name": "qwen2-5-coder-32b-instruct", "display_name": "Qwen2.5-Coder 32B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.287" }, "completion": { "unit": "per_M_tokens", "price": "0.861" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.287" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.861" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen2.5-coder-32b-instruct" } ], "released_at": "2024-11", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "stream": true, "structured_output": true, "open_weights": true, "parallel_function_calling": true }, "intro": "Qwen coding model for software agents, repository edits, and code reasoning", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "@cf/qwen/qwen2.5-coder-32b-instruct", "Qwen/Qwen2.5-Coder-32B-Instruct", "Qwen2.5-Coder-32B-Instruct", "deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct", "hf:Qwen/Qwen2.5-Coder-32B-Instruct", "qwen/Qwen2.5-Coder-32B-Instruct", "qwen/qwen2.5-coder-32b-instruct", "qwen2.5-coder-32b-instruct", "workers-ai/@cf/qwen/qwen2.5-coder-32b-instruct" ], "intro_i18n": { "zh-CN": "Qwen2.5 Coder 32B Instruct 是阿里云最新面向编程的大语言模型。基于 Qwen2.5 构建，并使用 5.5 万亿 tokens 进行训练，在代码生成、推理和修复方面有显著提升，同时保留数学和通用能力，为构建编程智能体提供强大基础。", "zh-TW": "Qwen2.5 Coder 32B Instruct 是阿里雲最新專注於程式碼的 LLM。基於 Qwen2.5 並使用 5.5T token 訓練，顯著提升程式碼生成、推理與修復能力，同時保有數學與通用能力，為程式代理提供強大基礎。", "ja-JP": "Qwen2.5 Coder 32B Instruct は、Alibaba Cloud による最新のコード特化型 LLM です。Qwen2.5 を基盤とし、5.5T トークンで訓練されており、コード生成、推論、修復を大幅に改善し、数学および一般的な能力も維持しています。コーディングエージェントの強力な基盤を提供します。", "ru-RU": "Qwen2.5 Coder 32B Instruct — последняя модель от Alibaba Cloud, ориентированная на программирование. Построена на базе Qwen2.5 и обучена на 5.5 трлн токенов, значительно улучшает генерацию кода, логическое мышление и исправление ошибок, сохраняя при этом сильные стороны в математике и общем понимании, обеспечивая надёжную основу для кодирующих агентов." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen2.5-Coder 32B Instruct" } ] }, { "slug": "alibaba/qwen2-5-coder-7b-instruct", "model_name": "qwen2-5-coder-7b-instruct", "display_name": "Qwen2.5-Coder 7B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.144" }, "completion": { "unit": "per_M_tokens", "price": "0.287" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.144" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.287" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen2.5-coder-7b-instruct" } ], "released_at": "2024-11", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "qwen", "capabilities": { "function_calling": true, "stream": true, "structured_output": true, "open_weights": true }, "intro": "Qwen coding model for software agents, repository edits, and code reasoning", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen2.5-Coder-7B-Instruct", "qwen/qwen2.5-coder-7b-instruct", "qwen2.5-coder-7b-instruct" ], "intro_i18n": { "zh-CN": "开源 Qwen 编程模型。", "zh-TW": "開源 Qwen 程式碼模型。", "ja-JP": "オープンソースのQwenコードモデルです。", "ru-RU": "Открытая модель кода Qwen." }, "price_history": [ { "date": "2026-07-16", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-15", "kind": "capability", "note": "structured_output: true→false" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen2.5-Coder 7B Instruct" } ] }, { "slug": "alibaba/qwen2-5-math-72b-instruct", "model_name": "qwen2-5-math-72b-instruct", "display_name": "Qwen2.5-Math 72B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.574" }, "completion": { "unit": "per_M_tokens", "price": "1.721" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.574" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.721" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen2.5-math-72b-instruct" } ], "released_at": "2024-09", "knowledge_cutoff": "2024-04", "max_input_tokens": 4096, "max_output_tokens": 3072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "qwen", "capabilities": { "function_calling": true, "stream": true, "open_weights": true }, "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen2.5-math-72b-instruct" ], "intro_i18n": { "zh-CN": "Qwen-Math 在数学问题求解方面表现出色。", "zh-TW": "Qwen-Math 擅長數學問題解決。", "ja-JP": "Qwen-Mathは、数学問題の解決に優れた性能を発揮します。", "ru-RU": "Qwen-Math демонстрирует высокую эффективность в решении математических задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen2.5-Math 72B Instruct" } ] }, { "slug": "alibaba/qwen2-5-math-7b-instruct", "model_name": "qwen2-5-math-7b-instruct", "display_name": "Qwen2.5-Math 7B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.144" }, "completion": { "unit": "per_M_tokens", "price": "0.287" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.144" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.287" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen2.5-math-7b-instruct" } ], "released_at": "2024-09", "knowledge_cutoff": "2024-04", "max_input_tokens": 4096, "max_output_tokens": 3072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "qwen", "capabilities": { "function_calling": true, "stream": true, "open_weights": true }, "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen2.5-math-7b-instruct" ], "intro_i18n": { "zh-CN": "Qwen-Math 在数学问题求解方面表现出色。", "zh-TW": "Qwen-Math 擅長數學問題解決。", "ja-JP": "Qwen-Mathは、数学問題の解決に優れた性能を発揮します。", "ru-RU": "Qwen-Math демонстрирует высокую эффективность в решении математических задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen2.5-Math 7B Instruct" } ] }, { "slug": "alibaba/qwen2-5-omni-7b", "model_name": "qwen2-5-omni-7b", "display_name": "Qwen2.5-Omni 7B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "audio_input": { "unit": "per_M_tokens", "price": "6.76" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.087" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.345" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen2.5-omni-7b" } ], "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks", "released_at": "2024-12", "knowledge_cutoff": "2024-04", "max_input_tokens": 32768, "max_output_tokens": 2048, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "audio_input": true, "audio_output": true, "video_input": true, "open_weights": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "omni", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen2.5-omni-7b" ], "intro_i18n": { "zh-CN": "Qwen-Omni 模型支持多模态输入（视频、音频、图像、文本）并输出音频与文本。", "zh-TW": "Qwen-Omni 模型支援多模態輸入（影片、音訊、圖片、文字）並可輸出語音與文字。", "ja-JP": "Qwen-Omniモデルは、動画、音声、画像、テキストなどのマルチモーダル入力に対応し、音声およびテキスト出力を生成します。", "ru-RU": "Модели Qwen-Omni поддерживают мультимодальные входные данные (видео, аудио, изображения, текст) и вывод в виде аудио и текста." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen2-5-vl-32b-instruct", "model_name": "qwen2-5-vl-32b-instruct", "display_name": "Qwen2.5 VL 32B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.176471" }, "completion": { "unit": "per_M_tokens", "price": "3.529412" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen2.5-vl-32b-instruct" } ], "released_at": "2025-03-24", "max_input_tokens": 131072, "max_output_tokens": 8192, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "vision": true, "image_output": true, "video_input": true, "pdf_input": true, "open_weights": true, "prompt_caching": true, "stream": true }, "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "knowledge_cutoff": "2024-09", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen2.5-VL-32B-Instruct", "Qwen2.5-VL-32B-Instruct", "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct", "qwen/qwen2.5-vl-32b-instruct", "qwen2.5-vl-32b-instruct", "qwen2.5-vl-32b-instruct:free" ], "intro_i18n": { "zh-CN": "Qwen2.5VL系列模型在数学和主题问答方面接近Qwen2.5VL-72B的性能。响应风格经过调优以符合人类偏好，特别是针对数学、逻辑推理和知识问答等客观查询，输出更清晰、更详细。这是32B版本。", "zh-TW": "Qwen2.5VL 系列模型在數學和主題問答方面接近 Qwen2.5VL-72B 的性能。響應風格根據人類偏好進行調整，特別是針對數學、邏輯推理和知識問答等客觀查詢，輸出更清晰和詳細。這是32B版本。", "ja-JP": "Qwen2.5VLシリーズモデルで、数学や主題QAにおいてQwen2.5VL-72Bに近い性能を達成しています。応答スタイルは人間の好みに合わせて調整されており、特に数学、論理的推論、知識QAのような客観的なクエリに対して、より明確で詳細な出力を提供します。これは32Bバージョンです。", "ru-RU": "Модель серии Qwen2.5VL, достигающая почти уровня производительности Qwen2.5VL-72B в математике и предметных вопросах. Стиль ответов настроен для предпочтений человека, особенно для объективных запросов, таких как математика, логическое рассуждение и вопросы знаний, с более четкими и детализированными выводами. Это версия с 32B параметрами." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen2.5 VL 32B" } ] }, { "slug": "alibaba/qwen2-5-vl-72b-instruct", "model_name": "qwen2-5-vl-72b-instruct", "display_name": "Qwen2.5-VL 72B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.8" }, "completion": { "unit": "per_M_tokens", "price": "8.4" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.294" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "8.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6.881" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "16", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "8.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "48", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen2.5-vl-72b-instruct" } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2024-09", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "vision_understanding", "parameters": { "unsupported": [ "temperature" ] }, "docs_url": "https://nebius.com/prices-ai-studio", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen2.5-VL-72B-Instruct", "Qwen2.5-VL-72B-Instruct", "TEE/qwen2.5-vl-72b-instruct", "qwen/qwen2.5-vl-72b-instruct", "qwen2.5-vl-72b-instruct", "qwen2.5-vl-72b-instruct:free" ], "intro_i18n": { "zh-CN": "提升了指令跟随、数学、问题求解与编程能力，具备更强的通用物体识别能力。支持跨格式视觉元素精准定位、最长 10 分钟视频理解（秒级事件定位）、时间顺序与速度理解，以及可解析与定位的操作系统或移动端代理控制。具备强大的关键信息提取与 JSON 输出能力。此为 72B 系列中最强版本。", "zh-TW": "強化指令遵循、數學、問題解決與程式能力，具備更強的物體辨識能力。支援跨格式精準視覺元素定位、長影片理解（最長 10 分鐘）、事件時間點與順序理解、速度感知，以及可控制作業系統或行動裝置的代理。具備強大的關鍵資訊擷取與 JSON 輸出能力。此為系列中最強的 72B 版本。", "ja-JP": "指示追従、数学、問題解決、コーディングの性能が向上し、一般的な物体認識も強化されています。形式を問わず正確な視覚要素の位置特定、10分までの長時間動画理解、秒単位のイベントタイミング、時間順序や速度の理解、OSやモバイルを操作可能なエージェント機能を備えています。重要情報の抽出やJSON出力にも優れています。これはシリーズ中最強の72Bバージョンです。", "ru-RU": "Улучшенное следование инструкциям, решение задач, математика и программирование, а также более точное распознавание объектов. Поддерживает точную локализацию визуальных элементов в различных форматах, понимание длинных видео (до 10 минут) с точной временной разметкой событий, определением порядка и скорости, а также агентов, способных управлять ОС или мобильными устройствами через парсинг и локализацию. Эффективное извлечение ключевой информации и вывод в формате JSON. Это версия 72B — самая мощная в серии." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "alibaba/qwen2-5-vl-7b-instruct", "model_name": "qwen2-5-vl-7b-instruct", "display_name": "Qwen2.5-VL 7B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.35" }, "completion": { "unit": "per_M_tokens", "price": "1.05" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.35" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.287" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.05" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.717" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.35" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.05" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen2.5-vl-7b-instruct" } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2024-09", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "audio_input": true, "video_input": true, "open_weights": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen2.5-VL-7B-Instruct", "qwen2.5-vl-7b-instruct" ], "intro_i18n": { "zh-CN": "改进了指令遵循、数学、问题解决和编程能力，具有更强的通用对象识别能力。支持跨格式的精确视觉元素定位、长视频理解（最长 10 分钟）以及秒级事件时间、时间顺序和速度理解，并支持通过解析和定位控制操作系统或移动设备的代理。具有强大的关键信息提取和 JSON 输出能力。这是该系列中最强的 720 亿参数版本。", "zh-TW": "改進了指令跟隨、數學、問題解決和編程能力，具有更強的通用物體識別能力。支持跨格式的精確視覺元素定位、長視頻理解（最多 10 分鐘），包括秒級事件定時、時間順序和速度理解，以及能通過解析和定位控制操作系統或移動設備的代理。具有強大的關鍵信息提取和 JSON 輸出能力。這是系列中最強的 72B 版本。", "ja-JP": "指示追従、数学、問題解決、コーディングが改善され、より強力な一般物体認識を備えています。形式を超えた正確な視覚要素のローカリゼーション、10分間の長時間ビデオ理解、秒単位のイベントタイミング、時間順序および速度理解、OSやモバイルを制御できるエージェントをサポートします。強力な重要情報抽出とJSON出力を提供します。これはシリーズ中で最も強力な72Bバージョンです。", "ru-RU": "Улучшенное выполнение инструкций, математика, решение задач и программирование с более сильным общим распознаванием объектов. Поддерживает точное локализованное определение визуальных элементов в различных форматах, понимание длинных видео (до 10 минут) с точным определением событий на уровне секунд, временным упорядочением и пониманием скорости, а также агентов, которые могут управлять ОС или мобильными устройствами через парсинг и локализацию. Сильное извлечение ключевой информации и вывод JSON. Это самая мощная версия в серии с 72 миллиардами параметров." }, "price_history": [ { "date": "2026-07-16", "kind": "capability", "note": "structured_output: true→false" }, { "date": "2026-07-06", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen3-0-6b", "model_name": "qwen3-0-6b", "display_name": "Qwen3 0.6B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.044118" }, "completion": { "unit": "per_M_tokens", "price": "0.441176" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-0.6b" } ], "released_at": "2025-04-28", "max_input_tokens": 32768, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen3-0.6b" ], "intro_i18n": { "zh-CN": "Qwen3是下一代同义Qwen模型，在推理、通用能力、代理能力和多语言性能方面取得了重大进展，并支持切换思维模式。", "zh-TW": "Qwen3 是下一代同意 Qwen 模型，在推理、通用能力、代理能力和多語言性能方面取得重大進展，並支持切換思考模式。", "ja-JP": "Qwen3は次世代のTongyi Qwenモデルで、推論、汎用能力、エージェント機能、多言語性能において大幅な向上を実現し、思考モードの切り替えをサポートします。", "ru-RU": "Qwen3 — это модель следующего поколения Tongyi Qwen с значительными улучшениями в рассуждении, общих способностях, агентных возможностях и многоязычной производительности, поддерживающая переключение режимов мышления." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen3 0.6B" } ] }, { "slug": "alibaba/qwen3-1-7b", "model_name": "qwen3-1-7b", "display_name": "Qwen3 1.7B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.044118" }, "completion": { "unit": "per_M_tokens", "price": "0.441176" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-1.7b" } ], "released_at": "2025-04-28", "max_input_tokens": 32768, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen3-1.7b" ], "intro_i18n": { "zh-CN": "Qwen3是下一代同义Qwen模型，在推理、通用能力、代理能力和多语言性能方面取得了重大进展，并支持切换思维模式。", "zh-TW": "Qwen3 是下一代同意 Qwen 模型，在推理、通用能力、代理能力和多語言性能方面取得重大進展，並支持切換思考模式。", "ja-JP": "Qwen3は次世代のTongyi Qwenモデルで、推論、汎用能力、エージェント機能、多言語性能において大幅な向上を実現し、思考モードの切り替えをサポートします。", "ru-RU": "Qwen3 — это модель следующего поколения Tongyi Qwen с значительными улучшениями в рассуждении, общих способностях, агентных возможностях и многоязычной производительности, поддерживающая переключение режимов мышления." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen3 1.7B" } ] }, { "slug": "alibaba/qwen3-14b", "model_name": "qwen3-14b", "display_name": "Qwen3 14B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.35" }, "completion": { "unit": "per_M_tokens", "price": "1.4" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "4.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.35" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.144" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.574" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.35" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "released_at": "2025-04", "knowledge_cutoff": "2025-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 128 }, "docs_url": "https://nebius.com/prices-ai-studio", "deprecated": true, "benchmarks": { "intelligence_index": 10.4, "coding_index": 13.8, "agentic_index": 1.9 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-14B", "Qwen3-14B", "accounts/fireworks/models/qwen3-14b", "deepinfra/Qwen/Qwen3-14B", "qwen/qwen3-14b", "qwen3-14b:free" ], "intro_i18n": { "zh-CN": "Qwen3 是新一代通义千问模型，在推理能力、通用能力、智能体能力和多语言表现方面有重大提升，支持思维模式切换。", "zh-TW": "Qwen3 是新一代通義千問模型，在推理、通用能力、代理能力與多語言表現方面取得重大突破，並支援思維模式切換。", "ja-JP": "Qwen3は、次世代のTongyi Qwenモデルであり、推論能力、汎用性、エージェント機能、多言語対応において大幅な向上を実現しています。思考モードの切り替えにも対応しています。", "ru-RU": "Qwen3 — это модель нового поколения Tongyi Qwen с существенными улучшениями в области рассуждений, общей способности, агентных возможностей и многоязычной производительности. Поддерживает переключение режимов мышления." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "1.29", "new": "2.65" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.33", "new": "0.38" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.74117075", "new": "0.74140805" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.74117075", "new": "0.74140805" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.74128665", "new": "0.74117075" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.74128665", "new": "0.74117075" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.7412264", "new": "0.74128665" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.7412264", "new": "0.74128665" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.74100195", "new": "0.7412264" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.74100195", "new": "0.7412264" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.74094815", "new": "0.74100195" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.74094815", "new": "0.74100195" }, { "date": "2026-08-10", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "0.91", "new": "0.24" }, { "date": "2026-08-10", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.2275", "new": "0.12" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.87", "new": "1.29" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.21", "new": "0.33" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.7410294", "new": "0.74094815" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.7410294", "new": "0.74094815" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.7410414", "new": "0.7410294" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.7410414", "new": "0.7410294" } ] }, { "slug": "alibaba/qwen3-235b-a22b", "model_name": "qwen3-235b-a22b", "display_name": "Qwen3 235B-A22B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.7" }, "completion": { "unit": "per_M_tokens", "price": "2.8" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "8.4" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.287" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.147" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Large open Qwen MoE for multilingual reasoning, coding, and tool use", "released_at": "2025-04", "knowledge_cutoff": "2025-04", "max_input_tokens": 131072, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1 }, "docs_url": "https://nebius.com/prices-ai-studio", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-235B-A22B", "Qwen3-235B-A22B", "accounts/fireworks/models/qwen3-235b-a22b", "deepinfra/Qwen/Qwen3-235B-A22B", "qwen/qwen3-235b-a22b", "qwen3-235b-a22b:free" ], "intro_i18n": { "zh-CN": "Qwen3 235B A22B 是 Qwen3 的超大规模模型，提供顶级的 AI 能力。", "zh-TW": "Qwen3 235B A22B 是 Qwen3 超大規模模型，提供頂級 AI 能力。", "ja-JP": "Qwen3 235B A22Bは、トップクラスのAI能力を提供するQwen3の超大規模モデルです。", "ru-RU": "Qwen3 235B A22B — это ультрамасштабная модель Qwen3, обеспечивающая первоклассные возможности ИИ." }, "price_history": [ { "date": "2026-07-11", "kind": "capability", "note": "vision: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "alibaba/Qwen3-235B-A22B-Instruct-2507", "model_name": "Qwen3-235B-A22B-Instruct-2507", "display_name": "Qwen3 235B A22B Instruct 2507", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.294118" }, "completion": { "unit": "per_M_tokens", "price": "1.176471" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-235b-a22b-instruct-2507" } ], "released_at": "2025-07-22", "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "vision": true, "pdf_input": true, "open_weights": true, "prompt_caching": true, "parallel_function_calling": true, "stream": true }, "intro": "Tool-capable chat model for instruction following and agentic application workflows", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "knowledge_cutoff": "2025-04", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-235B-A22B-Instruct-2507", "accounts/fireworks/models/qwen3-235b-a22b-instruct-2507", "anthropic/pioneer/Qwen/Qwen3-235B-A22B-Instruct-2507", "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507", "hf:Qwen/Qwen3-235B-A22B-Instruct-2507", "nebius/qwen/qwen3-235b-a22b-instruct-2507", "qwen/Qwen3-235B-A22B-Instruct-2507", "qwen/qwen3-235b-a22b-instruct-2507", "qwen3-235b-a22b-instruct-2507" ], "intro_i18n": { "zh-CN": "Qwen3 非思维模式开源模型。与上一版本（Qwen3-235B-A22B）相比，主观创造力和模型安全性略有提升。", "zh-TW": "Qwen3 非思維開源模型。與之前版本（Qwen3-235B-A22B）相比，主觀創造力和模型安全性略有提升。", "ja-JP": "Qwen3非思考オープンソースモデル。前バージョン（Qwen3-235B-A22B）と比較して、主観的な創造性とモデルの安全性がわずかに向上しています。", "ru-RU": "Qwen3 — открытая модель без режима мышления. По сравнению с предыдущей версией (Qwen3-235B-A22B) она слегка улучшает субъективное творчество и безопасность модели." }, "price_history": [ { "date": "2026-07-08", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen3 235B A22B Instruct 2507" } ] }, { "slug": "alibaba/Qwen3-235B-A22B-Thinking-2507", "model_name": "Qwen3-235B-A22B-Thinking-2507", "display_name": "Qwen3 235B A22B Thinking 2507", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.294118" }, "completion": { "unit": "per_M_tokens", "price": "2.941176" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-235b-a22b-thinking-2507" } ], "released_at": "2025-07-25", "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "vision": true, "video_input": true, "open_weights": true, "prompt_caching": true, "parallel_function_calling": true, "stream": true }, "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2025-04", "family": "qwen", "reasoning_config": { "mandatory": true, "budget_min": 128 }, "docs_url": "https://openrouter.ai/qwen/qwen3-235b-a22b-thinking-2507", "deprecated": true, "benchmarks": { "intelligence_index": 19.9, "coding_index": 22.1, "agentic_index": 3.8 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-235B-A22B-Thinking-2507", "accounts/fireworks/models/qwen3-235b-a22b-thinking-2507", "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507", "hf:Qwen/Qwen3-235B-A22B-Thinking-2507", "qwen/Qwen3-235B-A22B-Thinking-2507", "qwen/qwen3-235b-a22b-thinking-2507", "qwen3-235b-a22b-thinking-2507" ], "intro_i18n": { "zh-CN": "Qwen3-235B-A22B-Thinking-2507 是 Qwen3 的思考版本，专为复杂数学与推理任务强化。", "zh-TW": "Qwen3-235B-A22B-Thinking-2507 是 Qwen3 的 Thinking 變體，強化數學與複雜推理能力。", "ja-JP": "Qwen3-235B-A22B-Thinking-2507は、Qwen3のThinkingバリアントで、複雑な数学や推論タスクに強化されています。", "ru-RU": "Qwen3-235B-A22B-Thinking-2507 — вариант модели Qwen3, усиленный для выполнения сложных математических и логических задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen3 235B A22B Thinking 2507" } ] }, { "slug": "alibaba/Qwen3-30B-A3B", "model_name": "Qwen3-30B-A3B", "display_name": "Qwen3 30B A3B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.110294" }, "completion": { "unit": "per_M_tokens", "price": "1.102941" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-30b-a3b" } ], "released_at": "2025-04-28", "max_input_tokens": 131072, "max_output_tokens": 8192, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "vision": true, "pdf_input": true, "prompt_caching": true, "open_weights": true, "stream": true }, "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "knowledge_cutoff": "2025-06", "docs_url": "https://nebius.com/prices-ai-studio", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-30B-A3B", "accounts/fireworks/models/qwen3-30b-a3b", "deepinfra/Qwen/Qwen3-30B-A3B", "qwen/qwen3-30b-a3b", "qwen3-30b-a3b", "qwen3-30b-a3b:free" ], "intro_i18n": { "zh-CN": "Qwen3 是最新一代 Qwen 大语言模型，采用稠密与 MoE 架构，擅长推理、多语言支持和高级智能体任务。其独特的“思考模式”与“非思考模式”切换能力，确保在多场景下实现高质量表现。\n\nQwen3 显著超越 QwQ 和 Qwen2.5 等前代模型，在数学、编程、常识推理、创意写作和交互对话方面表现卓越。Qwen3-30B-A3B 版本拥有 30.5B 参数（3.3B 激活），48 层，128 个专家（每任务激活 8 个），支持使用 YaRN 扩展至 131K 上下文，树立开源模型新标杆。", "zh-TW": "Qwen3 是最新一代的 Qwen 大型語言模型，採用密集與 MoE 架構，擅長推理、多語言支援與進階代理任務。其獨特的能力可在複雜推理的「思考模式」與高效對話的「非思考模式」間切換，確保多元且高品質的表現。\n\nQwen3 在數學、程式碼、常識推理、創意寫作與互動對話方面，表現遠超前代模型如 QwQ 與 Qwen2.5。Qwen3-30B-A3B 版本擁有 305 億參數（其中 3.3 億為活躍參數）、48 層、128 位專家（每次任務啟用 8 位），並透過 YaRN 支援最高 131K 的上下文長度，為開源模型樹立新標竿。", "ja-JP": "Qwen3は、密結合およびMoEアーキテクチャを採用した最新のQwen LLMで、推論、多言語対応、高度なエージェントタスクに優れています。思考モードと非思考モードを切り替える独自機能により、柔軟かつ高品質なパフォーマンスを実現します。\n\nQwen3は、QwQやQwen2.5などの従来モデルを大きく上回り、数学、コーディング、常識推論、創造的な文章生成、対話において優れた性能を発揮します。Qwen3-30B-A3Bバリアントは30.5Bパラメータ（3.3Bアクティブ）、48層、128エキスパート（1タスクあたり8アクティブ）を持ち、YaRNにより最大131Kのコンテキストに対応します。", "ru-RU": "Qwen3 — новейшее поколение LLM-моделей Qwen с плотной и MoE-архитектурами, превосходящее в логике, многоязычии и агентных задачах. Уникальная возможность переключения между режимом мышления и обычным режимом общения обеспечивает универсальную и высококачественную работу.\n\nQwen3 значительно превосходит предыдущие модели, такие как QwQ и Qwen2.5, демонстрируя отличные результаты в математике, программировании, логике, креативном письме и интерактивных диалогах. Вариант Qwen3-30B-A3B содержит 30,5 миллиарда параметров (3,3 миллиарда активных), 48 слоев, 128 экспертов (8 активных на задачу) и поддерживает контекст до 131K с помощью YaRN, устанавливая новый стандарт среди открытых моделей." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen3 30B A3B" } ] }, { "slug": "alibaba/Qwen3-30B-A3B-Instruct-2507", "model_name": "Qwen3-30B-A3B-Instruct-2507", "display_name": "Qwen3 30B A3B Instruct 2507", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.110294" }, "completion": { "unit": "per_M_tokens", "price": "0.441176" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-30b-a3b-instruct-2507" } ], "released_at": "2025-07-29", "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "vision": true, "pdf_input": true, "prompt_caching": true, "open_weights": true, "stream": true }, "intro": "Tool-capable chat model for instruction following and agentic application workflows", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "knowledge_cutoff": "2025-04", "family": "qwen", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-30B-A3B-Instruct-2507", "accounts/fireworks/models/qwen3-30b-a3b-instruct-2507", "alibaba/qwen3-30b-a3b-instruct-2507", "nebius/qwen/qwen3-30b-a3b-instruct-2507", "qwen/qwen3-30b-a3b-instruct-2507", "qwen/qwenLM/models/Qwen3-30B-A3B-Instruct-2507", "qwen3-30b-a3b-instruct-2507" ], "intro_i18n": { "zh-CN": "Qwen3-30B-A3B-Instruct-2507 是 Qwen3-30B-A3B 的更新版非推理模型。它采用具有 305 亿总参数和 33 亿激活参数的 MoE 架构，在指令遵循、逻辑推理、文本理解、数学、科学、编程和工具使用等方面显著提升，扩展了多语言长尾知识，并在主观开放任务上更好地符合用户偏好。支持 256K 上下文窗口。此模型仅限非推理模式，不会输出 `נקוד` 标签。", "zh-TW": "Qwen3-30B-A3B-Instruct-2507 是 Qwen3-30B-A3B 的更新版非思考模型。它是一個具有 305 億總參數和 33 億活躍參數的 MoE 模型。顯著提升了指令跟隨、邏輯推理、文本理解、數學、科學、編程和工具使用能力，擴展了多語言長尾知識，並更好地符合用戶對主觀開放任務的偏好。支持 256K 上下文。此模型僅限非思考模式，不會輸出 `נקוד` 標籤。", "ja-JP": "Qwen3-30B-A3B-Instruct-2507はQwen3-30B-A3Bの更新版で、非思考型バージョンです。30.5Bの総パラメータと3.3Bのアクティブパラメータを持つMoEモデルで、指示追従、論理的推論、テキスト理解、数学、科学、コーディング、ツール使用を大幅に改善し、多言語のロングテール知識を拡張し、主観的なオープンタスクでのユーザーの好みにより良く一致します。256Kのコンテキストをサポートします。このモデルは非思考型であり、`נקוד`タグを出力しません。", "ru-RU": "Qwen3-30B-A3B-Instruct-2507 — это обновленная версия Qwen3-30B-A3B без способности к самостоятельному мышлению. Это модель MoE с общим количеством параметров 30,5 миллиарда и 3,3 миллиардами активных параметров. Она значительно улучшает выполнение инструкций, логическое мышление, понимание текста, математику, науку, программирование и использование инструментов, расширяет многоязычные знания и лучше соответствует предпочтениям пользователей в субъективных открытых задачах. Поддерживает контекст на 256 тысяч токенов. Эта модель не обладает способностью к самостоятельному мышлению и не будет выводить теги `נקוד`." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.27", "new": "1.21" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.07", "new": "0.31" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.41505562", "new": "0.415188508" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103763905", "new": "0.103797127" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.415120524", "new": "0.41505562" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103780131", "new": "0.103763905" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.415086784", "new": "0.415120524" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103771696", "new": "0.103780131" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.414961092", "new": "0.415086784" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103740273", "new": "0.103771696" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.414930964", "new": "0.414961092" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103732741", "new": "0.103740273" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.414976464", "new": "0.414930964" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103744116", "new": "0.103732741" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.414983184", "new": "0.414976464" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103745796", "new": "0.103744116" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.414950844", "new": "0.414983184" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103737711", "new": "0.103745796" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.414355032", "new": "0.414950844" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103588758", "new": "0.103737711" } ] }, { "slug": "alibaba/Qwen3-30B-A3B-Thinking-2507", "model_name": "Qwen3-30B-A3B-Thinking-2507", "display_name": "Qwen3 30B A3B Thinking 2507", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.110294" }, "completion": { "unit": "per_M_tokens", "price": "1.102941" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-30b-a3b-thinking-2507" } ], "released_at": "2025-07-30", "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "open_weights": true, "prompt_caching": true, "stream": true }, "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2025-04", "family": "qwen", "benchmarks": { "intelligence_index": 14.6, "coding_index": 12.1, "agentic_index": 1.8 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-30B-A3B-Thinking-2507", "accounts/fireworks/models/qwen3-30b-a3b-thinking-2507", "qwen/qwen3-30b-a3b-thinking-2507", "qwen/qwenLM/models/Qwen3-30B-A3B-Thinking-2507", "qwen3-30b-a3b-thinking-2507" ], "intro_i18n": { "zh-CN": "Qwen3 思维模式开源模型。与上一版本（Qwen3-30B-A3B）相比，在逻辑、通用能力、知识和创造力方面显著提升，适用于复杂推理场景。", "zh-TW": "Qwen3 思維模式開源模型。與之前版本（Qwen3-30B-A3B）相比，邏輯、通用能力、知識和創造力顯著提升，適合高難度推理場景。", "ja-JP": "Qwen3思考モードオープンソースモデル。前バージョン（Qwen3-30B-A3B）と比較して、論理、一般能力、知識、創造性が大幅に向上しており、難しい推論シナリオに適しています。", "ru-RU": "Qwen3 — открытая модель с режимом мышления. По сравнению с предыдущей версией (Qwen3-30B-A3B) она значительно улучшает логику, общие возможности, знания и творчество, подходя для сложных сценариев рассуждений." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen3 30B A3B Thinking 2507" } ] }, { "slug": "alibaba/qwen3-32b", "model_name": "qwen3-32b", "display_name": "Qwen3 32B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.7" }, "completion": { "unit": "per_M_tokens", "price": "2.8" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "8.4" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.287" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.147" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Dense open Qwen model for self-hosted chat, reasoning, and coding", "released_at": "2025-04", "knowledge_cutoff": "2025-04", "max_input_tokens": 131072, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 128 }, "docs_url": "https://nebius.com/prices-ai-studio", "deprecated": true, "deprecation_date": "2026-07-17", "benchmarks": { "intelligence_index": 11.4, "coding_index": 15.3, "agentic_index": 1.8 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-32B", "Qwen3-32B", "accounts/fireworks/models/qwen3-32b", "deepinfra/Qwen/Qwen3-32B", "groq/qwen/qwen3-32b", "nebius/qwen/qwen3-32b", "qwen.qwen3-32b", "qwen.qwen3-32b-v1:0", "qwen/qwen3-32b" ], "intro_i18n": { "zh-CN": "Qwen3 是新一代通义千问模型，在推理能力、通用能力、智能体能力和多语言表现方面有重大提升，支持思维模式切换。", "zh-TW": "Qwen3 是新一代通義千問模型，在推理能力、通用能力、智能體能力與多語言表現方面有重大突破，並支援思考模式切換。", "ja-JP": "Qwen3は、次世代のTongyi Qwenモデルであり、推論能力、汎用性、エージェント機能、多言語対応において大幅な向上を実現しています。思考モードの切り替えにも対応しています。", "ru-RU": "Qwen3 — это модель нового поколения Tongyi Qwen с существенными улучшениями в области рассуждений, общей способности, агентных возможностей и многоязычной производительности. Поддерживает переключение режимов мышления." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "1.71", "new": "5.31" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.42", "new": "0.81" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14823415", "new": "0.14828161" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59302932", "new": "0.5929366" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14825733", "new": "0.14823415" }, { "date": "2026-08-12", "kind": "price", "provider": "kilo", "charge": "completion", "old": "0.416", "new": "0.28" }, { "date": "2026-08-12", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "0.104", "new": "0.08" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59298112", "new": "0.59302932" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14824528", "new": "0.14825733" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59280156", "new": "0.59298112" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820039", "new": "0.14824528" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59275852", "new": "0.59280156" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14818963", "new": "0.14820039" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59282352", "new": "0.59275852" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820588", "new": "0.14818963" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59283312", "new": "0.59282352" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820828", "new": "0.14820588" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59278692", "new": "0.59283312" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14819673", "new": "0.14820828" } ] }, { "slug": "alibaba/Qwen3-4B", "model_name": "Qwen3-4B", "display_name": "Qwen3 4B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.044118" }, "completion": { "unit": "per_M_tokens", "price": "0.441176" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-4b" } ], "released_at": "2025-04-28", "max_input_tokens": 131072, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "stream": true, "open_weights": true, "prompt_caching": true }, "docs_url": "https://nebius.com/prices-ai-studio", "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2024-07", "family": "qwen", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "accounts/fireworks/models/qwen3-4b", "qwen/qwen3-4b", "qwen/qwen3-4b:free", "qwen3-4b", "qwen3-4b:free" ], "intro_i18n": { "zh-CN": "Qwen3是下一代同义Qwen模型，在推理、通用能力、代理能力和多语言性能方面取得了重大进展，并支持切换思维模式。", "zh-TW": "Qwen3 是下一代同意 Qwen 模型，在推理、通用能力、代理能力和多語言性能方面取得重大進展，並支持切換思考模式。", "ja-JP": "Qwen3は次世代のTongyi Qwenモデルで、推論、汎用能力、エージェント機能、多言語性能において大幅な向上を実現し、思考モードの切り替えをサポートします。", "ru-RU": "Qwen3 — это модель следующего поколения Tongyi Qwen с значительными улучшениями в рассуждении, общих способностях, агентных возможностях и многоязычной производительности, поддерживающая переключение режимов мышления." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen3 4B" } ] }, { "slug": "alibaba/qwen3-5-flash", "model_name": "qwen3-5-flash", "display_name": "Qwen3.5 Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.172" }, "completion": { "unit": "per_M_tokens", "price": "1.72" }, "cache_read": { "unit": "per_M_tokens", "price": "0.005882" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb", "cache_read": "lobehub-modelbank" }, "tracks": [ { "label": "Context >256K", "source": "lobehub-modelbank", "charge_sources": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank" } }, { "label": "Context >128K", "source": "lobehub-modelbank", "charge_sources": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank" } }, { "label": "Base pricing", "source": "llmdb+lobehub-modelbank", "charge_sources": { "prompt": "llmdb", "completion": "llmdb", "cache_read": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.172" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.72" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen3.5-flash", "tracks": [ { "label": "Context >256K", "factor": "1", "charge_factors": { "cache_read": "6" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 256000, "inclusive": false } ] }, { "label": "Context >128K", "factor": "1", "charge_factors": { "cache_read": "4" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "released_at": "2026-02-23", "knowledge_cutoff": "2025-04", "max_input_tokens": 1000000, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "model_type": "deep_thinking", "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "stream": true, "structured_output": true, "open_weights": true, "pdf_input": true, "video_input": true, "image_output": true, "web_search": true }, "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "reasoning_config": { "budget_min": 1024 }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen3.5-Flash", "alibaba/qwen3.5-flash", "bailian/qwen3.5-flash", "qwen/qwen3.5-flash", "qwen/qwen3.5-flash-2026-02-23", "qwen3.5-flash", "qwen3.5-flash-2026-02-23", "qwen3.5-flash:thinking" ], "intro_i18n": { "zh-CN": "Qwen3.5 原生视觉语言 Flash 模型基于线性注意力机制与稀疏 Mixture-of-Experts（MoE）混合架构构建，推理效率更高。相较于 3 系列，无论在纯文本任务还是多模态任务上均有大幅性能提升，同时具备更快响应速度，在推理速度与整体能力之间实现良好平衡。", "zh-TW": "Qwen3.5 原生視覺語言 Flash 模型採用結合線性注意力機制與稀疏 Mixture-of-Experts（MoE）設計的混合架構，在推理效率上更具優勢。相較於 3 系列，在純文字與多模態表現上均有大幅提升，同時具備快速回應能力，兼顧推理速度與整體效能。", "ja-JP": "Qwen3.5 ネイティブ視覚言語 Flash モデルは、線形アテンション機構とスパース MoE を組み合わせたハイブリッド構造により、高い推論効率を実現しています。3 シリーズと比べてテキスト・マルチモーダル性能が大幅に向上し、高速応答と性能のバランスを両立しています。", "ru-RU": "Нативная модель Qwen3.5 Flash для работы с визуально-языковыми данными построена на гибридной архитектуре, сочетающей механизм линейного внимания и разреженный Mixture-of-Experts (MoE), что обеспечивает более высокую эффективность вывода. По сравнению с серией 3 модель значительно улучшает качество работы как в текстовых, так и в мультимодальных задачах. Она также отличается быстрым временем отклика, сочетая скорость вывода и общую мощность." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-08-07", "kind": "listed", "note": "Qwen3.5 Flash" } ] }, { "slug": "alibaba/qwen3-5-omni-flash", "model_name": "qwen3-5-omni-flash", "display_name": "Qwen3.5 Omni Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.323529" }, "audio_input": { "unit": "per_M_tokens", "price": "2.647059" }, "image_input": { "unit": "per_M_tokens", "price": "0.323529" }, "completion": { "unit": "per_M_tokens", "price": "1.955882" }, "audio_output": { "unit": "per_M_tokens", "price": "10.588235" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "audio_input": "lobehub-modelbank", "image_input": "lobehub-modelbank", "completion": "lobehub-modelbank", "audio_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3.5-omni-flash" } ], "released_at": "2026-03-30", "max_input_tokens": 262144, "max_output_tokens": 65536, "model_type": "omni", "capabilities": { "function_calling": true, "web_search": true, "structured_output": true, "vision": true, "audio_input": true, "video_input": true, "pdf_input": true, "prompt_caching": true, "audio_output": true }, "intro": "Omni-modal model for text, vision, audio, and multimodal agent tasks", "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "family": "qwen3.5", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen3.5-omni-flash" ], "intro_i18n": { "zh-CN": "Qwen3.5 Omni Flash 是一款快速、经济高效的全模态 Qwen 模型，支持文本、图像和视频输入。", "zh-TW": "Qwen3.5 Omni Flash 是一款快速、成本效益高的全模態 Qwen 模型，支持文本、圖像和視頻輸入。", "ja-JP": "Qwen3.5 Omni Flashは、テキスト、画像、動画入力をサポートする高速かつコスト効率の高いフルモーダルQwenモデルです。", "ru-RU": "Qwen3.5 Omni Flash — это быстрая, экономичная полноформатная модель Qwen, поддерживающая ввод текста, изображений и видео." }, "price_history": [ { "date": "2026-08-10", "kind": "listed", "note": "Qwen3.5 Omni Flash" } ] }, { "slug": "alibaba/qwen3-5-omni-plus", "model_name": "qwen3-5-omni-plus", "display_name": "Qwen3.5 Omni Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.029412" }, "audio_input": { "unit": "per_M_tokens", "price": "7.794118" }, "image_input": { "unit": "per_M_tokens", "price": "1.029412" }, "completion": { "unit": "per_M_tokens", "price": "5.882353" }, "audio_output": { "unit": "per_M_tokens", "price": "31.323529" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "audio_input": "lobehub-modelbank", "image_input": "lobehub-modelbank", "completion": "lobehub-modelbank", "audio_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3.5-omni-plus" } ], "released_at": "2026-03-30", "max_input_tokens": 262144, "max_output_tokens": 65536, "model_type": "omni", "capabilities": { "function_calling": true, "web_search": true, "structured_output": true, "vision": true, "audio_input": true, "video_input": true, "pdf_input": true, "prompt_caching": true, "audio_output": true }, "intro": "Omni-modal model for text, vision, audio, and multimodal agent tasks", "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "family": "qwen3.5", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen3.5-omni-plus" ], "intro_i18n": { "zh-CN": "Qwen3.5 Omni Plus 支持文本、图像和视频输入，是最新的高质量多模态理解与生成的全模态 Qwen 模型。", "zh-TW": "Qwen3.5 Omni Plus 支持文本、圖像和視頻輸入，是最新的高品質多模態理解與生成的全模態 Qwen 模型。", "ja-JP": "Qwen3.5 Omni Plusは、テキスト、画像、動画入力をサポートします。高品質なマルチモーダル理解と生成のための最新のフルモーダルQwenモデルです。", "ru-RU": "Qwen3.5 Omni Plus поддерживает ввод текста, изображений и видео. Это новейшая полноформатная модель Qwen для высококачественного мультимодального понимания и генерации." }, "price_history": [ { "date": "2026-08-10", "kind": "listed", "note": "Qwen3.5 Omni Plus" } ] }, { "slug": "alibaba/qwen3-7-flash", "model_name": "qwen3-7-flash", "display_name": "Qwen3.7 Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.029412" }, "completion": { "unit": "per_M_tokens", "price": "0.117647" }, "cache_read": { "unit": "per_M_tokens", "price": "0.005882" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank" }, "tracks": [ { "label": "Context >256K", "source": "lobehub-modelbank", "charge_sources": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank" } }, { "label": "Context >32K", "source": "lobehub-modelbank", "charge_sources": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank" } }, { "label": "Base pricing", "source": "lobehub-modelbank", "charge_sources": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "qwen3.7-flash", "tracks": [ { "label": "Context >256K", "factor": "6", "triggers": [ { "kind": "input_tokens_above", "threshold": 256000, "inclusive": false } ] }, { "label": "Context >32K", "factor": "3", "triggers": [ { "kind": "input_tokens_above", "threshold": 32000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "released_at": "2026-07-21", "max_input_tokens": 1000000, "max_output_tokens": 65536, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true, "open_weights": true }, "intro": "Lightweight multimodal Qwen model for high-throughput text, image, and video tasks", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "qwen", "reasoning_config": { "mandatory": false, "budget_min": 1 }, "parameters": { "supported": [ "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "alibaba/qwen3.7-flash", "qwen/qwen3.7-flash", "qwen/qwen3.7-flash-2026-07-15", "qwen3.7-flash", "qwen3.7-flash-2026-07-15", "qwen3.7-flash:thinking" ], "intro_i18n": { "zh-CN": "Qwen3.7 原生视觉语言 Flash 模型，相较于 Qwen3.6-Flash 在多模态理解和代理执行能力方面有全面提升。关键改进包括增强的多模态基础能力、更强的通用对象识别、进一步提升的现实感知和空间智能，以及在搜索代理和 CI 代理等多模态代理场景中的显著能力升级，更稳定的端到端任务执行，优化的多模态编码能力，以及更流畅的 vibe 编码体验。", "zh-TW": "Qwen3.7 原生視覺語言 Flash 模型，與 Qwen3.6-Flash 相比，在多模態理解和代理執行能力方面有全面提升。主要改進包括加強多模態基礎能力、增強通用物體識別、進一步提升真實世界感知和空間智能、顯著升級多模態代理場景（如搜索代理和 CI 代理）的能力、更穩定的端到端任務執行、優化多模態編碼能力以及更流暢的氛圍編碼體驗。", "ja-JP": "Qwen3.7は、ネイティブのビジョン言語Flashモデルで、Qwen3.6-Flashと比較してマルチモーダル理解とエージェント実行能力において包括的な改善を実現しています。主な強化点には、マルチモーダル基盤能力の強化、ユニバーサルオブジェクト認識の強化、実世界の知覚と空間知能のさらなる向上、Search AgentやCI Agentなどのマルチモーダルエージェントシナリオにおける能力の大幅なアップグレード、エンドツーエンドタスク実行の安定性向上、マルチモーダルコーディング能力の最適化、よりスムーズなバイブコーディング体験が含まれます。", "ru-RU": "Qwen3.7 — нативная модель Flash для работы с визуальными и языковыми данными, с комплексными улучшениями в мультимодальном понимании и возможностях выполнения задач агентами по сравнению с Qwen3.6-Flash. Ключевые улучшения включают усиленные мультимодальные базовые возможности, улучшенное универсальное распознавание объектов, повышенное восприятие реального мира и пространственный интеллект, значительно улучшенные возможности в мультимодальных сценариях с агентами, таких как Search Agent и CI Agent, более стабильное выполнение задач от начала до конца, оптимизированные возможности мультимодального кодирования и более плавный опыт кодирования." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-08-02", "kind": "listed", "note": "Qwen3.7 Flash" } ] }, { "slug": "alibaba/qwen3-8b", "model_name": "qwen3-8b", "display_name": "Qwen3 8B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.18" }, "completion": { "unit": "per_M_tokens", "price": "0.7" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.1" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.18" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.072" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.287" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.18" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "released_at": "2025-04", "knowledge_cutoff": "2025-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 128 }, "deprecated": true, "benchmarks": { "intelligence_index": 8.3, "coding_index": 9, "agentic_index": 1.6 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "defaults": { "temperature": 0.6, "top_p": 0.95, "top_k": 20 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-8B", "accounts/fireworks/models/qwen3-8b", "qwen/Qwen3-8B", "qwen/qwen3-8b", "qwen3-8b:free" ], "intro_i18n": { "zh-CN": "Qwen3 是新一代通义千问模型，在推理能力、通用能力、智能体能力和多语言表现方面有重大提升，支持思维模式切换。", "zh-TW": "Qwen3 是新一代通義千問模型，在推理能力、通用能力、智能體能力與多語言表現方面有重大突破，並支援思考模式切換。", "ja-JP": "Qwen3は、次世代のTongyi Qwenモデルであり、推論能力、汎用性、エージェント機能、多言語対応において大幅な向上を実現しています。思考モードの切り替えにも対応しています。", "ru-RU": "Qwen3 — это модель нового поколения Tongyi Qwen с существенными улучшениями в области рассуждений, общей способности, агентных возможностей и многоязычной производительности. Поддерживает переключение режимов мышления." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "alibaba/qwen3-asr-flash", "model_name": "qwen3-asr-flash", "display_name": "Qwen3-ASR Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.035" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.035" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.032" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.035" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.032" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Speech transcription model for accurate audio-to-text and captioning workflows", "released_at": "2025-09-08", "knowledge_cutoff": "2024-04", "max_input_tokens": 53248, "max_output_tokens": 4096, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "family": "qwen", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "reasoning": true, "audio_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen/qwen3-asr-flash" ], "model_type": "speech_recognition" }, { "slug": "alibaba/qwen3-coder-30b-a3b-instruct", "model_name": "qwen3-coder-30b-a3b-instruct", "display_name": "Qwen3-Coder 30B-A3B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.45" }, "completion": { "unit": "per_M_tokens", "price": "2.25" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.220588" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.330882" }, "prompt_0_128_0_2": { "unit": "per_M_tokens", "price": "0.551471" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "0.882353" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "1.323529" }, "completion_0_128_0_2": { "unit": "per_M_tokens", "price": "2.205882" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_2": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_0_2": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.45" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.216" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.861" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Smaller Qwen coder for efficient local agents and repo-level fixes", "released_at": "2025-04", "knowledge_cutoff": "2025-04", "max_input_tokens": 262144, "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true, "parallel_function_calling": true }, "model_type": "text_generation", "parameters": { "supported": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-Coder-30B-A3B-Instruct", "Qwen3-Coder-30B-A3B-Instruct", "accounts/fireworks/models/qwen3-coder-30b-a3b-instruct", "qwen.qwen3-coder-30b-a3b-instruct", "qwen/qwen3-coder-30b-a3b-instruct", "qwen/qwenCoder/models/Qwen3-Coder-30B-A3B-Instruct" ], "intro_i18n": { "zh-CN": "Qwen3-Coder-30B-A3B-Instruct 是 Qwen 团队推出的 Qwen3 系列代码模型。该模型在保持高性能和高效率的同时，显著增强了代码能力。在智能体编程、自动化浏览器操作和工具使用等开放模型中表现出色。原生支持 256K 上下文，并可扩展至 1M tokens，适用于代码库级理解。支持 Qwen Code 和 CLINE 等平台的智能体编程，采用专用函数调用格式。", "zh-TW": "Qwen3-Coder-30B-A3B-Instruct 是 Qwen 團隊推出的 Qwen3 程式模型。此模型在提升程式能力的同時，兼顧高效能與運行效率。其在智能體程式編寫、自動化瀏覽器操作與工具使用方面，在開源模型中表現出色。原生支援 256K 上下文，並可擴展至 1M token，適用於程式庫層級理解。支援 Qwen Code 與 CLINE 等平台上的智能體程式編寫，並採用專用函式呼叫格式。", "ja-JP": "Qwen3-Coder-30B-A3B-Instructは、QwenチームによるQwen3コードモデルです。高性能かつ効率的な設計で、コード生成能力を強化しています。エージェント型コーディング、自動ブラウザ操作、ツール使用においてオープンモデルの中でも優れた性能を発揮します。256Kのコンテキストをネイティブにサポートし、最大1Mトークンまで拡張可能で、コードベースレベルの理解に対応します。Qwen CodeやCLINEなどのプラットフォームで、関数呼び出し形式を用いたエージェント型コーディングを実現します。", "ru-RU": "Qwen3-Coder-30B-A3B-Instruct — это модель программирования серии Qwen3 от команды Qwen. Оптимизирована для высокой производительности и эффективности при работе с кодом. Демонстрирует сильные стороны в агентном программировании, автоматизации браузера и использовании инструментов среди открытых моделей. Нативно поддерживает контекст до 256K и может быть расширена до 1M токенов для понимания на уровне кодовой базы. Обеспечивает агентное программирование на платформах, таких как Qwen Code и CLINE, с использованием специального формата вызова функций." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14823415", "new": "0.14828161" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59302932", "new": "0.5929366" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14825733", "new": "0.14823415" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59298112", "new": "0.59302932" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14824528", "new": "0.14825733" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59280156", "new": "0.59298112" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820039", "new": "0.14824528" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59275852", "new": "0.59280156" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14818963", "new": "0.14820039" }, { "date": "2026-08-10", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "0.27", "new": "0.28" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59282352", "new": "0.59275852" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820588", "new": "0.14818963" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59283312", "new": "0.59282352" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820828", "new": "0.14820588" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59278692", "new": "0.59283312" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14819673", "new": "0.14820828" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59193576", "new": "0.59278692" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14798394", "new": "0.14819673" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "completion", "old": "0.222", "new": "0.245" } ] }, { "slug": "alibaba/qwen3-coder-480b-a35b-instruct", "model_name": "qwen3-coder-480b-a35b-instruct", "display_name": "Qwen3-Coder 480B-A35B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.882353" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "1.323529" }, "prompt_0_128_0_2": { "unit": "per_M_tokens", "price": "2.205882" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "3.529412" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "5.294118" }, "completion_0_128_0_2": { "unit": "per_M_tokens", "price": "8.823529" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_2": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_0_2": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.861" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "7.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.441" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Open Qwen coding heavyweight for repository reasoning and agentic engineering", "released_at": "2025-04", "knowledge_cutoff": "2025-04", "max_input_tokens": 262144, "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true, "parallel_function_calling": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-Coder-480B-A35B-Instruct", "Qwen/qwen3-coder-480b-a35b-instruct", "Qwen3-Coder-480B-A35B-Instruct", "accounts/fireworks/models/qwen3-coder-480b-a35b-instruct", "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct", "hf:Qwen/Qwen3-Coder-480B-A35B-Instruct", "qwen.qwen3-coder-480b-a35b-instruct", "qwen/qwen3-coder-480b-a35b-instruct" ], "intro_i18n": { "zh-CN": "开源 Qwen 代码模型。最新的 qwen3-coder-480b-a35b-instruct 基于 Qwen3，提供强大的编码代理能力、工具使用和环境交互能力，具备卓越的代码性能和扎实的通用能力。", "zh-TW": "開源 Qwen 代碼模型。最新的 qwen3-coder-480b-a35b-instruct 基於 Qwen3，提供強大的編碼代理能力、工具使用和環境交互能力，適用於自主編程，具有卓越的代碼性能和穩健的通用能力。", "ja-JP": "オープンソースのQwenコードモデル。最新のqwen3-coder-480b-a35b-instructはQwen3を基盤としており、強力なコーディングエージェント能力、ツール使用、環境との相互作用を提供し、自律的なプログラミングにおいて優れたコード性能と堅実な一般能力を発揮します。", "ru-RU": "Открытая модель кода Qwen. Последняя версия qwen3-coder-480b-a35b-instruct основана на Qwen3 и обеспечивает сильные способности кодирования агентов, использования инструментов и взаимодействия с окружающей средой для автономного программирования, с отличной производительностью кода и надежными общими возможностями." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.5576196", "new": "3.55875864" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.8894049", "new": "0.88968966" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.55817592", "new": "3.5576196" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.88954398", "new": "0.8894049" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.55788672", "new": "3.55817592" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.88947168", "new": "0.88954398" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.55680936", "new": "3.55788672" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.88920234", "new": "0.88947168" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.55655112", "new": "3.55680936" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.88913778", "new": "0.88920234" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.55694112", "new": "3.55655112" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.88923528", "new": "0.88913778" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.55699872", "new": "3.55694112" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.88924968", "new": "0.88923528" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.55672152", "new": "3.55699872" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.88918038", "new": "0.88924968" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.55161456", "new": "3.55672152" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.88790364", "new": "0.88918038" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.5538804", "new": "3.55161456" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.8884701", "new": "0.88790364" } ] }, { "slug": "alibaba/qwen3-coder-flash", "model_name": "qwen3-coder-flash", "display_name": "Qwen3 Coder Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.029412" }, "cache_read_0_032_0_128": { "unit": "per_M_tokens", "price": "0.044118" }, "cache_read_0_128_0_256": { "unit": "per_M_tokens", "price": "0.073529" }, "cache_read_0_256_1": { "unit": "per_M_tokens", "price": "0.147059" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.147059" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.220588" }, "prompt_0_128_0_256": { "unit": "per_M_tokens", "price": "0.367647" }, "prompt_0_256_1": { "unit": "per_M_tokens", "price": "0.735294" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "0.588235" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "0.882353" }, "completion_0_128_0_256": { "unit": "per_M_tokens", "price": "1.470588" }, "completion_0_256_1": { "unit": "per_M_tokens", "price": "3.676471" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_0_128": "lobehub-modelbank", "cache_read_0_128_0_256": "lobehub-modelbank", "cache_read_0_256_1": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_256": "lobehub-modelbank", "prompt_0_256_1": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_0_256": "lobehub-modelbank", "completion_0_256_1": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.144" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.574" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen coding model for software agents, repository edits, and code reasoning", "released_at": "2025-07-28", "knowledge_cutoff": "2025-04", "max_input_tokens": 1000000, "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "model_type": "text_generation", "parameters": { "supported": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen3-Coder-Flash", "alibaba/qwen3-coder-flash", "bailian/qwen3-coder-flash", "qwen/qwen3-coder-flash", "qwen/qwen3-coder-flash-2025-07-28", "qwen3-coder-flash-2025-07-28" ], "intro_i18n": { "zh-CN": "Qwen 编程模型。最新的 Qwen3-Coder 系列基于 Qwen3，具备强大的编程代理能力、工具使用与环境交互能力，编程表现优异，通用能力扎实。", "zh-TW": "Qwen 程式碼模型。最新的 Qwen3-Coder 系列基於 Qwen3，具備強大的程式代理能力、工具使用與環境互動能力，支援自主編程，程式碼表現優異，通用能力穩健。", "ja-JP": "Qwenコードモデル。最新のQwen3-Coderシリーズは、Qwen3をベースにしており、自律的なプログラミングのための強力なコードエージェント機能、ツール使用、環境との対話を提供します。優れたコード性能と堅実な汎用能力を備えています。", "ru-RU": "Модель кода Qwen. Новейшая серия Qwen3-Coder основана на Qwen3 и обладает мощными возможностями кодирующего агента, использования инструментов и взаимодействия со средой для автономного программирования, с отличной производительностью кода и общей функциональностью." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "reasoning: false→true" } ] }, { "slug": "alibaba/Qwen3-Coder-Next", "model_name": "Qwen3-Coder-Next", "display_name": "Qwen3 Coder Next", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.147059" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.220588" }, "prompt_0_128_infinity": { "unit": "per_M_tokens", "price": "0.367647" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "0.588235" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "0.882353" }, "completion_0_128_infinity": { "unit": "per_M_tokens", "price": "1.470588" } }, "provenance": { "base_charges": { "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_infinity": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-coder-next" } ], "max_input_tokens": 262144, "max_output_tokens": 65536, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "open_weights": true, "prompt_caching": true, "stream": true }, "intro": "Qwen coding model for software agents, repository edits, and code reasoning", "released_at": "2026-02-03", "knowledge_cutoff": "2025-09", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "docs_url": "https://aws.amazon.com/bedrock/pricing/", "benchmarks": { "intelligence_index": 21.3, "coding_index": 36.2, "agentic_index": 8.9 }, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-Coder-Next", "alibaba/qwen3-coder-next", "bailian/qwen3-coder-next", "qwen.qwen3-coder-next", "qwen/qwen3-coder-next", "qwen3-coder-next" ], "intro_i18n": { "zh-CN": "下一代Qwen编码器，优化用于复杂多文件代码生成、调试和高吞吐代理工作流。设计用于强大的工具集成和改进的推理性能。", "zh-TW": "下一代 Qwen 編碼器，針對複雜的多文件代碼生成、調試和高吞吐量代理工作流進行了優化。設計上強調工具集成和推理性能的提升。", "ja-JP": "次世代Qwenコーダーは、複雑なマルチファイルコード生成、デバッグ、高スループットエージェントワークフローに最適化されています。強力なツール統合と推論性能の向上を目指して設計されています。", "ru-RU": "Следующее поколение Qwen coder, оптимизированное для сложной генерации кода из нескольких файлов, отладки и высокопроизводительных рабочих процессов агентов. Разработано для сильной интеграции инструментов и улучшенной производительности рассуждений." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59302932", "new": "0.5929366" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59302932", "new": "0.5929366" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59298112", "new": "0.59302932" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59298112", "new": "0.59302932" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59280156", "new": "0.59298112" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59280156", "new": "0.59298112" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59275852", "new": "0.59280156" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59275852", "new": "0.59280156" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59282352", "new": "0.59275852" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59282352", "new": "0.59275852" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59283312", "new": "0.59282352" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59283312", "new": "0.59282352" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59278692", "new": "0.59283312" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59278692", "new": "0.59283312" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59193576", "new": "0.59278692" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59193576", "new": "0.59278692" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "completion", "old": "0.84", "new": "0.891" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "prompt", "old": "0.158", "new": "0.167" } ] }, { "slug": "alibaba/qwen3-coder-plus", "model_name": "qwen3-coder-plus", "display_name": "Qwen3 Coder Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "5" }, "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.117647" }, "cache_read_0_032_0_128": { "unit": "per_M_tokens", "price": "0.176471" }, "cache_read_0_128_0_256": { "unit": "per_M_tokens", "price": "0.294118" }, "cache_read_0_256_infinity": { "unit": "per_M_tokens", "price": "0.588235" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.588235" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.882353" }, "prompt_0_128_0_256": { "unit": "per_M_tokens", "price": "1.470588" }, "prompt_0_256_infinity": { "unit": "per_M_tokens", "price": "2.941176" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "2.352941" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "3.529412" }, "completion_0_128_0_256": { "unit": "per_M_tokens", "price": "5.882353" }, "completion_0_256_infinity": { "unit": "per_M_tokens", "price": "29.411765" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_0_128": "lobehub-modelbank", "cache_read_0_128_0_256": "lobehub-modelbank", "cache_read_0_256_infinity": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_256": "lobehub-modelbank", "prompt_0_256_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_0_256": "lobehub-modelbank", "completion_0_256_infinity": "lobehub-modelbank" }, "verification_status": "cross_checked" } } ], "intro": "Hosted Qwen coder for software agents, repo edits, and long-context code", "released_at": "2025-07-23", "knowledge_cutoff": "2025-04", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "model_type": "deep_thinking", "docs_url": "https://openrouter.ai/qwen/qwen3-coder-plus", "parameters": { "supported": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "alibaba/qwen3-coder-plus", "bailian/qwen3-coder-plus", "qwen/qwen3-coder-plus", "qwen/qwen3-coder-plus-2025-07-22", "qwen/qwen3-coder-plus-2025-09-23", "qwen3-coder-plus-2025-07-22", "qwen3-coder-plus-2025-09-23" ], "intro_i18n": { "zh-CN": "Qwen3-Coder-Plus 是 Qwen 系列的代码智能体模型，优化了复杂工具使用和长时间会话能力。", "zh-TW": "Qwen3-Coder-Plus 是 Qwen 系列中的程式代理模型，針對更複雜的工具使用與長時間工作流程進行最佳化。", "ja-JP": "Qwen3-Coder-Plusは、より複雑なツール利用と長時間セッションに最適化されたQwenシリーズのコーディングエージェントモデルです。", "ru-RU": "Qwen3-Coder-Plus — модель-агент для программирования из серии Qwen, оптимизированная для сложного использования инструментов и длительных сессий." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen3-livetranslate-flash-realtime", "model_name": "qwen3-livetranslate-flash-realtime", "display_name": "Qwen3-LiveTranslate Flash Realtime", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "audio_input": { "unit": "per_M_tokens", "price": "10" }, "audio_output": { "unit": "per_M_tokens", "price": "38" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev", "audio_output": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Speech generation model for controllable voice, narration, and audio delivery", "released_at": "2025-09-22", "knowledge_cutoff": "2024-04", "max_input_tokens": 53248, "max_output_tokens": 4096, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "family": "qwen", "capabilities": { "vision": true, "audio_input": true, "audio_output": true, "video_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "realtime_speech_translation" }, { "slug": "alibaba/qwen3-max", "model_name": "qwen3-max", "display_name": "Qwen3 Max", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank+pricetoken", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.2" }, "completion": { "unit": "per_M_tokens", "price": "6" }, "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.073529" }, "cache_read_0_032_0_128": { "unit": "per_M_tokens", "price": "0.117647" }, "cache_read_0_128_infinity": { "unit": "per_M_tokens", "price": "0.205882" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.367647" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.588235" }, "prompt_0_128_0_252": { "unit": "per_M_tokens", "price": "1.029412" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "1.470588" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "2.352941" }, "completion_0_128_0_252": { "unit": "per_M_tokens", "price": "4.117647" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_0_128": "lobehub-modelbank", "cache_read_0_128_infinity": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_252": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_0_252": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.861" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.441" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pricetoken", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3472" }, "message": "prompt from pricetoken conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pricetoken", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.3889" }, "message": "completion from pricetoken conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Flagship Qwen3 model for coding agents, complex reasoning, and tool use", "released_at": "2025-09-23", "knowledge_cutoff": "2025-04", "max_input_tokens": 262144, "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "parameters": { "supported": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 1 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-Max", "alibaba/qwen3-max", "bailian/qwen3-max", "deepinfra/Qwen/Qwen3-Max", "qwen/qwen3-max", "qwen/qwen3-max-2025-09-23", "qwen/qwen3-max-2026-01-23", "qwen3-max-2025-09-23", "qwen3-max-2026-01-23" ], "intro_i18n": { "zh-CN": "Qwen3 Max 是 Qwen3 系列的高端推理模型，专注于多语言推理与工具集成。", "zh-TW": "Qwen3 Max 是 Qwen3 系列中高階推理模型，支援多語言推理與工具整合。", "ja-JP": "Qwen3 Maxは、Qwen3シリーズの最上位推論モデルで、多言語推論とツール統合に対応します。", "ru-RU": "Qwen3 Max — флагманская модель логического вывода в серии Qwen3, предназначенная для многоязычного логического анализа и интеграции инструментов." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "alibaba/qwen3-max-preview", "model_name": "qwen3-max-preview", "display_name": "Qwen3 Max Preview", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.176471" }, "cache_read_0_032_0_128": { "unit": "per_M_tokens", "price": "0.294118" }, "cache_read_0_128_infinity": { "unit": "per_M_tokens", "price": "0.441176" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.882353" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "1.470588" }, "prompt_0_128_infinity": { "unit": "per_M_tokens", "price": "2.205882" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "3.529412" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "5.882353" }, "completion_0_128_infinity": { "unit": "per_M_tokens", "price": "8.823529" } }, "provenance": { "base_charges": { "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_0_128": "lobehub-modelbank", "cache_read_0_128_infinity": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_infinity": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-10-30", "max_input_tokens": 262144, "max_output_tokens": 65536, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "pdf_input": true, "prompt_caching": true, "stream": true, "open_weights": true }, "intro": "Flagship model for demanding analysis, coding, and production agent workflows", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2024-12", "family": "qwen", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "alibaba/qwen3-max-preview", "qwen/qwen3-max-preview" ], "intro_i18n": { "zh-CN": "Qwen3 Max（预览版）是面向高级推理与工具集成的 Max 版本。", "zh-TW": "Qwen3 Max（預覽版）是 Max 變體，專為進階推理與工具整合設計。", "ja-JP": "Qwen3 Max（プレビュー）は、高度な推論とツール統合に対応するMaxバリアントです。", "ru-RU": "Qwen3 Max (предпросмотр) — вариант Max для продвинутого логического вывода и интеграции инструментов." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen3 Max Preview" } ] }, { "slug": "alibaba/qwen3-next-80b-a3b-instruct", "model_name": "qwen3-next-80b-a3b-instruct", "display_name": "Qwen3-Next 80B-A3B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+litellm+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.2" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.144" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.574" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen instruction model for multilingual chat, reasoning, and tool use", "released_at": "2025-09", "knowledge_cutoff": "2025-04", "max_input_tokens": 131072, "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "parallel_function_calling": true }, "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "model_type": "text_generation", "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-Next-80B-A3B-Instruct", "Qwen3-Next-80B-A3B-Instruct", "accounts/fireworks/models/qwen3-next-80b-a3b-instruct", "alibaba/qwen3-next-80b-a3b-instruct", "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct", "qwen.qwen3-next-80b-a3b-instruct", "qwen/Qwen3-Next-80B-A3B-Instruct", "qwen/qwen3-next-80b-a3b-instruct", "qwen/qwen3-next-80b-a3b-instruct:free" ], "intro_i18n": { "zh-CN": "下一代 Qwen3 非推理开源模型。相比上一版本（Qwen3-235B-A22B-Instruct-2507），在中文理解、逻辑推理和文本生成方面均有显著提升。", "zh-TW": "下一代 Qwen3 非思考開源模型。相較前代（Qwen3-235B-A22B-Instruct-2507），具備更佳中文理解、更強邏輯推理與更優文本生成能力。", "ja-JP": "次世代のQwen3非思考型オープンソースモデル。前バージョン（Qwen3-235B-A22B-Instruct-2507）と比較して、中国語理解、論理的推論、テキスト生成が向上しています。", "ru-RU": "Модель следующего поколения Qwen3 без рассуждений с открытым исходным кодом. По сравнению с предыдущей версией (Qwen3-235B-A22B-Instruct-2507), улучшено понимание китайского языка, логическое мышление и генерация текста." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14823415", "new": "0.14828161" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59302932", "new": "0.5929366" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14825733", "new": "0.14823415" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.09", "new": "0.1" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59298112", "new": "0.59302932" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14824528", "new": "0.14825733" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59280156", "new": "0.59298112" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820039", "new": "0.14824528" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59275852", "new": "0.59280156" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14818963", "new": "0.14820039" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59282352", "new": "0.59275852" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820588", "new": "0.14818963" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59283312", "new": "0.59282352" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820828", "new": "0.14820588" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59278692", "new": "0.59283312" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14819673", "new": "0.14820828" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59193576", "new": "0.59278692" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14798394", "new": "0.14819673" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.5923134", "new": "0.59193576" } ] }, { "slug": "alibaba/qwen3-next-80b-a3b-thinking", "model_name": "qwen3-next-80b-a3b-thinking", "display_name": "Qwen3-Next 80B-A3B (Thinking)", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+litellm+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.2" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.144" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.434" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Efficient Qwen thinking model for local reasoning, math, and coding agents", "released_at": "2025-09", "knowledge_cutoff": "2025-04", "max_input_tokens": 131072, "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "parallel_function_calling": true }, "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "model_type": "deep_thinking", "reasoning_config": { "mandatory": true, "budget_min": 1 }, "benchmarks": { "intelligence_index": 16.9, "coding_index": 17.4, "agentic_index": 2.1 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-Next-80B-A3B-Thinking", "Qwen3-Next-80B-A3B-Thinking", "accounts/fireworks/models/qwen3-next-80b-a3b-thinking", "alibaba/qwen3-next-80b-a3b-thinking", "nebius/qwen/qwen3-next-80b-a3b-thinking", "qwen/qwen3-next-80b-a3b-thinking" ], "intro_i18n": { "zh-CN": "下一代 Qwen3 思维模式开源模型。与上一版本（Qwen3-235B-A22B-Thinking-2507）相比，指令遵循能力提升，总结更加简洁。", "zh-TW": "下一代 Qwen3 思維模式開源模型。與之前版本（Qwen3-235B-A22B-Thinking-2507）相比，指令遵循能力有所提升，摘要更為簡潔。", "ja-JP": "次世代Qwen3思考モードオープンソースモデル。前バージョン（Qwen3-235B-A22B-Thinking-2507）と比較して、指示の追従性が向上し、要約がより簡潔になっています。", "ru-RU": "Модель следующего поколения Qwen3 с режимом мышления (открытая). По сравнению с предыдущей версией (Qwen3-235B-A22B-Thinking-2507) улучшено следование инструкциям, а резюме стали более лаконичными." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen3-omni-flash", "model_name": "qwen3-omni-flash", "display_name": "Qwen3-Omni Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.43" }, "completion": { "unit": "per_M_tokens", "price": "1.66" }, "audio_input": { "unit": "per_M_tokens", "price": "3.81" }, "audio_output": { "unit": "per_M_tokens", "price": "15.11" }, "image_input": { "unit": "per_M_tokens", "price": "0.485294" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev", "audio_output": "models-dev", "image_input": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.43" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.058" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.66" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.23" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.43" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.8", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "3.81" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15.8", "currency": "CNY" }, "message": "audio_input from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.66" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6.9", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "audio_output", "selected_charge": { "unit": "per_M_tokens", "price": "15.11" }, "discarded_charge": { "unit": "per_M_tokens", "price": "62.6", "currency": "CNY" }, "message": "audio_output from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks", "released_at": "2025-09-15", "knowledge_cutoff": "2024-04", "max_input_tokens": 65536, "max_output_tokens": 16384, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "audio_input": true, "audio_output": true, "video_input": true, "stream": true }, "model_type": "omni", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Qwen3-Omni-Flash 是基于 Thinker–Talker 专家混合（MoE）架构构建的多模态大型模型。支持文本、图像、音频和视频的高效理解，以及语音生成能力。该模型支持 119 种语言的文本交互和 20 种语言的语音交互，能够生成类人语音，实现精准的跨语言交流。具备强大的指令跟随能力，并支持可定制的系统提示，灵活适应不同的对话风格和角色设置。广泛适用于文本创作、语音助手和多媒体分析等场景，提供自然流畅的多模态交互体验。", "zh-TW": "Qwen3-Omni-Flash 是基於 Thinker–Talker 專家混合架構（MoE）構建的多模態大型模型。支持文本、圖像、音頻和視頻的高效理解，以及語音生成能力。該模型支持 119 種語言的文本交互和 20 種語言的語音交互，生成類人語音以實現精確的跨語言溝通。具備強大的指令跟隨能力，支持可定制的系統提示，靈活適應不同的對話風格和角色設置。廣泛應用於文本創作、語音助手和多媒體分析等場景，提供自然流暢的多模態交互體驗。", "ja-JP": "Qwen3-Omni-Flashは、Thinker–Talker Mixture-of-Experts（MoE）アーキテクチャに基づくマルチモーダル大規模モデルです。テキスト、画像、音声、動画の効率的な理解をサポートし、音声生成機能も備えています。このモデルは、119言語でのテキストベースの対話と20言語での音声対話を可能にし、正確なクロスリンガルコミュニケーションのために人間らしい音声を生成します。強力な指示追従能力を持ち、カスタマイズ可能なシステムプロンプトをサポートすることで、さまざまな会話スタイルや役割設定に柔軟に適応できます。テキスト作成、音声アシスタント、マルチメディア分析などのシナリオで広く活用され、自然でシームレスなマルチモーダルインタラクション体験を提供します。", "ru-RU": "Qwen3-Omni-Flash — это мультимодальная крупная модель, построенная на архитектуре Thinker–Talker Mixture-of-Experts (MoE). Она поддерживает эффективное понимание текста, изображений, аудио и видео, а также возможности генерации речи. Модель обеспечивает текстовое взаимодействие на 119 языках и голосовое взаимодействие на 20 языках, создавая речь, близкую к человеческой, для точной межъязыковой коммуникации. Она обладает сильными способностями следовать инструкциям и поддерживает настраиваемые системные подсказки, позволяя гибко адаптироваться к различным стилям общения и ролевым настройкам. Широко применима в таких сценариях, как создание текста, голосовые помощники и мультимедийный анализ, обеспечивая естественное и бесшовное мультимодальное взаимодействие." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen3-omni-flash-realtime", "model_name": "qwen3-omni-flash-realtime", "display_name": "Qwen3-Omni Flash Realtime", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.52" }, "completion": { "unit": "per_M_tokens", "price": "1.99" }, "audio_input": { "unit": "per_M_tokens", "price": "4.57" }, "audio_output": { "unit": "per_M_tokens", "price": "18.13" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev", "audio_output": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.52" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.23" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.99" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.918" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen omni model for text, vision, audio, and multimodal agent tasks", "released_at": "2025-09-15", "knowledge_cutoff": "2024-04", "max_input_tokens": 65536, "max_output_tokens": 16384, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "audio_input": true, "audio_output": true, "video_input": true, "stream": true }, "model_type": "realtime_omni", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen3-vl-235b-a22b", "model_name": "qwen3-vl-235b-a22b", "display_name": "Qwen3-VL 235B-A22B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.7" }, "completion": { "unit": "per_M_tokens", "price": "2.8" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "8.4" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.286705" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.14682" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2025-04", "knowledge_cutoff": "2025-04", "max_input_tokens": 131072, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "model_type": "vision_understanding", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen.qwen3-vl-235b-a22b", "qwen.qwen3-vl-235b-a22b-v1:0", "qwen/qwen3-vl-235b-a22b" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen3-vl-235b-a22b-instruct", "model_name": "qwen3-vl-235b-a22b-instruct", "display_name": "qwen3-vl-235b-a22b-instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "litellm+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "open_weights": true, "stream": true, "image_output": true }, "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2024-01-01", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "knowledge_cutoff": "2025-03", "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.7, "top_p": 0.8 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-VL-235B-A22B-Instruct", "Qwen3-VL-235B-A22B-Instruct", "accounts/fireworks/models/qwen3-vl-235b-a22b-instruct", "alibaba/qwen3-vl-235b-a22b-instruct", "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct", "qwen.qwen3-vl-235b-a22b-instruct", "qwen/Qwen3-VL-235B-A22B-Instruct", "qwen/qwen3-vl-235b-a22b-instruct" ], "intro_i18n": { "zh-CN": "Qwen3 VL 235B A22B 非思维模式（Instruct）适用于非思维指令场景，同时保留了强大的视觉理解能力。", "zh-TW": "Qwen3 VL 235B A22B 非思維模式（指令）適用於非思維指令場景，同時保留強大的視覺理解能力。", "ja-JP": "Qwen3 VL 235B A22B非思考（Instruct）は、非思考指示シナリオ向けでありながら、強力な視覚理解を維持しています。", "ru-RU": "Qwen3 VL 235B A22B без режима мышления (Instruct) предназначена для сценариев выполнения инструкций без рассуждений, сохраняя при этом сильное визуальное понимание." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.1858732", "new": "1.18625288" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.2964683", "new": "0.29656322" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18605864", "new": "1.1858732" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29651466", "new": "0.2964683" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18596224", "new": "1.18605864" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29649056", "new": "0.29651466" }, { "date": "2026-08-12", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.1", "new": "0.11" }, { "date": "2026-08-12", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "1.9", "new": "1.04" }, { "date": "2026-08-12", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.21", "new": "0.26" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18560312", "new": "1.18596224" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29640078", "new": "0.29649056" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18551704", "new": "1.18560312" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29637926", "new": "0.29640078" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18564704", "new": "1.18551704" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29641176", "new": "0.29637926" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18566624", "new": "1.18564704" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29641656", "new": "0.29641176" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18557384", "new": "1.18566624" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29639346", "new": "0.29641656" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18387152", "new": "1.18557384" } ] }, { "slug": "alibaba/qwen3-vl-235b-a22b-thinking", "model_name": "qwen3-vl-235b-a22b-thinking", "display_name": "qwen3-vl-235b-a22b-thinking", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "litellm+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "4" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "pdf_input": true, "open_weights": true, "stream": true, "image_output": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-08-26", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "reasoning_config": { "mandatory": true, "budget_min": 1024 }, "knowledge_cutoff": "2025-03", "family": "qwen", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.8, "top_p": 0.95, "top_k": 20, "repetition_penalty": 1 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-VL-235B-A22B-Thinking", "Qwen3-VL-235B-A22B-Thinking", "accounts/fireworks/models/qwen3-vl-235b-a22b-thinking", "qwen/qwen3-vl-235b-a22b-thinking" ], "intro_i18n": { "zh-CN": "Qwen3 VL 235B A22B 思维模式（开源）针对复杂推理和长视频理解，具备顶级的视觉+文本推理能力。", "zh-TW": "Qwen3 VL 235B A22B 思維模式（開源）針對高難度推理和長視頻理解，具備頂級的視覺+文本推理能力。", "ja-JP": "Qwen3 VL 235B A22B思考モード（オープンソース）は、難しい推論や長いビデオ理解を対象とし、トップクラスの視覚+テキスト推論を提供します。", "ru-RU": "Qwen3 VL 235B A22B с режимом мышления (открытая) предназначена для сложных рассуждений и понимания длинных видео с первоклассным визуально-текстовым анализом." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.964683", "new": "2.9656322" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.2964683", "new": "0.29656322" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.9651466", "new": "2.964683" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29651466", "new": "0.2964683" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.9649056", "new": "2.9651466" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29649056", "new": "0.29651466" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.9640078", "new": "2.9649056" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29640078", "new": "0.29649056" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.9637926", "new": "2.9640078" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29637926", "new": "0.29640078" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.9641176", "new": "2.9637926" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29641176", "new": "0.29637926" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.9641656", "new": "2.9641176" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29641656", "new": "0.29641176" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.9639346", "new": "2.9641656" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29639346", "new": "0.29641656" }, { "date": "2026-08-07", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "3.95", "new": "4" }, { "date": "2026-08-07", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.98", "new": "0.4" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.9596788", "new": "2.9639346" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29596788", "new": "0.29639346" } ] }, { "slug": "alibaba/qwen3-vl-30b-a3b", "model_name": "qwen3-vl-30b-a3b", "display_name": "Qwen3-VL 30B-A3B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.8" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.4" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.108" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.431" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2025-04", "knowledge_cutoff": "2025-04", "max_input_tokens": 131072, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "open_weights": true, "stream": true }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/Qwen3-VL-30B-A3B-Instruct", "model_name": "Qwen3-VL-30B-A3B-Instruct", "display_name": "Qwen3 VL 30B A3B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.110294" }, "completion": { "unit": "per_M_tokens", "price": "0.441176" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-vl-30b-a3b-instruct" } ], "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "vision": true, "image_output": true, "video_input": true, "pdf_input": true, "open_weights": true, "parallel_function_calling": true, "stream": true, "prompt_caching": true }, "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2025-10-06", "knowledge_cutoff": "2025-03", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.7, "top_p": 0.8, "top_k": 20, "repetition_penalty": 1 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-VL-30B-A3B-Instruct", "accounts/fireworks/models/qwen3-vl-30b-a3b-instruct", "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct", "qwen/qwen3-vl-30b-a3b-instruct", "qwen3-vl-30b-a3b-instruct" ], "intro_i18n": { "zh-CN": "Qwen3-VL-30B-A3B-Instruct 是一款经过指令微调的 Qwen3-VL 模型，具备强大的视觉语言理解与生成能力。原生支持 256K 上下文长度，适用于多模态对话与图像条件生成任务。", "zh-TW": "Qwen3-VL-30B-A3B-Instruct 是指令微調的 Qwen3-VL 模型，具備強大的視覺語言理解與生成能力。原生支援 256K 上下文，適用於多模態對話與圖像條件生成。", "ja-JP": "Qwen3-VL-30B-A3B-Instructは、視覚と言語の理解と生成に優れた指示調整済みQwen3-VLモデルです。256Kのコンテキストをネイティブにサポートし、マルチモーダルチャットや画像条件付き生成に対応します。", "ru-RU": "Qwen3-VL-30B-A3B-Instruct — это модель Qwen3-VL, настроенная на выполнение инструкций, с сильным пониманием и генерацией в связке зрение-язык. Нативно поддерживает контекст до 256K для мультимодального чата и генерации, основанной на изображениях." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.41505562", "new": "0.415188508" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103763905", "new": "0.103797127" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "0.6", "new": "0.52" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.15", "new": "0.13" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.415120524", "new": "0.41505562" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103780131", "new": "0.103763905" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.415086784", "new": "0.415120524" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103771696", "new": "0.103780131" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.414961092", "new": "0.415086784" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103740273", "new": "0.103771696" }, { "date": "2026-08-10", "kind": "price", "provider": "evroc", "charge": "completion", "old": "0.92", "new": "0.94" }, { "date": "2026-08-10", "kind": "price", "provider": "evroc", "charge": "prompt", "old": "0.23", "new": "0.24" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.414930964", "new": "0.414961092" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103732741", "new": "0.103740273" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.414976464", "new": "0.414930964" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103744116", "new": "0.103732741" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.414983184", "new": "0.414976464" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103745796", "new": "0.103744116" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.414950844", "new": "0.414983184" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.103737711", "new": "0.103745796" } ] }, { "slug": "alibaba/Qwen3-VL-30B-A3B-Thinking", "model_name": "Qwen3-VL-30B-A3B-Thinking", "display_name": "Qwen3 VL 30B A3B Thinking", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.110294" }, "completion": { "unit": "per_M_tokens", "price": "1.102941" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-vl-30b-a3b-thinking" } ], "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "vision": true, "image_output": true, "video_input": true, "pdf_input": true, "open_weights": true, "parallel_function_calling": true, "stream": true, "prompt_caching": true }, "intro": "Multimodal model for analyzing text, images, documents, and rich media", "released_at": "2026-02-09", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": "2025-03", "family": "qwen", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.8, "top_p": 0.95, "top_k": 20, "repetition_penalty": 1 } }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-VL-30B-A3B-Thinking", "accounts/fireworks/models/qwen3-vl-30b-a3b-thinking", "qwen/qwen3-vl-30b-a3b-thinking", "qwen3-vl-30b-a3b-thinking" ], "intro_i18n": { "zh-CN": "Qwen3-VL-30B-A3B-Thinking 是 Qwen3-VL 的推理增强版本，专为多模态推理、图像转代码及复杂视觉理解任务优化。支持 256K 上下文，具备更强的思维链能力。", "zh-TW": "Qwen3-VL-30B-A3B-Thinking 是 Qwen3-VL 的推理增強版本，針對多模態推理、圖像轉程式碼與複雜視覺理解進行優化。支援 256K 上下文，具備更強的思考鏈能力。", "ja-JP": "Qwen3-VL-30B-A3B-Thinkingは、Qwen3-VLの推論強化バージョンで、マルチモーダル推論、画像からコードへの変換、複雑な視覚理解に最適化されています。256Kのコンテキストをサポートし、強力な思考の連鎖能力を備えています。", "ru-RU": "Qwen3-VL-30B-A3B-Thinking — версия Qwen3-VL с усиленными возможностями рассуждения, оптимизированная для мультимодальных рассуждений, преобразования изображений в код и сложного визуального понимания. Поддерживает контекст до 256K с улучшенной способностью к цепочкам рассуждений." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen3 VL 30B A3B Thinking" } ] }, { "slug": "alibaba/qwen3-vl-32b-instruct", "model_name": "qwen3-vl-32b-instruct", "display_name": "qwen3-vl-32b-instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "litellm+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.16" }, "completion": { "unit": "per_M_tokens", "price": "0.64" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.16" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.64" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "pdf_input": true, "open_weights": true, "stream": true, "image_output": true }, "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2025-10-23", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "parameters": { "supported": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.7, "top_p": 0.8, "top_k": 20, "repetition_penalty": 1 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-VL-32B-Instruct", "Qwen3-VL-32B-Instruct", "accounts/fireworks/models/qwen3-vl-32b-instruct", "qwen/qwen3-vl-32b-instruct" ], "intro_i18n": { "zh-CN": "Qwen3-VL-32B-Instruct 是 Qwen 团队推出的视觉语言模型，在多个 VL 基准测试中取得领先 SOTA 成绩。支持百万像素分辨率图像，具备强大的视觉理解、多语种 OCR、细粒度视觉定位与视觉对话能力，能够处理复杂多模态任务，并支持工具调用与前缀补全。", "zh-TW": "Qwen3-VL-32B-Instruct 是 Qwen 團隊推出的視覺語言模型，在多項 VL 基準測試中取得領先成績。支援百萬像素解析度圖像，具備強大的視覺理解、多語言 OCR、細粒度視覺定位與視覺對話能力。可處理複雜多模態任務，並支援工具呼叫與前綴補全。", "ja-JP": "Qwen3-VL-32B-Instructは、Qwenチームによる視覚と言語のモデルで、複数のVLベンチマークで最先端の結果を達成しています。メガピクセル解像度の画像をサポートし、強力な視覚理解、多言語OCR、精緻な視覚的グラウンディング、視覚対話に対応します。複雑なマルチモーダルタスクを処理し、ツール呼び出しやプレフィックス補完も可能です。", "ru-RU": "Qwen3-VL-32B-Instruct — это модель зрение-язык от команды Qwen с передовыми результатами на нескольких VL-бенчмарках. Поддерживает изображения с мегапиксельным разрешением и обеспечивает сильное визуальное понимание, многоязычное OCR, точную визуальную привязку и визуальный диалог. Обрабатывает сложные мультимодальные задачи и поддерживает вызов инструментов и автозавершение по префиксу." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "reasoning: false→true" } ] }, { "slug": "alibaba/qwen3-vl-32b-thinking", "model_name": "qwen3-vl-32b-thinking", "display_name": "qwen3-vl-32b-thinking", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "litellm+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.16" }, "completion": { "unit": "per_M_tokens", "price": "2.87" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.16" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.87" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "structured_output": true, "pdf_input": true, "stream": true, "image_output": true, "open_weights": true }, "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2025-10-21", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-VL-32B-Thinking", "Qwen3-VL-32B-Thinking", "qwen/qwen3-vl-32b-thinking" ], "intro_i18n": { "zh-CN": "Qwen3-VL-32B-Thinking 针对复杂视觉推理任务进行了优化，内置“思考模式”，在生成答案前输出中间推理步骤，提升多步骤逻辑、规划与复杂推理能力。支持百万像素图像，具备强大的视觉理解、多语种 OCR、细粒度定位、视觉对话、工具调用与前缀补全能力。", "zh-TW": "Qwen3-VL-32B-Thinking 專為複雜視覺推理優化。內建思考模式，在回答前生成中間推理步驟，提升多步邏輯、規劃與複雜推理能力。支援百萬像素圖像、強視覺理解、多語言 OCR、細粒度定位、視覺對話、工具呼叫與前綴補全。", "ja-JP": "Qwen3-VL-32B-Thinkingは、複雑な視覚的推論に最適化されたモデルです。内蔵の思考モードにより、回答前に中間的な推論ステップを生成し、マルチステップの論理、計画、複雑な推論を強化します。メガピクセル画像、強力な視覚理解、多言語OCR、精緻なグラウンディング、視覚対話、ツール呼び出し、プレフィックス補完に対応します。", "ru-RU": "Qwen3-VL-32B-Thinking оптимизирована для сложных визуальных рассуждений. Включает встроенный режим мышления, который генерирует промежуточные шаги рассуждений перед ответами, улучшая многошаговую логику, планирование и сложные рассуждения. Поддерживает изображения с мегапиксельным разрешением, сильное визуальное понимание, многоязычное OCR, точную привязку, визуальный диалог, вызов инструментов и автозавершение по префиксу." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" } ] }, { "slug": "alibaba/Qwen3-VL-8B-Instruct", "model_name": "Qwen3-VL-8B-Instruct", "display_name": "Qwen3 VL 8B Instruct", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.073529" }, "completion": { "unit": "per_M_tokens", "price": "0.294118" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-vl-8b-instruct" } ], "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "open_weights": true, "parallel_function_calling": true, "stream": true, "prompt_caching": true }, "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2025-10-14", "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "family": "qwen", "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.7, "top_p": 0.8 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-VL-8B-Instruct", "accounts/fireworks/models/qwen3-vl-8b-instruct", "qwen/qwen3-vl-8b-instruct", "qwen3-vl-8b-instruct" ], "intro_i18n": { "zh-CN": "Qwen3-VL-8B-Instruct 是基于 Qwen3-8B-Instruct 构建的视觉语言模型，训练于大规模图文数据，擅长通用视觉理解、以视觉为中心的对话及图像中的多语种文本识别，适用于视觉问答、图像描述、多模态指令跟随与工具使用等任务。", "zh-TW": "Qwen3-VL-8B-Instruct 是基於 Qwen3-8B-Instruct 的視覺語言模型，訓練於大量圖文資料。擅長通用視覺理解、以視覺為中心的對話與圖像中的多語言文字辨識，適用於視覺問答、圖說、多模態指令遵循與工具使用。", "ja-JP": "Qwen3-VL-8B-Instructは、Qwen3-8B-Instructをベースに構築された視覚と言語のモデルで、大規模な画像とテキストデータでトレーニングされています。一般的な視覚理解、視覚中心の対話、画像内の多言語テキスト認識に優れ、視覚QA、キャプション生成、マルチモーダル指示追従、ツール使用に適しています。", "ru-RU": "Qwen3-VL-8B-Instruct — это модель зрение-язык из серии Qwen3, построенная на базе Qwen3-8B-Instruct и обученная на больших объемах данных изображение-текст. Отличается общим визуальным пониманием, диалогом с упором на визуальные элементы и многоязычным распознаванием текста на изображениях. Подходит для визуального QA, создания подписей, мультимодального следования инструкциям и использования инструментов." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "reasoning: false→true" } ] }, { "slug": "alibaba/Qwen3-VL-8B-Thinking", "model_name": "Qwen3-VL-8B-Thinking", "display_name": "Qwen3 VL 8B Thinking", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.073529" }, "completion": { "unit": "per_M_tokens", "price": "0.735294" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwen3-vl-8b-thinking" } ], "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "open_weights": true, "stream": true }, "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2025-10-14", "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "family": "qwen", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3-VL-8B-Thinking", "qwen/qwen3-vl-8b-thinking", "qwen3-vl-8b-thinking" ], "intro_i18n": { "zh-CN": "Qwen3-VL-8B-Thinking 是 Qwen3 的视觉思考版本，专为复杂多步骤推理任务优化。在生成答案前输出思维链，提升准确性，适用于深度视觉问答与图像细节分析。", "zh-TW": "Qwen3-VL-8B-Thinking 是 Qwen3 的視覺思考版本，針對複雜多步推理進行優化。在回答前生成思考鏈以提升準確性，適用於深度視覺問答與細緻圖像分析。", "ja-JP": "Qwen3-VL-8B-Thinkingは、Qwen3の視覚的思考バージョンで、複雑なマルチステップ推論に最適化されています。回答前に思考の連鎖を生成し、精度を向上させます。深い視覚QAや詳細な画像分析に最適です。", "ru-RU": "Qwen3-VL-8B-Thinking — визуальная версия мышления в серии Qwen3, оптимизированная для сложных многошаговых рассуждений. Генерирует цепочку мышления перед ответами для повышения точности, идеально подходит для глубокого визуального QA и детального анализа изображений." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.74117075", "new": "0.74140805" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.074117075", "new": "0.074140805" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.74128665", "new": "0.74117075" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.074128665", "new": "0.074117075" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.7412264", "new": "0.74128665" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.07412264", "new": "0.074128665" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.74100195", "new": "0.7412264" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.074100195", "new": "0.07412264" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.74094815", "new": "0.74100195" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.074094815", "new": "0.074100195" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.7410294", "new": "0.74094815" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.07410294", "new": "0.074094815" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.7410414", "new": "0.7410294" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.07410414", "new": "0.07410294" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.74098365", "new": "0.7410414" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.074098365", "new": "0.07410414" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.7399197", "new": "0.74098365" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.07399197", "new": "0.074098365" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.74039175", "new": "0.7399197" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.074039175", "new": "0.07399197" } ] }, { "slug": "alibaba/qwen3-vl-flash", "model_name": "qwen3-vl-flash", "display_name": "Qwen3 VL Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.022059" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.044118" }, "prompt_0_128_0_256": { "unit": "per_M_tokens", "price": "0.088235" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "0.220588" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "0.441176" }, "completion_0_128_0_256": { "unit": "per_M_tokens", "price": "0.882353" } }, "provenance": { "base_charges": { "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_256": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_0_256": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 262144, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "vision": true, "image_output": true, "video_input": true, "pdf_input": true, "prompt_caching": true, "open_weights": true }, "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2025-10-09", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen/qwen3-vl-flash", "qwen/qwen3-vl-flash-2025-10-15", "qwen/qwen3-vl-flash-2026-01-22", "qwen3-vl-flash-2025-10-15", "qwen3-vl-flash-2026-01-22" ], "intro_i18n": { "zh-CN": "Qwen3 VL Flash：轻量级、高速推理版本，适用于对延迟敏感或高并发请求。", "zh-TW": "Qwen3 VL Flash：輕量高速推理版本，適用於對延遲敏感或高頻請求場景。", "ja-JP": "Qwen3 VL Flash：遅延に敏感または高トラフィックなリクエスト向けの軽量・高速推論モデルです。", "ru-RU": "Qwen3 VL Flash: легковесная, высокоскоростная версия рассуждений для задач с низкой задержкой или высоким объемом запросов." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Qwen3 VL Flash" } ] }, { "slug": "alibaba/qwen3-vl-plus", "model_name": "qwen3-vl-plus", "display_name": "Qwen3-VL Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "1.6" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "4.8" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.147059" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.220588" }, "prompt_0_128_infinity": { "unit": "per_M_tokens", "price": "0.441176" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "1.470588" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "2.205882" }, "completion_0_128_infinity": { "unit": "per_M_tokens", "price": "4.411765" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "models-dev", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_infinity": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.143353" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.433525" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2025-09-23", "knowledge_cutoff": "2025-04", "max_input_tokens": 262144, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwen/qwen3-vl-plus", "qwen/qwen3-vl-plus-2025-09-23", "qwen/qwen3-vl-plus-2025-12-19", "qwen3-vl-plus-2025-09-23", "qwen3-vl-plus-2025-12-19" ], "intro_i18n": { "zh-CN": "Qwen3 VL-Plus 是 Qwen3 的视觉增强版本，具备更强的多模态推理与视频处理能力。", "zh-TW": "Qwen3 VL-Plus 是強化視覺能力的 Qwen3 變體，具備更佳的多模態推理與影片處理能力。", "ja-JP": "Qwen3 VL-Plusは、視覚機能を強化したQwen3のバリアントで、マルチモーダル推論と動画処理に優れています。", "ru-RU": "Qwen3 VL-Plus — визуально-усиленный вариант Qwen3 с улучшенным мультимодальным логическим выводом и обработкой видео." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "alibaba/qwen3.5-122b-a10b", "model_name": "qwen3.5-122b-a10b", "display_name": "Qwen3.5 122B-A10B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "prompt_0_0_128": { "unit": "per_M_tokens", "price": "0.117647" }, "prompt_0_128_infinity": { "unit": "per_M_tokens", "price": "0.294118" }, "completion_0_0_128": { "unit": "per_M_tokens", "price": "0.941176" }, "completion_0_128_infinity": { "unit": "per_M_tokens", "price": "2.352941" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "prompt_0_0_128": "lobehub-modelbank", "prompt_0_128_infinity": "lobehub-modelbank", "completion_0_0_128": "lobehub-modelbank", "completion_0_128_infinity": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2026-02-23", "max_input_tokens": 262144, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "knowledge_cutoff": "2025-04", "docs_url": "https://openrouter.ai/qwen/qwen3.5-122b-a10b", "benchmarks": { "intelligence_index": 32.8, "coding_index": 45.7, "agentic_index": 21.3 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.6, "top_p": 0.95, "top_k": 20 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3.5-122B-A10B", "Qwen3.5-122B-A10B", "TEE/qwen3.5-122b-a10b", "bailian/qwen3.5-122b-a10b", "qwen/qwen3.5-122b-a10b", "qwen3-5-122b-a10b", "qwen3.5-122b-a10b:thinking" ], "intro_i18n": { "zh-CN": "Qwen3.5-122B-A10B 是 Qwen 团队开发的原生多模态大语言模型，具有 1220 亿总参数，仅 100 亿激活参数。它采用结合门控增量网络和稀疏专家混合（MoE）的高效混合架构，原生支持 256K 上下文长度，并可扩展至约 100 万个 token。", "zh-TW": "Qwen3.5-122B-A10B 是 Qwen 團隊開發的原生多模態大型語言模型，擁有 1220 億總參數，僅 100 億激活參數。它採用高效的混合架構，結合門控增量網絡和稀疏專家混合（MoE），原生支持 256K 上下文長度，並可擴展至約 100 萬個標記。", "ja-JP": "Qwen3.5-122B-A10BはQwenチームによるネイティブなマルチモーダル大規模言語モデルで、総パラメータ数は1220億、アクティブパラメータ数は10億です。効率的なハイブリッドアーキテクチャ（Gated Delta NetworksとSparse Mixture-of-Experts（MoE）の組み合わせ）を採用し、256Kの文脈長をネイティブにサポートし、約100万トークンまで拡張可能です。", "ru-RU": "Qwen3.5-122B-A10B — это нативная мультимодальная крупная языковая модель от команды Qwen с общим количеством параметров 122 миллиарда и только 10 миллиардами активных параметров. Она использует эффективную гибридную архитектуру, объединяющую Gated Delta Networks и Sparse Mixture-of-Experts (MoE), нативно поддерживает длину контекста 256K с возможностью расширения до примерно 1 миллиона токенов." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.4823415", "new": "1.4828161" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.20752781", "new": "0.207594254" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.4825733", "new": "1.4823415" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.207560262", "new": "0.20752781" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.4824528", "new": "1.4825733" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.207543392", "new": "0.207560262" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.4820039", "new": "1.4824528" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.207480546", "new": "0.207543392" }, { "date": "2026-08-11", "kind": "price", "provider": "trustedrouter", "charge": "prompt", "old": "0.273", "new": "0.231" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.4818963", "new": "1.4820039" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.207465482", "new": "0.207480546" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.4820588", "new": "1.4818963" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.207488232", "new": "0.207465482" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.4820828", "new": "1.4820588" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.207491592", "new": "0.207488232" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.4819673", "new": "1.4820828" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.207475422", "new": "0.207491592" }, { "date": "2026-08-07", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "2.08", "new": "2.4" }, { "date": "2026-08-07", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.26", "new": "0.29" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.4798394", "new": "1.4819673" } ] }, { "slug": "alibaba/qwen3.5-27b", "model_name": "qwen3.5-27b", "display_name": "Qwen3.5 27B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.4" }, "prompt_0_0_128": { "unit": "per_M_tokens", "price": "0.088235" }, "prompt_0_128_infinity": { "unit": "per_M_tokens", "price": "0.264706" }, "completion_0_0_128": { "unit": "per_M_tokens", "price": "0.705882" }, "completion_0_128_infinity": { "unit": "per_M_tokens", "price": "2.117647" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "prompt_0_0_128": "lobehub-modelbank", "prompt_0_128_infinity": "lobehub-modelbank", "completion_0_0_128": "lobehub-modelbank", "completion_0_128_infinity": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2026-02-23", "max_input_tokens": 262144, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "knowledge_cutoff": "2025-04", "docs_url": "https://openrouter.ai/qwen/qwen3.5-27b", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.6, "top_p": 0.95, "top_k": 20 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3.5-27B", "Qwen3.5-27B", "TEE/qwen3.5-27b", "bailian/qwen3.5-27b", "deepinfra/Qwen/Qwen3.5-27B", "qwen/qwen3.5-27b", "qwen3-5-27b", "qwen3.5-27b:thinking" ], "intro_i18n": { "zh-CN": "Qwen3.5-27B 是 Qwen 团队开发的原生多模态大语言模型，具有 270 亿参数。它采用结合门控增量网络和门控注意力的高效混合架构，原生支持 256K 上下文长度，并可扩展至约 100 万个 token。", "zh-TW": "Qwen3.5-27B 是 Qwen 團隊開發的原生多模態大型語言模型，擁有 270 億參數。它採用高效的混合架構，結合門控增量網絡和門控注意力，原生支持 256K 上下文長度，並可擴展至約 100 萬個標記。", "ja-JP": "Qwen3.5-27BはQwenチームによるネイティブなマルチモーダル大規模言語モデルで、総パラメータ数は270億です。効率的なハイブリッドアーキテクチャ（Gated Delta NetworksとGated Attentionの組み合わせ）を採用し、256Kの文脈長をネイティブにサポートし、約100万トークンまで拡張可能です。", "ru-RU": "Qwen3.5-27B — это нативная мультимодальная крупная языковая модель от команды Qwen с 27 миллиардами параметров. Она использует эффективную гибридную архитектуру, объединяющую Gated Delta Networks и Gated Attention, нативно поддерживает длину контекста 256K с возможностью расширения до примерно 1 миллиона токенов." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.71152392", "new": "0.711751728" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.08894049", "new": "0.088968966" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711635184", "new": "0.71152392" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088954398", "new": "0.08894049" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711577344", "new": "0.711635184" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088947168", "new": "0.088954398" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711361872", "new": "0.711577344" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088920234", "new": "0.088947168" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711310224", "new": "0.711361872" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088913778", "new": "0.088920234" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711388224", "new": "0.711310224" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088923528", "new": "0.088913778" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711399744", "new": "0.711388224" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088924968", "new": "0.088923528" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711344304", "new": "0.711399744" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088918038", "new": "0.088924968" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.710322912", "new": "0.711344304" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088790364", "new": "0.088918038" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.71077608", "new": "0.710322912" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.08884701", "new": "0.088790364" } ] }, { "slug": "alibaba/qwen3.5-35b-a3b", "model_name": "qwen3.5-35b-a3b", "display_name": "Qwen3.5 35B-A3B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "prompt_0_0_128": { "unit": "per_M_tokens", "price": "0.058824" }, "prompt_0_128_infinity": { "unit": "per_M_tokens", "price": "0.235294" }, "completion_0_0_128": { "unit": "per_M_tokens", "price": "0.470588" }, "completion_0_128_infinity": { "unit": "per_M_tokens", "price": "1.882353" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "prompt_0_0_128": "lobehub-modelbank", "prompt_0_128_infinity": "lobehub-modelbank", "completion_0_0_128": "lobehub-modelbank", "completion_0_128_infinity": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2026-02-23", "max_input_tokens": 262144, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "knowledge_cutoff": "2025-01", "docs_url": "https://openrouter.ai/qwen/qwen3.5-35b-a3b", "benchmarks": { "intelligence_index": 24.3, "coding_index": 37, "agentic_index": 11.8 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95, "top_k": 20 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3.5-35B-A3B", "Qwen3.5-35B-A3B", "bailian/qwen3.5-35b-a3b", "deepinfra/Qwen/Qwen3.5-35B-A3B", "qwen/qwen3-5-35b-a3b", "qwen/qwen3.5-35b-a3b", "qwen3-5-35b-a3b", "qwen3.5-35b-a3b:thinking" ], "intro_i18n": { "zh-CN": "Qwen3.5-35B-A3B 是 Qwen 团队开发的原生多模态大语言模型，具有 350 亿总参数，仅 30 亿激活参数。它采用结合门控增量网络和稀疏专家混合（MoE）的高效混合架构，原生支持 256K 上下文长度，并可扩展至约 100 万个 token。", "zh-TW": "Qwen3.5-35B-A3B 是 Qwen 團隊開發的原生多模態大型語言模型，擁有 350 億總參數，僅 30 億激活參數。它採用高效的混合架構，結合門控增量網絡和稀疏專家混合（MoE），原生支持 256K 上下文長度，並可擴展至約 100 萬個標記。", "ja-JP": "Qwen3.5-35B-A3BはQwenチームによるネイティブなマルチモーダル大規模言語モデルで、総パラメータ数は350億、アクティブパラメータ数は30億です。効率的なハイブリッドアーキテクチャ（Gated Delta NetworksとSparse Mixture-of-Experts（MoE）の組み合わせ）を採用し、256Kの文脈長をネイティブにサポートし、約100万トークンまで拡張可能です。", "ru-RU": "Qwen3.5-35B-A3B — это нативная мультимодальная крупная языковая модель от команды Qwen с общим количеством параметров 35 миллиардов и только 3 миллиардами активных параметров. Она использует эффективную гибридную архитектуру, объединяющую Gated Delta Networks и Sparse Mixture-of-Experts (MoE), нативно поддерживает длину контекста 256K с возможностью расширения до примерно 1 миллиона токенов." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.47434928", "new": "0.474501152" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.05929366", "new": "0.059312644" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.25", "new": "0.225" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "1.25", "new": "1.8" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.25", "new": "0.225" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "completion", "old": "1.05", "new": "1.3125" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "prompt", "old": "0.147", "new": "0.328125" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.474423456", "new": "0.47434928" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.059302932", "new": "0.05929366" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.05", "new": "0.25" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "1", "new": "1.25" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.14", "new": "0.25" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.474384896", "new": "0.474423456" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.059298112", "new": "0.059302932" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.474241248", "new": "0.474384896" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.059280156", "new": "0.059298112" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.474206816", "new": "0.474241248" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.059275852", "new": "0.059280156" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.474258816", "new": "0.474206816" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.059282352", "new": "0.059275852" } ] }, { "slug": "alibaba/qwen3.5-397b-a17b", "model_name": "qwen3.5-397b-a17b", "display_name": "Qwen3.5 397B-A17B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "3.6" }, "prompt_0_0_128": { "unit": "per_M_tokens", "price": "0.220588" }, "prompt_0_128_infinity": { "unit": "per_M_tokens", "price": "0.441176" }, "completion_0_0_128": { "unit": "per_M_tokens", "price": "1.058824" }, "completion_0_128_infinity": { "unit": "per_M_tokens", "price": "2.647059" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "prompt_0_0_128": "lobehub-modelbank", "prompt_0_128_infinity": "lobehub-modelbank", "completion_0_0_128": "lobehub-modelbank", "completion_0_128_infinity": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.43" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.58" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Large open Qwen multimodal MoE for visual agents and long technical tasks", "released_at": "2026-02-15", "max_input_tokens": 262144, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "stream": true, "parallel_function_calling": true }, "knowledge_cutoff": "2025-04", "model_type": "deep_thinking", "deprecated": true, "status": "deprecated", "reasoning_config": { "mandatory": false, "budget_min": 1 }, "docs_url": "https://openrouter.ai/qwen/qwen3.5-397b-a17b", "benchmarks": { "intelligence_index": 34.3, "coding_index": 48.2, "agentic_index": 19.8 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.6, "top_p": 0.95, "top_k": 20 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3.5-397B-A17B", "Qwen3.5-397B-A17B", "TEE/qwen3.5-397b-a17b", "bailian/qwen3.5-397b-a17b", "deepinfra/Qwen/Qwen3.5-397B-A17B", "nebius/qwen/qwen3.5-397b-a17b", "novita/qwen/qwen3.5-397b-a17b", "qwen/qwen3.5-397b-a17b", "qwen3-5-397b-a17b", "qwen3.5-397b-a17b:free" ], "intro_i18n": { "zh-CN": "Qwen3.5-397B-A17B 是 Qwen3.5 系列中最新的视觉语言模型，采用专家混合（MoE）架构，具有 3970 亿总参数和 170 亿激活参数。它原生支持 256K 上下文长度，并可扩展至约 100 万个 token，支持 201 种语言，提供统一的视觉语言理解、工具调用和推理能力。", "zh-TW": "Qwen3.5-397B-A17B 是 Qwen3.5 系列中最新的視覺語言模型，採用專家混合（MoE）架構，擁有 3970 億總參數和 170 億激活參數。它原生支持 256K 上下文長度，並可擴展至約 100 萬個標記，支持 201 種語言，提供統一的視覺語言理解、工具調用和推理能力。", "ja-JP": "Qwen3.5-397B-A17BはQwen3.5シリーズの最新のビジョンと言語モデルで、Mixture-of-Experts（MoE）アーキテクチャを採用し、総パラメータ数は3970億、アクティブパラメータ数は170億です。256Kの文脈長をネイティブにサポートし、約100万トークンまで拡張可能で、201言語をサポートし、統一されたビジョンと言語の理解、ツール呼び出し、推論能力を提供します。", "ru-RU": "Qwen3.5-397B-A17B — это последняя модель в серии Qwen3.5 для понимания языка и изображений, использующая архитектуру Mixture-of-Experts (MoE) с общим количеством параметров 397 миллиардов и 17 миллиардами активных параметров. Она нативно поддерживает длину контекста 256K с возможностью расширения до примерно 1 миллиона токенов, поддерживает 201 язык и предоставляет унифицированные возможности понимания языка и изображений, вызова инструментов и рассуждений." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "1.53", "new": "2.91" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.27", "new": "0.48" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.3", "new": "0.045" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.045", "new": "0.3" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "3.6", "new": "3" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "3", "new": "3.6" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.5", "new": "0.45" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.45", "new": "0.5" }, { "date": "2026-08-10", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.3", "new": "0.195" }, { "date": "2026-08-10", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.195", "new": "0.3" }, { "date": "2026-08-10", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "3.6", "new": "2.34" }, { "date": "2026-08-10", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "2.34", "new": "3.6" }, { "date": "2026-08-10", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.5", "new": "0.39" }, { "date": "2026-08-10", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.39", "new": "0.5" }, { "date": "2026-08-09", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.195", "new": "0.3" }, { "date": "2026-08-09", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.3", "new": "0.195" }, { "date": "2026-08-09", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "2.34", "new": "3.6" }, { "date": "2026-08-09", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "3.6", "new": "2.34" }, { "date": "2026-08-09", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.39", "new": "0.5" }, { "date": "2026-08-09", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.5", "new": "0.39" } ] }, { "slug": "alibaba/qwen3.5-plus", "model_name": "qwen3.5-plus", "display_name": "Qwen3.5 Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2.4" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.4" }, "cache_read_0_0_128": { "unit": "per_M_tokens", "price": "0.011765" }, "cache_read_0_128_0_256": { "unit": "per_M_tokens", "price": "0.029412" }, "cache_read_0_256_infinity": { "unit": "per_M_tokens", "price": "0.058824" }, "cache_write_0_0_128": { "unit": "per_M_tokens", "price": "0.147059" }, "cache_write_0_128_0_256": { "unit": "per_M_tokens", "price": "0.367647" }, "cache_write_0_256_infinity": { "unit": "per_M_tokens", "price": "0.735294" }, "prompt_0_0_128": { "unit": "per_M_tokens", "price": "0.117647" }, "prompt_0_128_0_256": { "unit": "per_M_tokens", "price": "0.294118" }, "prompt_0_256_infinity": { "unit": "per_M_tokens", "price": "0.588235" }, "completion_0_0_128": { "unit": "per_M_tokens", "price": "0.705882" }, "completion_0_128_0_256": { "unit": "per_M_tokens", "price": "1.764706" }, "completion_0_256_infinity": { "unit": "per_M_tokens", "price": "3.529412" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "models-dev", "cache_read_0_0_128": "lobehub-modelbank", "cache_read_0_128_0_256": "lobehub-modelbank", "cache_read_0_256_infinity": "lobehub-modelbank", "cache_write_0_0_128": "lobehub-modelbank", "cache_write_0_128_0_256": "lobehub-modelbank", "cache_write_0_256_infinity": "lobehub-modelbank", "prompt_0_0_128": "lobehub-modelbank", "prompt_0_128_0_256": "lobehub-modelbank", "prompt_0_256_infinity": "lobehub-modelbank", "completion_0_0_128": "lobehub-modelbank", "completion_0_128_0_256": "lobehub-modelbank", "completion_0_256_infinity": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.573" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.44" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwen3.5-plus-2026-04-20" } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2026-02-16", "knowledge_cutoff": "2025-04", "max_input_tokens": 1000000, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "stream": true, "web_search": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1 }, "deprecated": true, "status": "deprecated", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3.5-Plus", "Qwen3.5-Plus", "alibaba/qwen3.5-plus", "bailian/qwen3.5-plus", "qwen/qwen3.5-plus", "qwen/qwen3.5-plus-2026-02-15", "qwen/qwen3.5-plus-20260420", "qwen3-5-plus", "qwen3.5-plus-2026-02-15", "qwen3.5-plus-2026-04-20" ], "intro_i18n": { "zh-CN": "Qwen3.5 Plus 支持文本、图像与视频输入，在纯文本任务上的表现可比肩 Qwen3 Max，且成本更低。其多模态能力相较 Qwen3 VL 系列有显著提升。", "zh-TW": "Qwen3.5 Plus 支援文字、影像與影片輸入，在純文字任務上的效能接近 Qwen3 Max，但成本更低、表現更佳；多模態能力也較 Qwen3 VL 系列大幅提升。", "ja-JP": "Qwen3.5 Plus はテキスト、画像、動画入力に対応します。テキストタスクの性能は Qwen3 Max と同等で、より高性能かつ低コストです。マルチモーダル能力は Qwen3 VL シリーズより大幅に向上しています。", "ru-RU": "Qwen3.5 Plus поддерживает ввод текста, изображений и видео. Производительность в текстовых задачах сопоставима с Qwen3 Max, но модель быстрее и дешевле. Мультимодальные возможности значительно улучшены по сравнению с серией Qwen3 VL." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" } ] }, { "slug": "alibaba/qwen3.6-27b", "model_name": "qwen3.6-27b", "display_name": "Qwen3.6 27B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "3.6" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "18", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2026-04-22", "max_input_tokens": 262144, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "status": "beta", "docs_url": "https://console.groq.com/docs/model/qwen/qwen3.6-27b", "benchmarks": { "intelligence_index": 37.7, "coding_index": 53.7, "agentic_index": 27.5 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3.6-27B", "Qwen3.6-27B", "TEE/qwen3.6-27b", "alibaba/qwen3.6-27b", "alibaba/qwen3.6-27b:thinking", "bailian/qwen3.6-27b", "hf:Qwen/Qwen3.6-27B", "qwen/qwen3.6-27b", "qwen3-6-27b" ], "intro_i18n": { "zh-CN": "Qwen3.6-27B 是 Qwen3.6 系列中首个开源中型密集模型，在代码生成、代理工作流和真实开发场景中具有关键增强功能。与 Qwen3.5-27B 相比，该模型在前端开发、代码库级推理、工具调用和复杂问题解决方面表现显著提升，并新增了历史推理能力优化。", "zh-TW": "Qwen3.6-27B 是 Qwen3.6 系列中首個開源中型密集模型，針對代碼生成、代理工作流程和真實世界開發場景進行了關鍵增強。與 Qwen3.5-27B 相比，此模型在前端開發、倉庫級推理、工具調用和複雜問題解決方面顯著提升，並新增了歷史推理能力優化。", "ja-JP": "Qwen3.6-27BはQwen3.6シリーズの最初のオープンソース中型密集モデルで、コード生成、エージェントワークフロー、実世界の開発シナリオ向けに重要な強化が施されています。Qwen3.5-27Bと比較して、このモデルはフロントエンド開発、リポジトリレベルの推論、ツール呼び出し、複雑な問題解決において大幅な改善を示し、新たに履歴推論能力の最適化が追加されています。", "ru-RU": "Qwen3.6-27B — это первая открытая средняя плотная модель в серии Qwen3.6 с ключевыми улучшениями для генерации кода, рабочих процессов агентов и реальных сценариев разработки. По сравнению с Qwen3.5-27B, эта модель демонстрирует значительные улучшения в разработке интерфейсов, рассуждениях на уровне репозиториев, вызове инструментов и решении сложных задач, с новыми оптимизациями для исторического мышления." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.71152392", "new": "0.711751728" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.08894049", "new": "0.088968966" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.1984", "new": "0.1854" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.3968", "new": "0.3708" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711635184", "new": "0.71152392" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088954398", "new": "0.08894049" }, { "date": "2026-08-12", "kind": "price", "provider": "aiand", "charge": "completion", "old": "0", "new": "3.2" }, { "date": "2026-08-12", "kind": "price", "provider": "aiand", "charge": "prompt", "old": "0", "new": "0.32" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711577344", "new": "0.711635184" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088947168", "new": "0.088954398" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711361872", "new": "0.711577344" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088920234", "new": "0.088947168" }, { "date": "2026-08-10", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.1834", "new": "0.1984" }, { "date": "2026-08-10", "kind": "price", "provider": "io-net", "charge": "completion", "old": "3.13", "new": "3.03" }, { "date": "2026-08-10", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.3668", "new": "0.3968" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711310224", "new": "0.711361872" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088913778", "new": "0.088920234" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711388224", "new": "0.711310224" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.088923528", "new": "0.088913778" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.711399744", "new": "0.711388224" } ] }, { "slug": "alibaba/qwen3.6-35b-a3b", "model_name": "qwen3.6-35b-a3b", "display_name": "Qwen3.6 35B-A3B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.248" }, "completion": { "unit": "per_M_tokens", "price": "1.485" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.248" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.8", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.485" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10.8", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Open multimodal Qwen MoE for local agents that need vision, audio, and code", "released_at": "2026-04-17", "max_input_tokens": 262144, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true }, "model_type": "deep_thinking", "knowledge_cutoff": "2025-04", "status": "beta", "benchmarks": { "intelligence_index": 32.1, "coding_index": 41.9, "agentic_index": 21.6 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95, "top_k": 20 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3.6-35B-A3B", "Qwen/Qwen3.6-35B-A3B:thinking", "Qwen3.6-35B-A3B", "TEE/qwen3.6-35b-a3b", "alibaba/qwen3.6-35b-a3b", "qwen/Qwen3.6-35B-A3B", "qwen/Qwen3.6-35B-A3B:thinking", "qwen/qwen3-6-35b-a3b", "qwen/qwen3.6-35b-a3b", "qwen3-6-35b-a3b" ], "intro_i18n": { "zh-CN": "Qwen3.6-35B-A3B 是 Qwen 团队在 Qwen3.6 系列中推出的大语言模型，采用 Mixture-of-Experts（MoE）架构，总参数量为 350 亿，激活参数量为 30 亿。在高效推理与卓越性能之间实现了良好平衡，支持思考模式与非思考模式，可在快速响应与深度推理之间灵活切换。", "zh-TW": "Qwen3.6-35B-A3B 是 Qwen 團隊在 Qwen3.6 系列中推出的大型語言模型，採用 Mixture-of-Experts（MoE）架構，具備 350 億總參數與 30 億啟用參數。其兼具高效推理與卓越效能，並支援思考模式與非思考模式，可在快速回應與深度推理間靈活切換。", "ja-JP": "Qwen3.6-35B-A3B は、Qwen チームによる Qwen3.6 シリーズの大規模言語モデルで、35B の総パラメータと 3B のアクティブパラメータを備えた Mixture-of-Experts (MoE) アーキテクチャを採用しています。高速推論と優れた性能の両立を図り、思考モードと非思考モードの双方をサポートし、迅速な応答と深い推論を柔軟に切り替えることができます。", "ru-RU": "Qwen3.6-35B-A3B — это крупная языковая модель команды Qwen из серии Qwen3.6, использующая архитектуру Mixture-of-Experts (MoE) с общим числом параметров 35B и 3B активных параметров. Она сочетает эффективный вывод с высокой производительностью и поддерживает как режимы с размышлением, так и без него, позволяя гибко переключаться между быстрым ответом и глубоким рассуждением." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.0824", "new": "0.0884" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.06275", "new": "1.11675" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.1648", "new": "0.1768" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.47434928", "new": "0.474501152" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.05929366", "new": "0.059312644" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "completion", "old": "0.315", "new": "1.05" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "prompt", "old": "0.04725", "new": "0.105" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.0798", "new": "0.0824" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.084", "new": "1.06275" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.1596", "new": "0.1648" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.474423456", "new": "0.47434928" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.059302932", "new": "0.05929366" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.0934", "new": "0.0798" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.23675", "new": "1.084" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.1868", "new": "0.1596" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.474384896", "new": "0.474423456" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.059298112", "new": "0.059302932" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.0886", "new": "0.0934" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.11675", "new": "1.23675" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.1772", "new": "0.1868" } ] }, { "slug": "alibaba/qwen3.6-flash", "model_name": "qwen3.6-flash", "display_name": "Qwen3.6 Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1875" }, "completion": { "unit": "per_M_tokens", "price": "1.125" }, "cache_write": { "unit": "per_M_tokens", "price": "0.234375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.035294" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_write": "models-dev", "cache_read": "lobehub-modelbank" }, "tracks": [ { "label": "Context >256K", "source": "lobehub-modelbank", "charge_sources": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank" } }, { "label": "Base pricing", "source": "models-dev+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_write": "models-dev", "cache_read": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1875" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "7.2", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >256K", "factor": "1", "charge_factors": { "cache_read": "4" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 256000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Qwen vision-language model for visual reasoning, documents, and agent tasks", "released_at": "2026-04-27", "max_input_tokens": 1000000, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "qwen3.6", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "web_search": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1 }, "knowledge_cutoff": "2025-04", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen3.6-Flash", "alibaba/qwen3.6-flash", "bailian/qwen3.6-flash", "qwen/qwen3.6-flash", "qwen/qwen3.6-flash-2026-04-16", "qwen3-6-flash", "qwen3.6-flash-2026-04-16" ], "intro_i18n": { "zh-CN": "Qwen3.6 原生视觉语言 Flash 模型相比 3.5-Flash 具备显著性能提升。该模型重点增强了智能体编码能力（在多项代码智能体基准中大幅领先前代），并进一步提升数学推理与代码推理表现。在视觉方面，空间智能显著增强，尤其在物体定位与目标检测任务上表现突出。", "zh-TW": "Qwen3.6 原生視覺語言 Flash 模型的性能相較 3.5-Flash 版本有明顯提升。本模型著重強化代理式程式碼能力（在多項程式代理基準上大幅領先前代），並提升數學推理與程式碼推理能力。在視覺方面，其空間智能獲得顯著增強，尤其在物件定位與目標檢測任務上有卓越表現。", "ja-JP": "Qwen3.6 ネイティブ視覚言語 Flash モデルは、3.5-Flash と比べて大幅に性能が向上しています。とくにエージェント型コーディング能力（複数のコードエージェントベンチマークで前世代を大幅に上回る）、数理推論・コード推論が強化されています。視覚面では空間認識能力が向上し、物体位置特定やターゲット検出で顕著な改善が見られます。", "ru-RU": "Нативная модель Qwen3.6 Flash для визуально-языковых задач демонстрирует значительно улучшенную производительность по сравнению с версией 3.5-Flash. Она фокусируется на усилении возможностей агентного программирования (существенно превосходя предыдущую версию по множеству бенчмарков), а также улучшает способности к математическим рассуждениям и анализу кода. В области компьютерного зрения модель демонстрирует заметный рост пространственного интеллекта, особенно в задачах локализации объектов и обнаружения целей." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" } ] }, { "slug": "alibaba/qwen3.6-max-preview", "model_name": "qwen3.6-max-preview", "display_name": "Qwen3.6 Max Preview", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.3" }, "completion": { "unit": "per_M_tokens", "price": "7.8" }, "cache_read": { "unit": "per_M_tokens", "price": "0.13" }, "cache_write": { "unit": "per_M_tokens", "price": "1.625" }, "cache_read_0_0_128": { "unit": "per_M_tokens", "price": "0.264706" }, "cache_read_0_128_infinity": { "unit": "per_M_tokens", "price": "0.441176" }, "prompt_0_0_128": { "unit": "per_M_tokens", "price": "1.323529" }, "prompt_0_128_infinity": { "unit": "per_M_tokens", "price": "2.205882" }, "completion_0_0_128": { "unit": "per_M_tokens", "price": "7.941176" }, "completion_0_128_infinity": { "unit": "per_M_tokens", "price": "13.235294" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_read_0_0_128": "lobehub-modelbank", "cache_read_0_128_infinity": "lobehub-modelbank", "prompt_0_0_128": "lobehub-modelbank", "prompt_0_128_infinity": "lobehub-modelbank", "completion_0_0_128": "lobehub-modelbank", "completion_0_128_infinity": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "intro": "Flagship Qwen model for complex reasoning, coding, and agentic workflows", "released_at": "2026-04-20", "knowledge_cutoff": "2025-04", "max_input_tokens": 262144, "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "web_search": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bailian/qwen3.6-max-preview", "qwen/qwen3.6-max-preview", "qwen3-6-max-preview" ], "intro_i18n": { "zh-CN": "Qwen3.6 系列中规模最大的闭源模型。具备更强的世界知识、指令理解能力与智能体编码性能，可处理复杂任务。该模型为纯文本模型，默认支持思考模式、显式缓存与函数调用。", "zh-TW": "Qwen3.6 系列中最大的封閉源模型，具備更強的世界知識、指令跟隨能力與代理式程式碼性能，適用於複雜任務。該模型為純文字模式，預設支援思考模式、顯式快取與函式呼叫。", "ja-JP": "Qwen3.6 シリーズで最大規模のクローズドソースモデルです。世界知識、指示理解、エージェント型コーディングなど複雑なタスクに対して高い性能を発揮します。テキスト専用で、思考モードがデフォルト有効、明示的なキャッシング、関数呼び出しに対応しています。", "ru-RU": "Крупнейшая закрытая модель серии Qwen3.6. Она обеспечивает улучшенные знания о мире, лучшее следование инструкциям и высокую производительность в агентном программировании для сложных задач. Это текстовая модель, по умолчанию поддерживает режим размышления, явное кэширование и вызов функций." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "alibaba/qwen3.6-plus", "model_name": "qwen3.6-plus", "display_name": "Qwen3.6 Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+lobehub-modelbank+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "cache_write": { "unit": "per_M_tokens", "price": "0.625" }, "prompt_0_0_256": { "unit": "per_M_tokens", "price": "0.294118" }, "prompt_0_256_1": { "unit": "per_M_tokens", "price": "1.176471" }, "completion_0_0_256": { "unit": "per_M_tokens", "price": "1.764706" }, "completion_0_256_1": { "unit": "per_M_tokens", "price": "7.058824" }, "cache_read_0_0_256": { "unit": "per_M_tokens", "price": "0.058824" }, "cache_read_0_256_1": { "unit": "per_M_tokens", "price": "0.235294" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "prompt_0_0_256": "lobehub-modelbank", "prompt_0_256_1": "lobehub-modelbank", "completion_0_0_256": "lobehub-modelbank", "completion_0_256_1": "lobehub-modelbank", "cache_read_0_0_256": "lobehub-modelbank", "cache_read_0_256_1": "lobehub-modelbank" }, "tracks": [ { "label": "Context >256K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" } }, { "label": "Base pricing", "source": "models-dev+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "prompt_0_0_256": "lobehub-modelbank", "prompt_0_256_1": "lobehub-modelbank", "completion_0_0_256": "lobehub-modelbank", "completion_0_256_1": "lobehub-modelbank", "cache_read_0_0_256": "lobehub-modelbank", "cache_read_0_256_1": "lobehub-modelbank" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Context >256K", "factor": "1", "charge_factors": { "prompt": "4", "completion": "2", "cache_read": "4", "cache_write": "4" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 256000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Earlier Qwen multimodal workhorse for million-token agent and document tasks", "released_at": "2026-04-02", "knowledge_cutoff": "2025-04", "max_input_tokens": 1000000, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "web_search": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1 }, "deprecated": true, "status": "deprecated", "docs_url": "https://openrouter.ai/qwen/qwen3.6-plus", "benchmarks": { "intelligence_index": 40.5, "coding_index": 54.5, "agentic_index": 29 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3.6-Plus", "Qwen3.6-Plus", "alibaba/qwen3.6-plus", "bailian/qwen3.6-plus", "qwen/qwen3.6-plus", "qwen/qwen3.6-plus-2026-04-02", "qwen/qwen3.6-plus:free", "qwen3-6-plus", "qwen3.6-plus-2026-04-02", "qwen3.6-plus-free", "stealth/qwen3.6-plus" ], "intro_i18n": { "zh-CN": "Qwen3.6 Plus支持文本、图像和视频输入，在质量、速度和成本之间实现了平衡性能。与Qwen3 VL系列相比，其多模态能力显著提升。", "zh-TW": "Qwen3.6 Plus 支持文本、影像和視頻輸入。在質量、速度和成本方面提供平衡的性能。與 Qwen3 VL 系列相比，其多模態能力顯著提升。", "ja-JP": "Qwen3.6 Plusはテキスト、画像、動画入力をサポートします。品質、速度、コストのバランスが取れた性能を提供し、Qwen3 VLシリーズと比較してマルチモーダル機能が大幅に向上しています。", "ru-RU": "Qwen3.6 Plus поддерживает ввод текста, изображений и видео. Она обеспечивает сбалансированную производительность по качеству, скорости и стоимости. Её мультимодальные возможности значительно улучшены по сравнению с серией Qwen3 VL." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "1.12", "new": "2.42" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.18", "new": "0.4" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "7.1152392", "new": "7.11751728" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.1858732", "new": "1.18625288" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "7.11635184", "new": "7.1152392" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.18605864", "new": "1.1858732" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "7.11577344", "new": "7.11635184" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.18596224", "new": "1.18605864" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "7.11361872", "new": "7.11577344" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.18560312", "new": "1.18596224" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "7.11310224", "new": "7.11361872" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.18551704", "new": "1.18560312" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "7.11388224", "new": "7.11310224" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.18564704", "new": "1.18551704" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "7.11399744", "new": "7.11388224" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.18566624", "new": "1.18564704" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "7.11344304", "new": "7.11399744" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.18557384", "new": "1.18566624" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "7.10322912", "new": "7.11344304" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.18387152", "new": "1.18557384" } ] }, { "slug": "alibaba/qwen3.6-plus-256k", "model_name": "qwen3.6-plus-256k", "display_name": "Qwen3.6 Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Qwen3.6 Plus" } ] }, { "slug": "alibaba/qwen3.7-max", "model_name": "qwen3.7-max", "display_name": "Qwen3.7 Max", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+litellm+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "cache_write": { "unit": "per_M_tokens", "price": "3.125" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.4000000000000004", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "7.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "36", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks", "released_at": "2026-05-21", "max_input_tokens": 1000000, "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "web_search": true }, "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models", "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1 }, "benchmarks": { "intelligence_index": 46.7, "coding_index": 66, "agentic_index": 30.9 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3.7-Max", "Qwen3.7-Max", "alibaba/qwen3.7-max", "bailian/qwen3.7-max", "cline-pass/qwen3.7-max", "qwen/qwen3.7-max", "qwen/qwen3.7-max-2026-05-20", "qwen/qwen3.7-max-2026-06-08", "qwen3-7-max", "qwen3.7-max-2026-05-20", "qwen3.7-max-2026-06-08", "qwen3.7-max:thinking" ], "intro_i18n": { "zh-CN": "Qwen3.7 Max是AI代理时代的旗舰全能模型，提供全面的文本、图像和视频理解能力。它在推理、函数调用和代理任务执行性能方面表现卓越。", "zh-TW": "Qwen3.7 Max 是 AI 代理時代的旗艦全能模型，提供全面的文本、影像和視頻理解能力。它在推理、函數調用和代理任務執行性能方面表現卓越。", "ja-JP": "Qwen3.7 MaxはAIエージェント時代のフラッグシップ万能モデルで、テキスト、画像、動画理解において包括的な能力を提供します。優れた推論、関数呼び出し、エージェントタスク実行性能を備えています。", "ru-RU": "Qwen3.7 Max — это флагманская универсальная модель эпохи AI-агентов, предлагающая комплексные возможности в понимании текста, изображений и видео. Она обеспечивает превосходное рассуждение, вызов функций и выполнение агентных задач." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" } ] }, { "slug": "alibaba/qwen3.7-plus", "model_name": "qwen3.7-plus", "display_name": "Qwen3.7 Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "cache_write": { "unit": "per_M_tokens", "price": "0.625" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "tracks": [ { "label": "Context >256K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.05" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >256K", "factor": "1", "charge_factors": { "prompt": "4", "completion": "2", "cache_read": "4", "cache_write": "4" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 256000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Multimodal Qwen workhorse for long-context agents, visual inputs, and coding", "released_at": "2026-06-02", "knowledge_cutoff": "2025-04", "max_input_tokens": 1000000, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "web_search": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1 }, "benchmarks": { "intelligence_index": 39.4, "coding_index": 55.9, "agentic_index": 20.7 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3.7-Plus", "Qwen3.7-Plus", "alibaba/qwen3.7-plus", "bailian/qwen3.7-plus", "cline-pass/qwen3.7-plus", "fireworks/qwen3.7-plus", "qwen/qwen3.7-plus", "qwen/qwen3.7-plus-2026-05-26", "qwen3-7-plus", "qwen3.7-plus-2026-05-26", "qwen3.7-plus:thinking" ], "intro_i18n": { "zh-CN": "Qwen3.7 Plus是一款多模态交互混合代理模型，基于Qwen3.7系列的文本能力，统一了视觉与语言。它在GUI操作、视觉编码和复杂代理工作流方面表现出色。", "zh-TW": "Qwen3.7 Plus 是一款多模態交互混合代理模型，基於 Qwen3.7 系列的文本能力，統一視覺與語言。它在 GUI 操作、視覺編程和複雜代理工作流方面表現出色。", "ja-JP": "Qwen3.7 Plusはマルチモーダルインタラクティブハイブリッドエージェントモデルで、Qwen3.7シリーズのテキスト能力を基盤に、ビジョンと言語を統合しています。GUI操作、視覚的コーディング、複雑なエージェントワークフローに優れています。", "ru-RU": "Qwen3.7 Plus — это мультимодальная интерактивная гибридная агентная модель, основанная на текстовых возможностях серии Qwen3.7, объединяющая визуализацию и язык. Она превосходно справляется с операциями GUI, визуальным кодированием и сложными агентными рабочими процессами." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" } ] }, { "slug": "alibaba/qwen3.8-max", "model_name": "qwen3.8-max", "display_name": "Qwen3.8 Max", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.25" }, "cache_write": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows", "released_at": "2026-08-03", "max_input_tokens": 1000000, "max_output_tokens": 131072, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "family": "qwen", "reasoning_config": { "mandatory": true, "budget_min": 0 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true }, "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models", "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 58.1, "coding_index": 71.8, "agentic_index": 58.4 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/Qwen3.8-Max", "alibaba/qwen3.8-max", "bailian/qwen3.8-max", "novita/qwen/qwen3.8-max", "qwen/qwen3.8-max", "qwen3-8-max", "qwen3.8-max:thinking" ], "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" } ] }, { "slug": "alibaba/QwQ-32B", "model_name": "QwQ-32B", "display_name": "QwQ 32B", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb+lobehub-modelbank+pricetoken", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.287" }, "completion": { "unit": "per_M_tokens", "price": "0.861" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.287" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "llmdb", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.861" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with llmdb; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pricetoken", "selected_source": "llmdb", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.287" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2222" }, "message": "prompt from pricetoken conflicts with llmdb; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pricetoken", "selected_source": "llmdb", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.861" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5556" }, "message": "completion from pricetoken conflicts with llmdb; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "qwq-32b" } ], "released_at": "2024-12", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "deep_thinking", "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "stream": true, "structured_output": true, "open_weights": true, "web_search": true, "parallel_function_calling": true }, "intro": "Qwen reasoning model for deliberate problem solving, math, and coding", "docs_url": "https://nebius.com/prices-ai-studio", "deprecated": true, "deprecation_date": "2025-06-25", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "@cf/qwen/qwq-32b", "Qwen/QwQ-32B", "accounts/fireworks/models/qwq-32b", "qwen/qwq-32b", "qwq-32b", "qwq-32b:free", "workers-ai/@cf/qwen/qwq-32b" ], "intro_i18n": { "zh-CN": "QwQ 是 Qwen 系列中的推理模型。相比标准指令微调模型，具备更强的思维与推理能力，显著提升下游复杂任务表现。QwQ-32B 是一款中型推理模型，性能可媲美 DeepSeek-R1 和 o1-mini 等顶级模型。", "zh-TW": "QwQ 是 Qwen 系列中的推理模型。相較於標準指令微調模型，它具備更強的思考與推理能力，顯著提升下游任務表現，特別是在處理複雜問題時。QwQ-32B 是中型推理模型，表現可媲美 DeepSeek-R1 與 o1-mini 等頂尖模型。", "ja-JP": "QwQは、Qwenファミリーの推論モデルです。標準的な指示調整モデルと比較して、思考と推論能力に優れ、特に複雑な問題において下流性能を大幅に向上させます。QwQ-32Bは、DeepSeek-R1やo1-miniと並ぶ中規模の推論モデルです。", "ru-RU": "QwQ — модель логического вывода из семейства Qwen. По сравнению со стандартными моделями, обученными на инструкциях, она обеспечивает более глубокое мышление и логический анализ, значительно повышая производительность на сложных задачах. QwQ-32B — среднеразмерная модель, сопоставимая с ведущими моделями, такими как DeepSeek-R1 и o1-mini." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14823415", "new": "0.14828161" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59302932", "new": "0.5929366" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14825733", "new": "0.14823415" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59298112", "new": "0.59302932" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14824528", "new": "0.14825733" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59280156", "new": "0.59298112" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820039", "new": "0.14824528" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59275852", "new": "0.59280156" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14818963", "new": "0.14820039" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59282352", "new": "0.59275852" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820588", "new": "0.14818963" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59283312", "new": "0.59282352" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14820828", "new": "0.14820588" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59278692", "new": "0.59283312" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14819673", "new": "0.14820828" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.59193576", "new": "0.59278692" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14798394", "new": "0.14819673" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.5923134", "new": "0.59193576" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14807835", "new": "0.14798394" } ] }, { "slug": "alibaba/QwQ-32B-Preview", "model_name": "QwQ-32B-Preview", "display_name": "QwQ 32B Preview", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.294118" }, "completion": { "unit": "per_M_tokens", "price": "0.882353" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "qwq-32b-preview" } ], "released_at": "2024-11-28", "max_input_tokens": 32768, "max_output_tokens": 16384, "model_type": "deep_thinking", "capabilities": { "reasoning": true, "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Qwen/QwQ-32B-Preview", "qwen/qwq-32b-preview", "qwq-32b-preview" ], "intro_i18n": { "zh-CN": "Qwen QwQ 是一个实验性研究模型，专注于提升推理能力。", "zh-TW": "Qwen QwQ 是一個實驗性研究模型，專注於提升推理能力。", "ja-JP": "Qwen QwQ は、推論能力の向上に焦点を当てた実験的研究モデルです。", "ru-RU": "Qwen QwQ — это экспериментальная исследовательская модель, направленная на улучшение логического мышления." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "QwQ 32B Preview" } ] }, { "slug": "alibaba/qwq-plus", "model_name": "qwq-plus", "display_name": "QwQ Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba", "official": true, "source": "models-dev+litellm+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "2.4" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.23" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.574" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.6", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Qwen reasoning model for deliberate problem solving, math, and coding", "released_at": "2025-03-05", "knowledge_cutoff": "2024-04", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "qwen", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "stream": true, "web_search": true }, "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models", "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "qwq-plus-2025-03-05" ], "intro_i18n": { "zh-CN": "QwQ 推理模型基于 Qwen2.5 训练，并通过强化学习大幅提升推理能力。在数学/代码（AIME 24/25、LiveCodeBench）及通用评测（IFEval、LiveBench）中达到 DeepSeek-R1 的水平。", "zh-TW": "QwQ 推理模型基於 Qwen2.5 訓練，透過強化學習大幅提升推理能力。在數學/程式碼（AIME 24/25、LiveCodeBench）與部分通用基準（IFEval、LiveBench）上達到 DeepSeek-R1 的水準。", "ja-JP": "Qwen2.5を基盤としたQwQ推論モデルは、強化学習により推論能力を大幅に向上させています。数学やコード（AIME 24/25、LiveCodeBench）および一般ベンチマーク（IFEval、LiveBench）において、DeepSeek-R1と同等の性能を達成しています。", "ru-RU": "Модель логического вывода QwQ, обученная на основе Qwen2.5 с использованием RL, значительно улучшает логический анализ. Основные метрики в математике/коде (AIME 24/25, LiveCodeBench) и на общих бенчмарках (IFEval, LiveBench) достигают уровня DeepSeek-R1." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-13", "kind": "capability", "note": "prompt_caching: true→false" }, { "date": "2026-07-13", "kind": "capability", "note": "structured_output: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "alibaba/tongyi-intent-detect-v3", "model_name": "tongyi-intent-detect-v3", "display_name": "Tongyi Intent Detect V3", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "provider_name": "Alibaba (China)", "official": true, "source": "llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.058" }, "completion": { "unit": "per_M_tokens", "price": "0.144" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "verification_status": "aggregator_only" } } ], "released_at": "2024-01", "knowledge_cutoff": "2024-04", "max_input_tokens": 8192, "max_output_tokens": 1024, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "yi", "capabilities": {}, "intro": "General-purpose chat model for instruction following, writing, and analysis", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Tongyi Intent Detect V3" } ] }, { "slug": "alibaba/wan2.2-i2v-flash", "model_name": "wan2.2-i2v-flash", "display_name": "Wan2.2 I2V Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.029412" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-08-11", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.2极速版提供超快速生成，具有更准确的提示理解和摄像机控制能力。保持视觉元素的一致性，同时显著提升整体稳定性和成功率。", "zh-TW": "萬象2.2速度版提供超高速生成，具備更精確的提示理解及相機控制。保持視覺元素的一致性，同時顯著提升整體穩定性及成功率。", "ja-JP": "Wanxiang 2.2スピードエディションは、超高速生成を提供し、プロンプトの理解とカメラ制御がより正確になりました。視覚要素の一貫性を維持しながら、全体的な安定性と成功率を大幅に向上させます。", "ru-RU": "Wanxiang 2.2 Speed Edition обеспечивает ультрабыструю генерацию, с более точным пониманием подсказок и управлением камерой. Она поддерживает согласованность визуальных элементов, значительно улучшая общую стабильность и успешность." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.2 I2V Flash" } ] }, { "slug": "alibaba/wan2.2-i2v-plus", "model_name": "wan2.2-i2v-plus", "display_name": "Wan2.2 I2V Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.102941" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-07-28", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.2专业版提供更准确的提示理解和可控的摄像机运动。保持视觉元素的一致性，同时显著提升稳定性和成功率，生成更丰富、更详细的内容。", "zh-TW": "萬象2.2專業版提供更精確的提示理解及可控的相機運動。保持視覺元素的一致性，同時顯著提升穩定性及成功率，並生成更豐富、更詳細的內容。", "ja-JP": "Wanxiang 2.2プロエディションは、プロンプトの理解がより正確になり、制御可能なカメラ動作を提供します。視覚要素の一貫性を維持しながら、安定性と成功率を大幅に向上させ、より豊かで詳細なコンテンツを生成します。", "ru-RU": "Wanxiang 2.2 Pro Edition предлагает более точное понимание подсказок и управляемые движения камеры. Она поддерживает согласованность визуальных элементов, значительно улучшая стабильность и успешность, и генерирует более богатый и детализированный контент." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.2 I2V Plus" } ] }, { "slug": "alibaba/wan2.2-kf2v-flash", "model_name": "wan2.2-kf2v-flash", "display_name": "Wan2.2 KF2V Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.029412" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-09-12", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.2极速版", "zh-TW": "萬象2.2速度版", "ja-JP": "Wanxiang 2.2スピードエディション", "ru-RU": "Wanxiang 2.2 Speed Edition" }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.2 KF2V Flash" } ] }, { "slug": "alibaba/wan2.2-kf2v-plus", "model_name": "wan2.2-kf2v-plus", "display_name": "Wan2.2 KF2V Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.102941" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-09-12", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.2专业版", "zh-TW": "萬象2.2專業版", "ja-JP": "Wanxiang 2.2プラスエディション", "ru-RU": "Wanxiang 2.2 Plus Edition" }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.2 KF2V Plus" } ] }, { "slug": "alibaba/wan2.2-t2i-flash", "model_name": "wan2.2-t2i-flash", "display_name": "Wanxiang2.2 T2I Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.020588" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-07-28", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.2 Flash是最新模型，在创造力、稳定性和真实感方面进行了升级，提供快速生成和高价值。", "zh-TW": "萬象 2.2 Flash 是最新模型，在創意、穩定性和真實感方面進行了升級，提供快速生成和高價值。", "ja-JP": "Wanxiang 2.2 Flashは、創造性、安定性、リアリズムの向上を伴う最新モデルで、高速生成と高い価値を提供します。", "ru-RU": "Wanxiang 2.2 Flash — это последняя модель с улучшениями в креативности, стабильности и реалистичности, обеспечивающая быструю генерацию и высокую ценность." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.2 T2I Flash" } ] }, { "slug": "alibaba/wan2.2-t2i-plus", "model_name": "wan2.2-t2i-plus", "display_name": "Wanxiang2.2 T2I Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.029412" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-07-28", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.2 Plus是最新模型，在创造力、稳定性和真实感方面进行了升级，生成更丰富的细节。", "zh-TW": "萬象 2.2 Plus 是最新模型，在創意、穩定性和真實感方面進行了升級，生成更豐富的細節。", "ja-JP": "Wanxiang 2.2 Plusは、創造性、安定性、リアリズムの向上を伴う最新モデルで、より豊かな詳細を生成します。", "ru-RU": "Wanxiang 2.2 Plus — это последняя модель с улучшениями в креативности, стабильности и реалистичности, создающая более богатые детали." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.2 T2I Plus" } ] }, { "slug": "alibaba/wan2.2-t2v-plus", "model_name": "wan2.2-t2v-plus", "display_name": "Wan2.2 T2V Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.102941" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-07-28", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.2专业版提供更准确的提示理解，生成稳定流畅的动作，并生成更丰富、更详细的视觉效果。", "zh-TW": "萬象2.2專業版提供更精確的提示理解，生成穩定且流暢的動作影像，並產生更豐富、更詳細的視覺效果。", "ja-JP": "Wanxiang 2.2プロエディションは、プロンプトの理解がより正確になり、安定した滑らかな動きの生成を提供し、より豊かで詳細なビジュアルを生成します。", "ru-RU": "Wanxiang 2.2 Pro Edition обеспечивает более точное понимание подсказок, стабильную и плавную генерацию движений, а также создает более богатые и детализированные визуальные эффекты." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.2 T2V Plus" } ] }, { "slug": "alibaba/wan2.5-i2i-preview", "model_name": "wan2.5-i2i-preview", "display_name": "Wanxiang2.5 I2I Preview", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.029412" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-09-23", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.5 I2I Preview支持单图编辑和多图融合。", "zh-TW": "萬象 2.5 I2I Preview 支持單圖編輯和多圖融合。", "ja-JP": "Wanxiang 2.5 I2I Previewは、単一画像編集と複数画像の融合をサポートします。", "ru-RU": "Wanxiang 2.5 I2I Preview поддерживает редактирование одного изображения и слияние нескольких изображений." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.5 I2I Preview" } ] }, { "slug": "alibaba/wan2.5-i2v-preview", "model_name": "wan2.5-i2v-preview", "display_name": "Wan2.5 I2V Preview", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.147059" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-09-23", "model_type": "video_generation", "capabilities": { "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.5预览版支持自动配音生成以及自定义音频文件的嵌入。", "zh-TW": "萬象2.5預覽版支持自動配音生成及整合自定義音頻文件。", "ja-JP": "Wanxiang 2.5プレビューは、自動音声生成とカスタムオーディオファイルの組み込みをサポートします。", "ru-RU": "Wanxiang 2.5 Preview поддерживает автоматическую генерацию озвучки и возможность добавления пользовательских аудиофайлов." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Wan2.5 I2V Preview" } ] }, { "slug": "alibaba/wan2.5-t2i-preview", "model_name": "wan2.5-t2i-preview", "display_name": "Wanxiang2.5 T2I Preview", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.029412" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-09-23", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.5 T2I支持在总像素面积和纵横比限制内灵活选择图像尺寸。", "zh-TW": "萬象 2.5 T2I 支持在總像素面積和長寬比限制內靈活選擇圖像尺寸。", "ja-JP": "Wanxiang 2.5 T2Iは、総ピクセルエリアとアスペクト比の制約内で画像寸法の柔軟な選択をサポートします。", "ru-RU": "Wanxiang 2.5 T2I поддерживает гибкий выбор размеров изображения в пределах общей площади пикселей и ограничений соотношения сторон." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.5 T2I Preview" } ] }, { "slug": "alibaba/wan2.5-t2v-preview", "model_name": "wan2.5-t2v-preview", "display_name": "Wan2.5 T2V Preview", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.147059" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-09-23", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.5预览版支持自动配音生成以及自定义音频文件的嵌入。", "zh-TW": "萬象2.5預覽版支持自動配音生成及整合自定義音頻文件。", "ja-JP": "Wanxiang 2.5プレビューは、自動音声生成とカスタムオーディオファイルの組み込みをサポートします。", "ru-RU": "Wanxiang 2.5 Preview поддерживает автоматическую генерацию озвучки и возможность добавления пользовательских аудиофайлов." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.5 T2V Preview" } ] }, { "slug": "alibaba/wan2.6-i2v", "model_name": "wan2.6-i2v", "display_name": "Wan2.6 I2V", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.147059" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-12-16", "model_type": "video_generation", "capabilities": { "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.6引入多镜头叙事能力，同时支持自动配音生成以及自定义音频文件的嵌入。", "zh-TW": "萬象2.6引入多鏡頭敘事能力，同時支持自動配音生成及整合自定義音頻文件。", "ja-JP": "Wanxiang 2.6は、マルチショットの物語能力を導入し、自動音声生成とカスタムオーディオファイルの組み込みもサポートします。", "ru-RU": "Wanxiang 2.6 вводит возможности многокадрового повествования, а также поддерживает автоматическую генерацию озвучки и возможность добавления пользовательских аудиофайлов." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Wan2.6 I2V" } ] }, { "slug": "alibaba/wan2.6-i2v-flash", "model_name": "wan2.6-i2v-flash", "display_name": "Wan2.6 I2V Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.073529" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-01-17", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.6引入多镜头叙事能力，同时支持自动配音生成以及自定义音频文件的嵌入。", "zh-TW": "萬象2.6引入多鏡頭敘事能力，同時支持自動配音生成及整合自定義音頻文件。", "ja-JP": "Wanxiang 2.6は、マルチショットの物語能力を導入し、自動音声生成とカスタムオーディオファイルの組み込みもサポートします。", "ru-RU": "Wanxiang 2.6 вводит возможности многокадрового повествования, а также поддерживает автоматическую генерацию озвучки и возможность добавления пользовательских аудиофайлов." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.6 I2V Flash" } ] }, { "slug": "alibaba/Wan2.6-image", "model_name": "Wan2.6-image", "display_name": "Wanxiang2.6 Image", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.029412" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "wan2.6-image" } ], "released_at": "2025-07-28", "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Wan-AI/Wan2.6-image", "wan2.6-image" ], "intro_i18n": { "zh-CN": "万象2.6 Image支持图像编辑和混合图像-文本布局输出。", "zh-TW": "萬象 2.6 Image 支持圖像編輯和混合圖文佈局輸出。", "ja-JP": "Wanxiang 2.6 Imageは、画像編集と画像とテキストの混合レイアウト出力をサポートします。", "ru-RU": "Wanxiang 2.6 Image поддерживает редактирование изображений и смешанный вывод макета изображений и текста." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.6 Image" } ] }, { "slug": "alibaba/wan2.6-r2v", "model_name": "wan2.6-r2v", "display_name": "Wan2.6 R2V", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.073529" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-12-16", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.6参考转视频支持参考特定角色或任何物体，准确保持外观和声音的一致性，并支持多角色参考协同表演。注意：使用视频作为参考时，输入视频也将计入成本。请参阅模型定价文档了解详情。", "zh-TW": "萬象2.6參考生成影像支持參考特定角色或任意物件，精確保持外觀及聲音的一致性，並支持多角色參考共同表演。注意：使用影像作為參考時，輸入影像也將計入成本。請參閱模型定價文檔了解詳情。", "ja-JP": "Wanxiang 2.6参照からビデオは、特定のキャラクターやオブジェクトを参照し、外観と声の一貫性を正確に維持し、複数キャラクターの参照による共演を可能にします。注：ビデオを参照として使用する場合、入力ビデオもコストに含まれます。モデルの価格設定ドキュメントを参照してください。", "ru-RU": "Wanxiang 2.6 Reference-to-Video поддерживает ссылки на конкретных персонажей или любые объекты, точно сохраняя согласованность внешнего вида и голоса, а также позволяет использовать ссылки на нескольких персонажей для совместного исполнения. Примечание: при использовании видео в качестве ссылок входное видео также будет учитываться в стоимости. Пожалуйста, ознакомьтесь с документацией по ценообразованию модели для получения подробной информации." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.6 R2V" } ] }, { "slug": "alibaba/wan2.6-r2v-flash", "model_name": "wan2.6-r2v-flash", "display_name": "Wan2.6 R2V Flash", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.147059" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-12-16", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.6参考转视频极速版提供更快的生成速度和更高的性价比。支持参考特定角色或任何物体，准确保持外观和声音的一致性，并支持多角色参考协同表演。", "zh-TW": "萬象2.6參考生成影像——速度版提供更快的生成速度及更高的性價比。支持參考特定角色或任意物件，精確保持外觀及聲音的一致性，並支持多角色參考共同表演。", "ja-JP": "Wanxiang 2.6参照からビデオ – Flashは、より高速な生成と優れたコストパフォーマンスを提供します。特定のキャラクターやオブジェクトを参照し、外観と声の一貫性を正確に維持し、複数キャラクターの参照による共演を可能にします。", "ru-RU": "Wanxiang 2.6 Reference-to-Video – Flash предлагает более быструю генерацию и лучшую стоимость. Она поддерживает ссылки на конкретных персонажей или любые объекты, точно сохраняя согласованность внешнего вида и голоса, а также позволяет использовать ссылки на нескольких персонажей для совместного исполнения." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.6 R2V Flash" } ] }, { "slug": "alibaba/Wan2.6-T2I", "model_name": "Wan2.6-T2I", "display_name": "Wanxiang2.6 T2I", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.029412" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "wan2.6-t2i" } ], "released_at": "2025-12-16", "model_type": "image_generation", "capabilities": { "image_output": true }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Wan-AI/Wan2.6-T2I", "wan2.6-t2i" ], "intro_i18n": { "zh-CN": "万象2.6 T2I支持在总像素面积和纵横比限制内灵活选择图像尺寸（与万象2.5相同）。", "zh-TW": "萬象 2.6 T2I 支持在總像素面積和長寬比限制內靈活選擇圖像尺寸（與萬象 2.5 相同）。", "ja-JP": "Wanxiang 2.6 T2Iは、総ピクセルエリアとアスペクト比の制約内で画像寸法の柔軟な選択をサポートします（Wanxiang 2.5と同様）。", "ru-RU": "Wanxiang 2.6 T2I поддерживает гибкий выбор размеров изображения в пределах общей площади пикселей и ограничений соотношения сторон (аналогично Wanxiang 2.5)." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.6 T2I" } ] }, { "slug": "alibaba/Wan2.6-T2V", "model_name": "Wan2.6-T2V", "display_name": "Wan2.6 T2V", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.147059" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "wan2.6-t2v" } ], "released_at": "2025-12-16", "model_type": "video_generation", "capabilities": { "audio_input": true }, "modalities": { "input": [ "text", "audio" ], "output": [ "video" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Wan-AI/Wan2.6-T2V", "wan2.6-t2v" ], "intro_i18n": { "zh-CN": "万象2.6引入多镜头叙事能力，同时支持自动配音生成以及自定义音频文件的嵌入。", "zh-TW": "萬象2.6引入多鏡頭敘事能力，同時支持自動配音生成及整合自定義音頻文件。", "ja-JP": "Wanxiang 2.6は、マルチショットの物語能力を導入し、自動音声生成とカスタムオーディオファイルの組み込みもサポートします。", "ru-RU": "Wanxiang 2.6 вводит возможности многокадрового повествования, а также поддерживает автоматическую генерацию озвучки и возможность добавления пользовательских аудиофайлов." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.6 T2V" } ] }, { "slug": "alibaba/wan2.7-i2v-2026-04-25", "model_name": "wan2.7-i2v-2026-04-25", "display_name": "Wan2.7 I2V", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.147059" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "wan2.7-i2v" } ], "released_at": "2026-04-03", "model_type": "video_generation", "capabilities": { "vision": true, "audio_input": true, "video_input": true }, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "video" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Wan-AI/wan2.7-i2v", "wan2.7-i2v" ], "intro_i18n": { "zh-CN": "万象 2.7 图生视频在表现力全面升级。剧情场景中情绪细腻自然，动作场景紧凑有力。结合更具动感与节奏感的镜头切换，整体性能与叙事能力大幅增强。", "zh-TW": "萬象 2.7 圖生影在性能上全面升級。戲劇場景情感細緻自然，動作場景張力十足，並結合更具節奏感與動態性的鏡頭轉換，呈現更強的整體表現力與故事敘事能力。", "ja-JP": "Wanxiang 2.7 Image-to-Videoは、性能能力において包括的なアップグレードを提供します。ドラマチックなシーンでは繊細で自然な感情表現を特徴とし、アクションシーンでは激しくインパクトのある演出を実現します。より動的でリズムに基づいたショットの切り替えを組み合わせることで、全体的な性能とストーリーテリングを強化します。", "ru-RU": "Wanxiang 2.7 Image-to-Video получила комплексное обновление возможностей. Драматические сцены демонстрируют естественную эмоциональную выразительность, а экшен-сцены — динамичность и силу. В сочетании с более выразительными и ритмичными переходами модель обеспечивает улучшенное повествование и визуальный эффект." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.7 I2V" } ] }, { "slug": "alibaba/wan2.7-image", "model_name": "wan2.7-image", "display_name": "Wanxiang2.7 Image", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.029412" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-04-01", "model_type": "image_generation", "capabilities": { "image_output": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "max_input_tokens": 8192, "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.7图像，图像生成速度更快。", "zh-TW": "萬象2.7影像，影像生成速度更快。", "ja-JP": "Wanxiang 2.7画像は、より高速な画像生成速度を提供します。", "ru-RU": "Wanxiang 2.7 Image обеспечивает более быструю скорость генерации изображений." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.7 Image" } ] }, { "slug": "alibaba/wan2.7-image-pro", "model_name": "wan2.7-image-pro", "display_name": "Wanxiang2.7 Image Pro", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.073529" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-04-01", "model_type": "image_generation", "capabilities": { "image_output": true, "prompt_caching": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "max_input_tokens": 8192, "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.7图像专业版，支持4K高清输出。", "zh-TW": "萬象2.7影像專業版，支持4K高清輸出。", "ja-JP": "Wanxiang 2.7画像プロフェッショナルエディションは、4K高解像度出力をサポートします。", "ru-RU": "Wanxiang 2.7 Image Professional Edition поддерживает вывод в 4K высоком разрешении." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.7 Image Pro" } ] }, { "slug": "alibaba/wan2.7-r2v", "model_name": "wan2.7-r2v", "display_name": "Wan2.7 R2V", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.147059" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-04-03", "model_type": "video_generation", "capabilities": { "vision": true, "video_input": true }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Wan-AI/wan2.7-r2v" ], "intro_i18n": { "zh-CN": "万象2.7参考转视频为角色、道具和场景提供更稳定的参考。支持最多5张混合参考图像或视频，以及音频音调参考。结合升级的核心能力，提供更强的表现力和表达能力。", "zh-TW": "萬象2.7參考生成影像提供更穩定的角色、道具及場景參考。支持最多5張混合參考影像或影像，以及音頻音調參考。結合升級的核心能力，提供更強的性能及表現力。", "ja-JP": "Wanxiang 2.7参照からビデオは、キャラクター、小道具、シーンのより安定した参照を提供します。最大5つの混合参照画像またはビデオをサポートし、オーディオトーンの参照も可能です。アップグレードされたコア能力と組み合わせることで、より強力なパフォーマンスと表現力を提供します。", "ru-RU": "Wanxiang 2.7 Reference-to-Video предлагает более стабильные ссылки для персонажей, реквизита и сцен. Поддерживает до 5 смешанных эталонных изображений или видео, а также ссылки на аудиотон. В сочетании с обновленными основными возможностями обеспечивает более сильную производительность и выразительность." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.7 R2V" } ] }, { "slug": "alibaba/wan2.7-t2v-2026-04-25", "model_name": "wan2.7-t2v-2026-04-25", "display_name": "Wan2.7 T2V", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.147059" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "wan2.7-t2v" } ], "released_at": "2026-04-03", "model_type": "video_generation", "capabilities": { "audio_input": true }, "modalities": { "input": [ "text", "audio" ], "output": [ "video" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Wan-AI/wan2.7-t2v", "wan2.7-t2v" ], "intro_i18n": { "zh-CN": "万象 2.7 文生视频在表现力全面升级。剧情场景中情绪细腻自然，动作场景紧凑有力。结合更具节奏的镜头切换，在演绎与叙事方面表现更为出色。", "zh-TW": "萬象 2.7 文生影在性能上全面升級。戲劇場景情感細緻自然，動作場景張力十足，並強化鏡頭節奏與動態切換，讓表演與敘事能力更上層樓。", "ja-JP": "Wanxiang 2.7 Text-to-Videoは、性能能力において包括的なアップグレードを提供します。ドラマチックなシーンでは繊細で自然な感情表現を特徴とし、アクションシーンでは激しくインパクトのある演出を実現します。より動的でリズムに基づいたショットの切り替えを組み合わせることで、全体的な演技とストーリーテリング性能を強化します。", "ru-RU": "Wanxiang 2.7 Text-to-Video получила комплексное обновление возможностей. Драматические сцены стали более эмоционально выразительными, а динамичные эпизоды — более впечатляющими. Улучшенные ритмичные переходы создают более сильный общий эффект и выразительность повествования." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wan2.7 T2V" } ] }, { "slug": "alibaba/wanx-v1", "model_name": "wanx-v1", "display_name": "Wanxiang v1", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.023529" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2024-05-22", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "基础文本转图像模型。对应通义万象 1.0 通用版。", "zh-TW": "基礎文字轉圖像模型。對應通義萬象 1.0 通用版。", "ja-JP": "基本的なテキストから画像への変換モデル。Tongyi Wanxiang 1.0 Generalに対応。", "ru-RU": "Базовая модель преобразования текста в изображение. Соответствует Tongyi Wanxiang 1.0 General." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang v1" } ] }, { "slug": "alibaba/wanx2.0-t2i-turbo", "model_name": "wanx2.0-t2i-turbo", "display_name": "Wanxiang2.0 T2I Turbo", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.005882" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-01-17", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "擅长纹理人像，速度适中，成本较低。对应通义万象 2.0 极速版。", "zh-TW": "擅長紋理人像，速度適中、成本較低。對應通義萬象 2.0 Speed。", "ja-JP": "中程度の速度と低コストで質感のあるポートレートに優れています。Tongyi Wanxiang 2.0 Speedに対応。", "ru-RU": "Отличается текстурированными портретами при умеренной скорости и низкой стоимости. Соответствует Tongyi Wanxiang 2.0 Speed." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.0 T2I Turbo" } ] }, { "slug": "alibaba/wanx2.1-i2v-plus", "model_name": "wanx2.1-i2v-plus", "display_name": "Wanxiang2.1 I2V Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.102941" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-01-17", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.1专业版提供更精致的视觉效果和更高质量的图像。", "zh-TW": "萬象2.1專業版提供更精緻且高質量的影像。", "ja-JP": "Wanxiang 2.1プロエディションは、より視覚的に洗練され、高品質な画像を提供します。", "ru-RU": "Wanxiang 2.1 Pro Edition обеспечивает более утонченное визуальное оформление и изображения более высокого качества." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.1 I2V Plus" } ] }, { "slug": "alibaba/wanx2.1-i2v-turbo", "model_name": "wanx2.1-i2v-turbo", "display_name": "Wanxiang2.1 I2V Turbo", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.035294" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-02-25", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.1极速版提供高性价比。", "zh-TW": "萬象2.1速度版提供高性價比。", "ja-JP": "Wanxiang 2.1スピードエディションは、高いコストパフォーマンスを提供します。", "ru-RU": "Wanxiang 2.1 Speed Edition предлагает высокую стоимость." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.1 I2V Turbo" } ] }, { "slug": "alibaba/wanx2.1-t2i-plus", "model_name": "wanx2.1-t2i-plus", "display_name": "Wanxiang2.1 T2I Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.029412" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-01-08", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "全面升级版本，图像细节更丰富，生成速度略慢。对应通义万象 2.1 专业版。", "zh-TW": "全面升級版本，圖像細節更豐富，速度略慢。對應通義萬象 2.1 Pro。", "ja-JP": "画像のディテールがより豊かになった完全アップグレード版で、やや速度は遅めです。Tongyi Wanxiang 2.1 Proに対応。", "ru-RU": "Полностью обновленная версия с более богатыми деталями изображения и немного меньшей скоростью. Соответствует Tongyi Wanxiang 2.1 Pro." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.1 T2I Plus" } ] }, { "slug": "alibaba/wanx2.1-t2i-turbo", "model_name": "wanx2.1-t2i-turbo", "display_name": "Wanxiang2.1 T2I Turbo", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.020588" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-01-08", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "全面升级版本，生成速度快，整体质量强，性价比高。对应通义万象 2.1 极速版。", "zh-TW": "全面升級版本，生成快速、整體品質強、性價比高。對應通義萬象 2.1 Speed。", "ja-JP": "高速生成、全体的な品質の高さ、高いコストパフォーマンスを備えた完全アップグレード版です。Tongyi Wanxiang 2.1 Speedに対応。", "ru-RU": "Полностью обновленная версия с быстрой генерацией, высоким общим качеством и отличной ценностью. Соответствует Tongyi Wanxiang 2.1 Speed." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.1 T2I Turbo" } ] }, { "slug": "alibaba/wanx2.1-t2v-plus", "model_name": "wanx2.1-t2v-plus", "display_name": "Wanxiang2.1 T2V Plus", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.102941" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-01-08", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.1专业版提供更丰富的视觉纹理和更高质量的图像。", "zh-TW": "萬象2.1專業版提供更豐富的視覺紋理及更高質量的影像。", "ja-JP": "Wanxiang 2.1プロエディションは、より豊かな視覚的テクスチャと高品質な画像を提供します。", "ru-RU": "Wanxiang 2.1 Pro Edition обеспечивает более богатую визуальную текстуру и изображения более высокого качества." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.1 T2V Plus" } ] }, { "slug": "alibaba/wanx2.1-t2v-turbo", "model_name": "wanx2.1-t2v-turbo", "display_name": "Wanxiang2.1 T2V Turbo", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_second", "price": "0.035294" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-01-08", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "万象2.1极速版提供卓越的性价比。", "zh-TW": "萬象2.1速度版提供卓越的性價比。", "ja-JP": "Wanxiang 2.1スピードエディションは、優れたコストパフォーマンスを提供します。", "ru-RU": "Wanxiang 2.1 Speed Edition предлагает отличное соотношение цены и качества." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Wanxiang2.1 T2V Turbo" } ] }, { "slug": "alibaba/z-image-turbo", "model_name": "z-image-turbo", "display_name": "Z-Image Turbo", "vendor": "alibaba", "pricing": [ { "provider": "alibaba", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.014706" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-12-19", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Z-Image是一个轻量级文本生成图像模型，能够快速生成图像，支持中英文文本渲染，并灵活适应多种分辨率和纵横比。", "zh-TW": "Z-Image 是一款輕量級文本生成圖像模型，能快速生成圖像，支持中英文文本渲染，並靈活適應多種分辨率和長寬比。", "ja-JP": "Z-Imageは軽量なテキストから画像生成モデルで、迅速に画像を生成し、中国語と英語のテキストレンダリングをサポートし、複数の解像度とアスペクト比に柔軟に適応します。", "ru-RU": "Z-Image — это легковесная модель генерации изображений из текста, которая может быстро создавать изображения, поддерживает рендеринг текста на китайском и английском языках, а также гибко адаптируется к различным разрешениям и соотношениям сторон." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Z-Image Turbo" } ] }, { "slug": "amazon/amazon-nova-lite", "model_name": "amazon-nova-lite", "display_name": "Amazon Nova Lite", "vendor": "amazon", "pricing": [ { "provider": "amazon", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Amazon Nova Lite" } ] }, { "slug": "amazon/amazon-nova-micro", "model_name": "amazon-nova-micro", "display_name": "Amazon Nova Micro", "vendor": "amazon", "pricing": [ { "provider": "amazon", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Amazon Nova Micro" } ] }, { "slug": "amazon/amazon-nova-premier", "model_name": "amazon-nova-premier", "display_name": "Amazon Nova Premier", "vendor": "amazon", "pricing": [ { "provider": "amazon", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "12.5" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Amazon Nova Premier" } ] }, { "slug": "amazon/amazon-nova-pro", "model_name": "amazon-nova-pro", "display_name": "Amazon Nova Pro", "vendor": "amazon", "pricing": [ { "provider": "amazon", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Amazon Nova Pro" } ] }, { "slug": "amazon/amazon.nova-2-multimodal-embeddings-v1:0", "model_name": "amazon.nova-2-multimodal-embeddings-v1:0", "display_name": "amazon.nova-2-multimodal-embeddings-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.135" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_input": { "unit": "per_image", "price": "0.00006" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm" }, "verification_status": "aggregator_only" } }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.0006" }, "audio_input": { "unit": "per_second", "price": "0.00014" }, "prompt": { "unit": "per_M_tokens", "price": "0.135" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" } ], "docs_url": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/model-catalog/serverless/amazon.nova-2-multimodal-embeddings-v1:0", "max_input_tokens": 8172, "model_type": "multimodal_embedding", "capabilities": { "vision": true, "audio_input": true, "video_input": true }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "embedding" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" } ] }, { "slug": "amazon/amazon.nova-2-sonic-v1:0", "model_name": "amazon.nova-2-sonic-v1:0", "display_name": "amazon.nova-2-sonic-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.33" }, "completion": { "unit": "per_M_tokens", "price": "2.75" }, "audio_input": { "unit": "per_M_tokens", "price": "3" }, "audio_output": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "audio_input": "pydantic-prices", "audio_output": "pydantic-prices" }, "verification_status": "aggregator_only" } }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "3.63" }, "prompt": { "unit": "per_M_tokens", "price": "0.396" }, "audio_output": { "unit": "per_M_tokens", "price": "14.52" }, "completion": { "unit": "per_M_tokens", "price": "3.311" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-northeast-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "2.91" }, "prompt": { "unit": "per_M_tokens", "price": "0.363" }, "audio_output": { "unit": "per_M_tokens", "price": "11.65" }, "completion": { "unit": "per_M_tokens", "price": "2.92" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-north-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "3" }, "prompt": { "unit": "per_M_tokens", "price": "0.33" }, "audio_output": { "unit": "per_M_tokens", "price": "12" }, "completion": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "3" }, "prompt": { "unit": "per_M_tokens", "price": "0.319" }, "audio_output": { "unit": "per_M_tokens", "price": "12" }, "completion": { "unit": "per_M_tokens", "price": "2.651" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "capabilities": { "function_calling": true, "audio_input": true, "audio_output": true }, "max_input_tokens": 1000000, "max_output_tokens": 65536, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ] }, "model_type": "realtime_omni", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "amazon.nova-2-sonic-v1:0" } ] }, { "slug": "amazon/amazon.nova-reel-v1:1", "model_name": "amazon.nova-reel-v1:1", "display_name": "amazon.nova-reel-v1:1", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.08" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-reel-v1:0" } ], "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "model_type": "video_generation", "capabilities": { "vision": true, "video_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon.nova-reel-v1:0" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "amazon.nova-reel-v1:1" } ] }, { "slug": "amazon/amazon.nova-sonic-v1:0", "model_name": "amazon.nova-sonic-v1:0", "display_name": "amazon.nova-sonic-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "audio_input": { "unit": "per_M_tokens", "price": "3.4" }, "audio_output": { "unit": "per_M_tokens", "price": "13.6" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "audio_input": "pydantic-prices", "audio_output": "pydantic-prices" }, "verification_status": "aggregator_only" } }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "3.7" }, "prompt": { "unit": "per_M_tokens", "price": "0.072" }, "audio_output": { "unit": "per_M_tokens", "price": "14.7" }, "completion": { "unit": "per_M_tokens", "price": "0.288" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-northeast-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "4.1" }, "prompt": { "unit": "per_M_tokens", "price": "0.065" }, "audio_output": { "unit": "per_M_tokens", "price": "16.3" }, "completion": { "unit": "per_M_tokens", "price": "0.26" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-north-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "3.4" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "audio_output": { "unit": "per_M_tokens", "price": "13.6" }, "completion": { "unit": "per_M_tokens", "price": "0.24" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" } ], "capabilities": { "function_calling": true }, "max_input_tokens": 300000, "modalities": { "input": [], "output": [ "text" ] }, "model_type": "realtime_omni", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "amazon.nova-sonic-v1:0" } ] }, { "slug": "amazon/amazon.rerank-v1:0", "model_name": "amazon.rerank-v1:0", "display_name": "amazon.rerank-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1000" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_request", "price": "0.001" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-northeast-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_request", "price": "0.001" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ca-central-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_request", "price": "0.001" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-central-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_request", "price": "0.001" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_rerank", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "amazon.rerank-v1:0" } ] }, { "slug": "amazon/amazon.titan-embed-g1-text-02", "model_name": "amazon.titan-embed-g1-text-02", "display_name": "amazon.titan-embed-g1-text-02", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.02" }, "message": "prompt from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "max_input_tokens": 8192, "model_type": "text_embedding", "capabilities": {}, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "amazon/amazon.titan-embed-image-v1", "model_name": "amazon.titan-embed-image-v1", "display_name": "amazon.titan-embed-image-v1", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_input": { "unit": "per_image", "price": "0.00006" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "cache_write": { "unit": "per_M_tokens", "price": "6.25" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "25" }, "message": "completion from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "3.125", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00007" }, "prompt": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "ap-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00008" }, "prompt": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "ap-southeast-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.0001" }, "prompt": { "unit": "per_M_tokens", "price": "0.9" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "ca-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.0001" }, "prompt": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "eu-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00007" }, "prompt": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "eu-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.0001" }, "prompt": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "eu-west-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00008" }, "prompt": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "eu-west-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.0001" }, "prompt": { "unit": "per_M_tokens", "price": "1.2" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "sa-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00006" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00006" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/providers?model=amazon.titan-image-generator-v1", "max_input_tokens": 128, "model_type": "multimodal_embedding", "capabilities": { "vision": true }, "modalities": { "input": [ "text", "image" ], "output": [ "embedding" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" } ] }, { "slug": "amazon/amazon.titan-embed-text-v1", "model_name": "amazon.titan-embed-text-v1", "display_name": "amazon.titan-embed-text-v1", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm+pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-northeast-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-south-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-central-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "max_input_tokens": 8192, "model_type": "text_embedding", "capabilities": {}, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "amazon/amazon.titan-embed-text-v2:0", "model_name": "amazon.titan-embed-text-v2:0", "display_name": "amazon.titan-embed-text-v2:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.02" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.02" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.02" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from litellm conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.029" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "ap-northeast-1", "tracks": [ { "label": "Batch", "factor": "0.417241", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.02459" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "ap-northeast-2", "tracks": [ { "label": "Batch", "factor": "0.500203", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.027" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-northeast-3" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.024" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-south-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.027" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-south-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.028" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-southeast-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.026" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-southeast-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "ca-central-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "eu-central-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.027" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-central-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.021" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "eu-north-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.023" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "eu-south-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.021" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "eu-south-2", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.026" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "eu-west-2", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-3" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "sa-east-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.02" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.02" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-gov-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.11" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-gov-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.024" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.02" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west-2", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 8192, "model_type": "text_embedding", "capabilities": {}, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "amazon/amazon.titan-image-generator-v1", "model_name": "amazon.titan-image-generator-v1", "display_name": "amazon.titan-image-generator-v1", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm", "charges": { "image_output": { "unit": "per_image", "price": "0.008" }, "image_input": { "unit": "per_image", "price": "0" } }, "provenance": { "base_charges": { "image_output": "litellm", "image_input": "litellm" }, "verification_status": "aggregator_only" } }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.01" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-south-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.0107" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ca-central-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.013" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.0101" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.018" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "sa-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "amazon/amazon.titan-image-generator-v2", "model_name": "amazon.titan-image-generator-v2", "display_name": "amazon.titan-image-generator-v2", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm", "charges": { "image_output": { "unit": "per_image", "price": "0.008" }, "image_input": { "unit": "per_image", "price": "0" } }, "provenance": { "base_charges": { "image_output": "litellm", "image_input": "litellm" }, "verification_status": "aggregator_only" } } ], "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "amazon/amazon.titan-image-generator-v2:0", "model_name": "amazon.titan-image-generator-v2:0", "display_name": "amazon.titan-image-generator-v2:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm", "charges": { "image_output": { "unit": "per_image", "price": "0.008" }, "image_input": { "unit": "per_image", "price": "0" } }, "provenance": { "base_charges": { "image_output": "litellm", "image_input": "litellm" }, "verification_status": "aggregator_only" } }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.012" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.012" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "amazon/amazon.titan-text-express-v1", "model_name": "amazon.titan-text-express-v1", "display_name": "amazon.titan-text-express-v1", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "litellm+pydantic-prices+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.3" }, "completion": { "unit": "per_M_tokens", "price": "1.7" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from pydantic-prices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.6" }, "message": "completion from pydantic-prices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.6" }, "message": "completion from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.6" }, "message": "completion from llmdb conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.076923", "completion": "0.176471" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.275" }, "completion": { "unit": "per_M_tokens", "price": "0.825" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-northeast-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "1.9" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-south-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.788" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-southeast-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.8" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ca-central-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.863" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-central-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "1.7" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.9" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.788" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-3" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "1.1" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "sa-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-gov-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "max_input_tokens": 42000, "max_output_tokens": 8000, "model_type": "text_generation", "capabilities": { "function_calling": true, "stream": true }, "released_at": "2024-12-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "titan", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "amazon/amazon.titan-text-express-v1:0:8k", "model_name": "amazon.titan-text-express-v1:0:8k", "display_name": "Titan Text G1 - Express", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb" }, "verification_status": "aggregator_only" } } ], "released_at": "2024-12-01", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "titan", "capabilities": { "function_calling": true, "stream": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Titan Text G1 - Express" } ] }, { "slug": "amazon/amazon.titan-text-lite-v1", "model_name": "amazon.titan-text-lite-v1", "display_name": "amazon.titan-text-lite-v1", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm+pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from pydantic-prices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "completion from pydantic-prices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "completion from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "0.25", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-south-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-southeast-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ca-central-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-3" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "sa-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "max_input_tokens": 42000, "max_output_tokens": 4000, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "amazon/amazon.titan-text-premier-v1:0", "model_name": "amazon.titan-text-premier-v1:0", "display_name": "amazon.titan-text-premier-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" } ], "max_input_tokens": 42000, "max_output_tokens": 32000, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "amazon/amazon.titan-tg1-large", "model_name": "amazon.titan-tg1-large", "display_name": "amazon.titan-tg1-large", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 8000, "max_output_tokens": 8000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "amazon.titan-tg1-large" } ] }, { "slug": "amazon/nova-2-lite-v1", "model_name": "nova-2-lite-v1", "display_name": "Nova 2 Lite", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon AWS", "official": true, "source": "computeprices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.33" }, "completion": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "prompt": "computeprices", "completion": "computeprices" }, "tracks": [ { "label": "Batch", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } }, { "label": "Base pricing", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "family": "Nova", "capabilities": { "vision": true, "video_input": true, "prompt_caching": true, "function_calling": true, "reasoning": true, "pdf_input": true, "stream": true }, "intro": "Efficient model for low-latency assistance, extraction, and routine automation", "released_at": "2024-01-01", "max_output_tokens": 65535, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "deep_thinking", "benchmarks": { "intelligence_index": null, "coding_index": 23, "agentic_index": null }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon/nova-2-lite-v1" ], "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Nova 2 Lite" } ] }, { "slug": "amazon/nova-lite-v1", "model_name": "nova-lite-v1", "display_name": "Nova Lite", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon AWS", "official": true, "source": "computeprices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" } }, "provenance": { "base_charges": { "prompt": "computeprices", "completion": "computeprices" }, "tracks": [ { "label": "Batch", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } }, { "label": "Base pricing", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 300000, "family": "Nova", "capabilities": { "vision": true, "video_input": true, "function_calling": true, "reasoning": true, "structured_output": true, "pdf_input": true, "prompt_caching": true, "stream": true }, "intro": "Nova Lite is a fast, low-cost multimodal foundation model capable of reasoning over text, images, and video in 200+ languages.", "released_at": "2025-04-14", "max_output_tokens": 300000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "knowledge_cutoff": "2024-10", "model_type": "vision_understanding", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon/nova-lite-v1" ], "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "300000", "new": "5120", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "5120", "new": "300000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "5120", "new": "300000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "300000", "new": "5120", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "5120", "new": "300000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "300000", "new": "5120", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "5120", "new": "300000", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "300000", "new": "5120", "note": "max_output_tokens" }, { "date": "2026-08-05", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Nova Lite" } ] }, { "slug": "amazon/nova-micro-v1", "model_name": "nova-micro-v1", "display_name": "Nova Micro", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon AWS", "official": true, "source": "computeprices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" } }, "provenance": { "base_charges": { "prompt": "computeprices", "completion": "computeprices" }, "tracks": [ { "label": "Batch", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } }, { "label": "Base pricing", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 128000, "family": "Nova", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "stream": true }, "intro": "Nova Micro is a multilingual text-to-text foundation model with strong reasoning capabilities and broad language coverage across 200+ languages.", "released_at": "2025-04-14", "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "knowledge_cutoff": "2024-10", "model_type": "vision_understanding", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon/nova-micro-v1" ], "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "128000", "new": "5120", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "5120", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "5120", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "128000", "new": "5120", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "5120", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "128000", "new": "5120", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "5120", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "128000", "new": "5120", "note": "max_output_tokens" }, { "date": "2026-08-05", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-08-05", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Nova Micro" } ] }, { "slug": "amazon/nova-premier-v1", "model_name": "nova-premier-v1", "display_name": "Nova Premier", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon AWS", "official": true, "source": "computeprices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "12.5" } }, "provenance": { "base_charges": { "prompt": "computeprices", "completion": "computeprices" }, "tracks": [ { "label": "Batch", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } }, { "label": "Base pricing", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "family": "Nova", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "pdf_input": true, "stream": true }, "intro": "Flagship model for demanding analysis, coding, and production agent workflows", "released_at": "2025-10-31", "max_output_tokens": 32000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "parameters": { "supported": [ "max_tokens", "stop", "temperature", "tools", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon/nova-premier-v1" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Nova Premier" } ] }, { "slug": "amazon/nova-pro-v1", "model_name": "nova-pro-v1", "display_name": "Nova Pro", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon AWS", "official": true, "source": "computeprices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "computeprices", "completion": "computeprices", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "computeprices+portkey", "charge_sources": { "prompt": "computeprices", "completion": "computeprices", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "us.amazon.nova-pro-v1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "af-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.96" }, "completion": { "unit": "per_M_tokens", "price": "3.84" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-northeast-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.95" }, "completion": { "unit": "per_M_tokens", "price": "3.8" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-northeast-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-northeast-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.94" }, "completion": { "unit": "per_M_tokens", "price": "3.76" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-south-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "1.08" }, "completion": { "unit": "per_M_tokens", "price": "4.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-southeast-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.84" }, "completion": { "unit": "per_M_tokens", "price": "3.36" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-southeast-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-southeast-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.87" }, "completion": { "unit": "per_M_tokens", "price": "3.48" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-southeast-4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-southeast-5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-southeast-6", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ap-southeast-7", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ca-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "ca-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "1.05" }, "completion": { "unit": "per_M_tokens", "price": "4.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "eu-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "eu-central-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.87" }, "completion": { "unit": "per_M_tokens", "price": "3.48" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "eu-north-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "1.28" }, "completion": { "unit": "per_M_tokens", "price": "5.21" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "eu-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.88" }, "completion": { "unit": "per_M_tokens", "price": "3.52" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "eu-south-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.92" }, "completion": { "unit": "per_M_tokens", "price": "3.68" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "eu-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "1.13" }, "completion": { "unit": "per_M_tokens", "price": "4.52" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "eu-west-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "1.18" }, "completion": { "unit": "per_M_tokens", "price": "4.72" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "eu-west-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "me-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "me-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "mx-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "sa-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "us-east-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "us-gov-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.96" }, "completion": { "unit": "per_M_tokens", "price": "3.84" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "us-gov-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "us.amazon.nova-pro-v1", "region": "us-west-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 300000, "family": "Nova", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "structured_output": true, "pdf_input": true, "prompt_caching": true, "stream": true }, "intro": "Flagship model for demanding analysis, coding, and production agent workflows", "released_at": "2024-12-03", "knowledge_cutoff": "2024-04", "max_output_tokens": 5000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "deprecated": true, "parameters": { "supported": [ "max_tokens", "stop", "temperature", "tools", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon/nova-pro-v1", "us.amazon.nova-pro-v1" ], "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "5000", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "32000", "new": "5000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "32000", "new": "5000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "5000", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "32000", "new": "5000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "5000", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "32000", "new": "5000", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "5000", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-15", "kind": "limit", "old": "5000", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Nova Pro" } ] }, { "slug": "amazon/regional.amazon.nova-2-lite-v1:0", "model_name": "regional.amazon.nova-2-lite-v1:0", "display_name": "regional.amazon.nova-2-lite-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.33" }, "completion": { "unit": "per_M_tokens", "price": "2.75" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0825" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Amazon Nova 2 Lite is an advanced multimodal reasoning model that intelligently balances performance and efficiency by dynamically adjusting reasoning depth based on task complexity. With flexible controls for developers to adjust the reasoning process, Nova 2 Lite delivers superior results for agentic workflows across software development, consumer experiences and enterprise application.", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "regional.amazon.nova-2-lite-v1:0" } ] }, { "slug": "amazon/rerank-v4.0-fast", "model_name": "rerank-v4.0-fast", "display_name": "rerank-v4.0-fast", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2000" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_rerank", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "rerank-v4.0-fast" } ] }, { "slug": "amazon/stability.sd3-5-large-v1:0", "model_name": "stability.sd3-5-large-v1:0", "display_name": "stability.sd3-5-large-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm+portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.08" } }, "provenance": { "base_charges": { "image_output": "litellm" }, "verification_status": "cross_checked" } }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.08" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "max_input_tokens": 77, "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true }, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "amazon/stability.sd3-large-v1:0", "model_name": "stability.sd3-large-v1:0", "display_name": "stability.sd3-large-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm+portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.08" } }, "provenance": { "base_charges": { "image_output": "litellm" }, "verification_status": "cross_checked" } }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.00000008" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.00000008" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "max_input_tokens": 77, "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "amazon/stability.stable-diffusion-xl-v0", "model_name": "stability.stable-diffusion-xl-v0", "display_name": "stability.stable-diffusion-xl-v0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm+portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.018" } }, "provenance": { "base_charges": { "image_output": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.018" }, "discarded_charge": { "unit": "per_image", "price": "0.036" }, "message": "image_output from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.018" }, "discarded_charge": { "unit": "per_image", "price": "0.036" }, "message": "image_output from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.018" }, "discarded_charge": { "unit": "per_image", "price": "0.072" }, "message": "image_output from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.018" }, "discarded_charge": { "unit": "per_image", "price": "0.04" }, "message": "image_output from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 77, "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "amazon/stability.stable-diffusion-xl-v1", "model_name": "stability.stable-diffusion-xl-v1", "display_name": "stability.stable-diffusion-xl-v1", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm+portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.04" }, "discarded_charge": { "unit": "per_image", "price": "0.08" }, "message": "image_output from litellm conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 77, "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "amazon/stability.stable-image-core-v1:1", "model_name": "stability.stable-image-core-v1:1", "display_name": "stability.stable-image-core-v1:1", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm+portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "litellm" }, "verification_status": "cross_checked" }, "provider_model_id": "stability.stable-image-core-v1:0" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00000004" } }, "provenance": { "base_charges": { "image_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "stability.stable-image-core-v1:0", "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00000004" }, "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "stability.stable-image-core-v1:0", "region": "us-west-2" } ], "max_input_tokens": 77, "model_type": "image_generation", "capabilities": { "image_output": true }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "stability.stable-image-core-v1:0" ], "price_history": [ { "date": "2026-07-26", "kind": "capability", "note": "vision: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "amazon/stability.stable-image-ultra-v1:1", "model_name": "stability.stable-image-ultra-v1:1", "display_name": "stability.stable-image-ultra-v1:1", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm+portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.14" } }, "provenance": { "base_charges": { "image_output": "litellm" }, "verification_status": "cross_checked" }, "provider_model_id": "stability.stable-image-ultra-v1:0" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00000014" }, "image_output": { "unit": "per_image", "price": "0.14" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "stability.stable-image-ultra-v1:0", "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00000014" }, "image_output": { "unit": "per_image", "price": "0.14" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "stability.stable-image-ultra-v1:0", "region": "us-west-2" } ], "max_input_tokens": 77, "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true }, "modalities": { "input": [ "image" ], "output": [] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "stability.stable-image-ultra-v1:0" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "amazon/us.amazon.nova-2-lite-v1:0", "model_name": "us.amazon.nova-2-lite-v1:0", "display_name": "us.amazon.nova-2-lite-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "models-dev+litellm+pydantic-prices+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.33" }, "completion": { "unit": "per_M_tokens", "price": "2.75" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.33" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.75" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0825" }, "message": "cache_read from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0825" }, "message": "cache_read from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.33" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.75" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0825" }, "message": "cache_read from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.33" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.75" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from pydantic-prices conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-2-lite-v1:0" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.09" }, "prompt": { "unit": "per_M_tokens", "price": "0.36" }, "completion": { "unit": "per_M_tokens", "price": "3.01" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ap-east-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.09" }, "prompt": { "unit": "per_M_tokens", "price": "0.36" }, "completion": { "unit": "per_M_tokens", "price": "3.01" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.09" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0825" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.36" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.33" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.01" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.75" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ap-northeast-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.09" }, "prompt": { "unit": "per_M_tokens", "price": "0.36" }, "completion": { "unit": "per_M_tokens", "price": "2.96" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ap-northeast-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0875" }, "prompt": { "unit": "per_M_tokens", "price": "0.35" }, "completion": { "unit": "per_M_tokens", "price": "2.95" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ap-south-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.1025" }, "prompt": { "unit": "per_M_tokens", "price": "0.41" }, "completion": { "unit": "per_M_tokens", "price": "3.39" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ap-southeast-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.08" }, "prompt": { "unit": "per_M_tokens", "price": "0.32" }, "completion": { "unit": "per_M_tokens", "price": "2.63" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ap-southeast-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.08" }, "prompt": { "unit": "per_M_tokens", "price": "0.32" }, "completion": { "unit": "per_M_tokens", "price": "2.64" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ap-southeast-3" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0825" }, "prompt": { "unit": "per_M_tokens", "price": "0.33" }, "completion": { "unit": "per_M_tokens", "price": "2.71" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ap-southeast-4" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.1025" }, "prompt": { "unit": "per_M_tokens", "price": "0.41" }, "completion": { "unit": "per_M_tokens", "price": "3.39" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ap-southeast-5" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.1025" }, "prompt": { "unit": "per_M_tokens", "price": "0.41" }, "completion": { "unit": "per_M_tokens", "price": "3.39" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ap-southeast-7" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.08" }, "prompt": { "unit": "per_M_tokens", "price": "0.32" }, "completion": { "unit": "per_M_tokens", "price": "2.67" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.32" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.352" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.67" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.97" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ca-central-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.085" }, "prompt": { "unit": "per_M_tokens", "price": "0.34" }, "completion": { "unit": "per_M_tokens", "price": "2.81" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.34" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.374" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.81" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.091" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "ca-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.10725" }, "prompt": { "unit": "per_M_tokens", "price": "0.429" }, "completion": { "unit": "per_M_tokens", "price": "3.597" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.10725" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0975" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.429" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.39" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.597" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.27" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-2-lite-v1:0", "region": "eu-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.550042" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.09075" }, "prompt": { "unit": "per_M_tokens", "price": "0.363" }, "completion": { "unit": "per_M_tokens", "price": "2.992" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.09075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0825" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.363" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.33" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.992" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.72" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-2-lite-v1:0", "region": "eu-north-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.132" }, "prompt": { "unit": "per_M_tokens", "price": "0.528" }, "completion": { "unit": "per_M_tokens", "price": "4.411" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.132" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0825" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.528" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.481" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4.411" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4.1" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-2-lite-v1:0", "region": "eu-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.09075" }, "prompt": { "unit": "per_M_tokens", "price": "0.363" }, "completion": { "unit": "per_M_tokens", "price": "3.205" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.09075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0825" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.363" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.33" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.205" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.75" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-2-lite-v1:0", "region": "eu-south-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0935" }, "prompt": { "unit": "per_M_tokens", "price": "0.374" }, "completion": { "unit": "per_M_tokens", "price": "3.157" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0935" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.085" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.374" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.34" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.157" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.87" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-2-lite-v1:0", "region": "eu-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.105" }, "prompt": { "unit": "per_M_tokens", "price": "0.42" }, "completion": { "unit": "per_M_tokens", "price": "3.52" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "eu-west-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.121" }, "prompt": { "unit": "per_M_tokens", "price": "0.484" }, "completion": { "unit": "per_M_tokens", "price": "4.059" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.121" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.11" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.484" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.44" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4.059" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.69" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-2-lite-v1:0", "region": "eu-west-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.095" }, "prompt": { "unit": "per_M_tokens", "price": "0.38" }, "completion": { "unit": "per_M_tokens", "price": "3.13" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "il-central-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.08" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "me-central-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.33" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.75" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.33" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.75" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "us-east-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0975" }, "prompt": { "unit": "per_M_tokens", "price": "0.39" }, "completion": { "unit": "per_M_tokens", "price": "3.21" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.39" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.429" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.21" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.531" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "us-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.33" }, "message": "prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.75" }, "message": "completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "global.amazon.nova-2-lite-v1:0", "region": "us-west-2" } ], "intro": "Multimodal reasoning model for visual analysis, planning, and tool use", "released_at": "2024-12-01", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "nova", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "pdf_input": true, "stream": true }, "model_type": "vision_understanding", "parameters": { "unsupported": [ "temperature" ] }, "knowledge_cutoff": "2024-10", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon.nova-2-lite-v1:0", "amazon/nova-2-lite", "apac.amazon.nova-2-lite-v1:0", "eu.amazon.nova-2-lite-v1:0", "global.amazon.nova-2-lite-v1:0", "jp.amazon.nova-2-lite-v1:0", "nova-2-Lite", "nova-2-lite" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "amazon/us.amazon.nova-2-pro-preview-20251202-v1:0", "model_name": "us.amazon.nova-2-pro-preview-20251202-v1:0", "display_name": "us.amazon.nova-2-pro-preview-20251202-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.1875" }, "completion": { "unit": "per_M_tokens", "price": "17.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.546875" }, "audio_input": { "unit": "per_M_tokens", "price": "2.1875" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm" }, "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-2-pro-preview-20251202-v1:0" } ], "max_input_tokens": 1000000, "max_output_tokens": 64000, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon.nova-2-pro-preview-20251202-v1:0", "apac.amazon.nova-2-pro-preview-20251202-v1:0", "eu.amazon.nova-2-pro-preview-20251202-v1:0" ] }, { "slug": "amazon/us.amazon.nova-canvas-v1:0", "model_name": "us.amazon.nova-canvas-v1:0", "display_name": "us.amazon.nova-canvas-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "litellm" }, "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-canvas-v1:0" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-canvas-v1:0", "region": "ap-northeast-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-canvas-v1:0", "region": "eu-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-canvas-v1:0", "region": "us-east-1" } ], "max_input_tokens": 2600, "model_type": "image_generation", "deprecation_date": "2026-09-30", "capabilities": { "vision": true, "image_output": true }, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon.nova-canvas-v1:0" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "amazon/us.amazon.nova-lite-v1:0", "model_name": "us.amazon.nova-lite-v1:0", "display_name": "us.amazon.nova-lite-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "models-dev+litellm+pydantic-prices+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.015" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.06" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.063" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.24" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.252" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.06" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.078" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.24" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.312" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.015" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "2", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "af-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.072" }, "completion": { "unit": "per_M_tokens", "price": "0.288" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "apac.amazon.nova-lite-v1:0", "region": "ap-east-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.072" }, "completion": { "unit": "per_M_tokens", "price": "0.288" }, "cache_read": { "unit": "per_M_tokens", "price": "0.018" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.018" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-northeast-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.666667", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.071" }, "completion": { "unit": "per_M_tokens", "price": "0.284" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0178" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0178" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-northeast-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.685393", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-northeast-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.071" }, "completion": { "unit": "per_M_tokens", "price": "0.284" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0178" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0178" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.685393", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-south-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.081" }, "completion": { "unit": "per_M_tokens", "price": "0.324" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0202" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0202" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-southeast-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.485149", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.063" }, "completion": { "unit": "per_M_tokens", "price": "0.252" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0157" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0157" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-southeast-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.910828", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-southeast-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.065" }, "completion": { "unit": "per_M_tokens", "price": "0.26" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0162" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0162" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-southeast-4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.851852", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.072" }, "completion": { "unit": "per_M_tokens", "price": "0.288" }, "cache_read": { "unit": "per_M_tokens", "price": "0.018" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.018" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-southeast-5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.666667", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-southeast-6", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.072" }, "completion": { "unit": "per_M_tokens", "price": "0.288" }, "cache_read": { "unit": "per_M_tokens", "price": "0.018" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.018" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ap-southeast-7", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.666667", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.064" }, "completion": { "unit": "per_M_tokens", "price": "0.256" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "cache_read": { "unit": "per_M_tokens", "price": "0.016" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.016" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.12" }, "message": "cache_write from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ca-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.875" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "ca-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.078" }, "completion": { "unit": "per_M_tokens", "price": "0.312" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0195" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0195" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "eu-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.538462", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "eu-central-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.065" }, "completion": { "unit": "per_M_tokens", "price": "0.26" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0162" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0162" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "eu-north-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.851852", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.096" }, "completion": { "unit": "per_M_tokens", "price": "0.384" }, "cache_read": { "unit": "per_M_tokens", "price": "0.024" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.024" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "eu-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.25", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.066" }, "completion": { "unit": "per_M_tokens", "price": "0.264" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0165" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0165" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "eu-south-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.818182", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.069" }, "completion": { "unit": "per_M_tokens", "price": "0.276" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0172" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0172" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "eu-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.744186", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.084" }, "completion": { "unit": "per_M_tokens", "price": "0.336" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "eu-west-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.088" }, "completion": { "unit": "per_M_tokens", "price": "0.352" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.022" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "eu-west-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.363636", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0187" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "il-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.015" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.015" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "me-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "2", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "me-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "mx-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "sa-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.06" }, "cache_read": { "unit": "per_M_tokens", "price": "0.015" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "us-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.015" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.015" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "us-east-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "2", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "us-gov-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.072" }, "completion": { "unit": "per_M_tokens", "price": "0.288" }, "cache_read": { "unit": "per_M_tokens", "price": "0.018" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.018" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "us-gov-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.666667", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.077" }, "completion": { "unit": "per_M_tokens", "price": "0.308" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "us-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.015" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.12" }, "cache_write": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.015" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-lite-v1:0", "region": "us-west-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "2", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Efficient model for low-latency assistance, extraction, and routine automation", "released_at": "2024-12-03", "knowledge_cutoff": "2024-10", "max_input_tokens": 300000, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "nova-lite", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "video_input": true, "structured_output": true, "pdf_input": true, "stream": true, "assistant_prefill": true }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon.nova-lite-v1:0", "amazon/nova-lite", "apac.amazon.nova-lite-v1:0", "ca.amazon.nova-lite-v1:0", "eu.amazon.nova-lite-v1:0" ], "intro_i18n": { "zh-CN": "一款极低成本的多模态模型，能够以极快速度处理图像、视频和文本输入。", "zh-TW": "一款極低成本的多模態模型，能以極快速度處理圖像、影片與文字輸入。", "ja-JP": "非常に低コストで、画像、動画、テキスト入力を超高速で処理できるマルチモーダルモデルです。", "ru-RU": "Очень недорогая мультимодальная модель с чрезвычайно быстрой обработкой изображений, видео и текста." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "assistant_prefill: false→true" } ] }, { "slug": "amazon/us.amazon.nova-micro-v1:0", "model_name": "us.amazon.nova-micro-v1:0", "display_name": "us.amazon.nova-micro-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "models-dev+litellm+pydantic-prices+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.00875" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.035" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.037" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.148" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.035" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.046" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.184" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.00875" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-micro-v1:0", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "2", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "af-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "ap-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0105" }, "prompt": { "unit": "per_M_tokens", "price": "0.042" }, "completion": { "unit": "per_M_tokens", "price": "0.168" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0105" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "apac.amazon.nova-micro-v1:0", "region": "ap-northeast-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.666667", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0103" }, "prompt": { "unit": "per_M_tokens", "price": "0.041" }, "completion": { "unit": "per_M_tokens", "price": "0.164" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0103" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "apac.amazon.nova-micro-v1:0", "region": "ap-northeast-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.699029", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "ap-northeast-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0103" }, "prompt": { "unit": "per_M_tokens", "price": "0.041" }, "completion": { "unit": "per_M_tokens", "price": "0.164" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0103" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "apac.amazon.nova-micro-v1:0", "region": "ap-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.699029", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "ap-south-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0117" }, "prompt": { "unit": "per_M_tokens", "price": "0.047" }, "completion": { "unit": "per_M_tokens", "price": "0.188" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0117" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "apac.amazon.nova-micro-v1:0", "region": "ap-southeast-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.495726", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.037" }, "completion": { "unit": "per_M_tokens", "price": "0.148" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0093" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.037" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03605" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.148" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1442" }, "message": "completion from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0093" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.0185" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.018025" }, "message": "batch prompt from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.074" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0721" }, "message": "batch completion from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "ap-southeast-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.88172", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "ap-southeast-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "ap-southeast-4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.042" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "cache_write_1h": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "cache_write_1h": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.042" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.035" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "apac.amazon.nova-micro-v1:0", "region": "ap-southeast-5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.416667", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "ap-southeast-6", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "ap-southeast-7", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "ca-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "ca-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0115" }, "prompt": { "unit": "per_M_tokens", "price": "0.046" }, "completion": { "unit": "per_M_tokens", "price": "0.184" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0115" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-micro-v1:0", "region": "eu-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.521739", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "eu-central-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0095" }, "prompt": { "unit": "per_M_tokens", "price": "0.038" }, "completion": { "unit": "per_M_tokens", "price": "0.152" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0095" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-micro-v1:0", "region": "eu-north-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.842105", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.014" }, "prompt": { "unit": "per_M_tokens", "price": "0.056" }, "completion": { "unit": "per_M_tokens", "price": "0.224" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.014" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-micro-v1:0", "region": "eu-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.25", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0097" }, "prompt": { "unit": "per_M_tokens", "price": "0.039" }, "completion": { "unit": "per_M_tokens", "price": "0.156" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0097" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-micro-v1:0", "region": "eu-south-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.804124", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "prompt": { "unit": "per_M_tokens", "price": "0.04" }, "completion": { "unit": "per_M_tokens", "price": "0.16" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.01" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-micro-v1:0", "region": "eu-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.75", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.049" }, "completion": { "unit": "per_M_tokens", "price": "0.196" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "eu-west-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.013" }, "prompt": { "unit": "per_M_tokens", "price": "0.052" }, "completion": { "unit": "per_M_tokens", "price": "0.208" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.013" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "eu.amazon.nova-micro-v1:0", "region": "eu-west-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.346154", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.011" }, "prompt": { "unit": "per_M_tokens", "price": "0.044" }, "completion": { "unit": "per_M_tokens", "price": "0.176" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "eu.amazon.nova-micro-v1:0", "region": "il-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.0087" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0087" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "apac.amazon.nova-micro-v1:0", "region": "me-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "2.011494", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "me-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "mx-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "sa-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0" }, "cache_read": { "unit": "per_M_tokens", "price": "0.00875" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.04375" }, "message": "cache_write from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "us-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.04375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.00875" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.00875" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0.04375" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.07" }, "message": "cache_write from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "us-east-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "2", "cache_write": "1.6" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "us-gov-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.042" }, "completion": { "unit": "per_M_tokens", "price": "0.168" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0175" }, "cache_write": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "us-gov-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.04375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.00875" }, "prompt": { "unit": "per_M_tokens", "price": "0.035" }, "completion": { "unit": "per_M_tokens", "price": "0.14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.07" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.00875" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0175" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0.04375" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.07" }, "message": "cache_write from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-micro-v1:0", "region": "us-west-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "2", "cache_write": "1.6" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Efficient model for low-latency assistance, extraction, and routine automation", "released_at": "2024-12-03", "knowledge_cutoff": "2024-10", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nova-micro", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "stream": true, "assistant_prefill": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon.nova-micro-v1:0", "amazon/nova-micro", "apac.amazon.nova-micro-v1:0", "eu.amazon.nova-micro-v1:0" ], "intro_i18n": { "zh-CN": "一款仅支持文本的模型，具备超低延迟和极低成本。", "zh-TW": "一款僅支援文字的模型，提供超低延遲與極低成本的運算效能。", "ja-JP": "超低レイテンシかつ非常に低コストで動作するテキスト専用モデルです。", "ru-RU": "Только текстовая модель с ультранизкой задержкой и минимальными затратами." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "assistant_prefill: false→true" } ] }, { "slug": "amazon/us.amazon.nova-premier-v1:0", "model_name": "us.amazon.nova-premier-v1:0", "display_name": "us.amazon.nova-premier-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "litellm+pydantic-prices+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "12.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.625" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "pydantic-prices" }, "verification_status": "cross_checked" }, "provider_model_id": "amazon.nova-premier-v1:0" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.625" }, "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "12.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.625" }, "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "12.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.625" }, "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "12.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "max_output_tokens": 10000, "model_type": "vision_understanding", "deprecation_date": "2026-09-14", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "stream": true }, "released_at": "2024-12-03", "knowledge_cutoff": "2024-10", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "nova", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon.nova-premier-v1:0" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "amazon/us.amazon.nova-pro-v1:0", "model_name": "us.amazon.nova-pro-v1:0", "display_name": "us.amazon.nova-pro-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "models-dev+litellm+pydantic-prices+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.96" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.84" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.96" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.84" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.84" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.36" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.05" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4.2" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "2", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "af-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.96" }, "completion": { "unit": "per_M_tokens", "price": "3.84" }, "cache_read": { "unit": "per_M_tokens", "price": "0.24" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.24" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-northeast-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.666667", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.95" }, "completion": { "unit": "per_M_tokens", "price": "3.8" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2375" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2375" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-northeast-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.684211", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-northeast-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.94" }, "completion": { "unit": "per_M_tokens", "price": "3.76" }, "cache_read": { "unit": "per_M_tokens", "price": "0.235" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.235" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.702128", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-south-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.08" }, "completion": { "unit": "per_M_tokens", "price": "4.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.27" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.27" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-southeast-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.481481", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.84" }, "completion": { "unit": "per_M_tokens", "price": "3.36" }, "cache_read": { "unit": "per_M_tokens", "price": "0.21" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.21" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-southeast-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.904762", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-southeast-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.87" }, "completion": { "unit": "per_M_tokens", "price": "3.48" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2175" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2175" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-southeast-4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.83908", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.96" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "cache_write_1h": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "cache_write_1h": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.96" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.8" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "apac.amazon.nova-pro-v1:0", "region": "ap-southeast-5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.416667", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-southeast-6", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ap-southeast-7", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ca-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "ca-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.05" }, "completion": { "unit": "per_M_tokens", "price": "4.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2625" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2625" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "eu-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.52381", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "eu-central-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.87" }, "completion": { "unit": "per_M_tokens", "price": "3.48" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2175" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2175" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "eu-north-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.83908", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.28" }, "completion": { "unit": "per_M_tokens", "price": "5.21" }, "cache_read": { "unit": "per_M_tokens", "price": "0.32" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.32" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "eu-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.25", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.88" }, "completion": { "unit": "per_M_tokens", "price": "3.52" }, "cache_read": { "unit": "per_M_tokens", "price": "0.22" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.22" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "eu-south-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1.818182", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.92" }, "completion": { "unit": "per_M_tokens", "price": "3.68" }, "cache_read": { "unit": "per_M_tokens", "price": "0.23" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.23" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "eu-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.73913", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.13" }, "completion": { "unit": "per_M_tokens", "price": "4.52" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "eu-west-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.18" }, "completion": { "unit": "per_M_tokens", "price": "4.72" }, "cache_read": { "unit": "per_M_tokens", "price": "0.295" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.295" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "eu-west-3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1.355932", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "il-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "me-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "2", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "me-south-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "mx-central-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "sa-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "us-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "us-east-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "2", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "cache_write_1h": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "us-gov-east-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "cache_write_1h": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.96" }, "completion": { "unit": "per_M_tokens", "price": "3.84" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "us-gov-west-1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.03" }, "completion": { "unit": "per_M_tokens", "price": "4.12" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "us-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "cache_write": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "truefoundry", "cache_write_1h": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "cache_read from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "amazon.nova-pro-v1:0", "region": "us-west-2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_write_1h": "1", "cache_read": "2", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Flagship model for demanding analysis, coding, and production agent workflows", "released_at": "2024-12-03", "knowledge_cutoff": "2024-10", "max_input_tokens": 300000, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "nova-pro", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "pdf_input": true, "stream": true, "assistant_prefill": true }, "model_type": "vision_understanding", "docs_url": "https://aws.amazon.com/bedrock/pricing/", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "amazon.nova-pro-v1:0", "amazon/nova-pro", "apac.amazon.nova-pro-v1:0", "eu.amazon.nova-pro-v1:0" ], "intro_i18n": { "zh-CN": "一款功能强大的多模态模型，在准确性、速度和成本之间实现最佳平衡，适用于多种任务。", "zh-TW": "一款功能強大的多模態模型，在準確性、速度與成本之間達到最佳平衡，適用於各類任務。", "ja-JP": "幅広いタスクにおいて、精度、速度、コストの最適なバランスを実現する高性能マルチモーダルモデルです。", "ru-RU": "Высокопроизводительная мультимодальная модель с оптимальным балансом точности, скорости и стоимости для широкого спектра задач." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "assistant_prefill: false→true" } ] }, { "slug": "amazon/us.twelvelabs.marengo-embed-2-7-v1:0", "model_name": "us.twelvelabs.marengo-embed-2-7-v1:0", "display_name": "us.twelvelabs.marengo-embed-2-7-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "70" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_input": { "unit": "per_image", "price": "0.0001" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm" }, "verification_status": "aggregator_only" }, "provider_model_id": "eu.twelvelabs.marengo-embed-2-7-v1:0" } ], "max_input_tokens": 77, "model_type": "text_embedding", "deprecation_date": "2026-11-30", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "eu.twelvelabs.marengo-embed-2-7-v1:0", "twelvelabs.marengo-embed-2-7-v1:0" ] }, { "slug": "amazon/us.twelvelabs.pegasus-1-2-v1:0", "model_name": "us.twelvelabs.pegasus-1-2-v1:0", "display_name": "us.twelvelabs.pegasus-1-2-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "litellm", "charges": { "completion": { "unit": "per_M_tokens", "price": "7.5" } }, "provenance": { "base_charges": { "completion": "litellm" }, "verification_status": "aggregator_only" }, "provider_model_id": "eu.twelvelabs.pegasus-1-2-v1:0" } ], "model_type": "vision_understanding", "capabilities": { "video_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "eu.twelvelabs.pegasus-1-2-v1:0", "twelvelabs.pegasus-1-2-v1:0" ] }, { "slug": "amazon/writer.palmyra-vision-7b-v1:0", "model_name": "writer.palmyra-vision-7b-v1:0", "display_name": "writer.palmyra-vision-7b-v1:0", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "ap-northeast-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "ap-south-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "ap-southeast-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "ap-southeast-3" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "ap-southeast-4" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "eu-central-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "eu-north-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "eu-south-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "eu-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "eu-west-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "sa-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "us-east-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "writer.palmyra-vision-7b", "region": "us-west-2" } ], "capabilities": { "vision": true }, "max_input_tokens": 4000, "max_output_tokens": 4000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "writer.palmyra-vision-7b" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "writer.palmyra-vision-7b-v1:0" } ] }, { "slug": "amazon/writer.palmyra-x4-v1:0", "model_name": "writer.palmyra-x4-v1:0", "display_name": "Palmyra X4", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "models-dev+litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" }, "provider_model_id": "us.writer.palmyra-x4-v1:0" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "us.writer.palmyra-x4-v1:0", "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "us.writer.palmyra-x4-v1:0", "region": "us-east-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "us.writer.palmyra-x4-v1:0", "region": "us-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "us.writer.palmyra-x4-v1:0", "region": "us-west-2" } ], "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "released_at": "2025-04-28", "max_input_tokens": 122880, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "palmyra", "capabilities": { "function_calling": true, "reasoning": true, "pdf_input": true, "stream": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "us.writer.palmyra-x4-v1:0", "writer/palmyra-x4" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "amazon/writer.palmyra-x5-v1:0", "model_name": "writer.palmyra-x5-v1:0", "display_name": "Palmyra X5", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "models-dev+litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" }, "provider_model_id": "us.writer.palmyra-x5-v1:0" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "us.writer.palmyra-x5-v1:0", "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "us.writer.palmyra-x5-v1:0", "region": "us-east-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "us.writer.palmyra-x5-v1:0", "region": "us-west-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "us.writer.palmyra-x5-v1:0", "region": "us-west-2" } ], "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "released_at": "2025-04-28", "max_input_tokens": 1040000, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "palmyra", "capabilities": { "function_calling": true, "reasoning": true, "pdf_input": true, "stream": true }, "model_type": "text_generation", "parameters": { "supported": [ "max_tokens", "stop", "temperature", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "palmyra-x5", "us.writer.palmyra-x5-v1:0", "writer/palmyra-x5" ], "price_history": [ { "date": "2026-08-02", "kind": "capability", "note": "vision: true→false" }, { "date": "2026-08-02", "kind": "capability", "note": "structured_output: true→false" }, { "date": "2026-07-30", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-30", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "amazon/zai.glm-4.7", "model_name": "zai.glm-4.7", "display_name": "GLM-4.7", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "models-dev+litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.72" }, "completion": { "unit": "per_M_tokens", "price": "2.64" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-northeast-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.72" }, "completion": { "unit": "per_M_tokens", "price": "2.64" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-south-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.618" }, "completion": { "unit": "per_M_tokens", "price": "2.266" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-southeast-2", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.72" }, "completion": { "unit": "per_M_tokens", "price": "2.64" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-southeast-3", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.72" }, "completion": { "unit": "per_M_tokens", "price": "2.64" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "eu-north-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.618" }, "completion": { "unit": "per_M_tokens", "price": "2.266" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu-west-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.72" }, "completion": { "unit": "per_M_tokens", "price": "2.64" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "sa-east-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "released_at": "2025-12-22", "knowledge_cutoff": "2025-04", "max_input_tokens": 204800, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true, "parallel_function_calling": true }, "docs_url": "https://aws.amazon.com/bedrock/pricing/", "model_type": "deep_thinking", "status": "beta", "parameters": { "supported": [ "frequency_penalty", "functions", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cerebras/zai-glm-4.7", "zai-glm-4.7" ], "intro_i18n": { "zh-CN": "GLM-4.7是智谱的新一代旗舰模型，总参数量为3550亿，活跃参数量为320亿，在通用对话、推理和代理能力方面全面升级。GLM-4.7增强了交错思维，并引入了保留思维和回合级思维。", "zh-TW": "GLM-4.7 是智譜的新一代旗艦模型，擁有3550億總參數和320億活躍參數，在通用對話、推理和代理能力方面全面升級。GLM-4.7 增強了交錯思考，並引入了保留思考和回合級思考。", "ja-JP": "GLM-4.7はZhipuの新世代フラッグシップモデルで、355Bの総パラメータと32Bのアクティブパラメータを備え、一般的な対話、推論、エージェント機能が完全にアップグレードされています。GLM-4.7はインターリーブド思考を強化し、保存思考およびターンレベル思考を導入しています。", "ru-RU": "GLM-4.7 — это новая флагманская модель Zhipu с 355B общих параметров и 32B активных параметров, полностью обновлённая в области общего диалога, рассуждений и агентных возможностей. GLM-4.7 улучшает Перемежающееся Мышление и вводит Сохранённое Мышление и Мышление на уровне хода." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" } ] }, { "slug": "amazon/zai.glm-4.7-flash", "model_name": "zai.glm-4.7-flash", "display_name": "GLM-4.7-Flash", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "models-dev+litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.07" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.08" }, "completion": { "unit": "per_M_tokens", "price": "0.48" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-northeast-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.08" }, "completion": { "unit": "per_M_tokens", "price": "0.48" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-south-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.0721" }, "completion": { "unit": "per_M_tokens", "price": "0.412" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-southeast-2", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.08" }, "completion": { "unit": "per_M_tokens", "price": "0.48" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-southeast-3", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.08" }, "completion": { "unit": "per_M_tokens", "price": "0.48" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "eu-central-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.08" }, "completion": { "unit": "per_M_tokens", "price": "0.48" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "eu-north-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.08" }, "completion": { "unit": "per_M_tokens", "price": "0.48" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "eu-south-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.08" }, "completion": { "unit": "per_M_tokens", "price": "0.48" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "eu-west-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.11" }, "completion": { "unit": "per_M_tokens", "price": "0.62" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "eu-west-2", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.08" }, "completion": { "unit": "per_M_tokens", "price": "0.48" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "sa-east-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.07" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.07" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.07" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows", "released_at": "2026-01-19", "knowledge_cutoff": "2025-04", "max_input_tokens": 200000, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm-flash", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "open_weights": true, "stream": true }, "docs_url": "https://aws.amazon.com/bedrock/pricing/", "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "amazon/zai.glm-5", "model_name": "zai.glm-5", "display_name": "GLM-5", "vendor": "amazon", "pricing": [ { "provider": "amazon-bedrock", "provider_name": "Amazon Bedrock", "official": true, "source": "models-dev+litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "3.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.2" }, "completion": { "unit": "per_M_tokens", "price": "3.84" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-northeast-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.2" }, "completion": { "unit": "per_M_tokens", "price": "3.84" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-south-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.03" }, "completion": { "unit": "per_M_tokens", "price": "3.3" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-southeast-2", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.2" }, "completion": { "unit": "per_M_tokens", "price": "3.84" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "ap-southeast-3", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.2" }, "completion": { "unit": "per_M_tokens", "price": "3.84" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "ap-southeast-4" }, { "provider": "amazon-bedrock", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.2" }, "completion": { "unit": "per_M_tokens", "price": "3.84" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "region": "eu-central-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.2" }, "completion": { "unit": "per_M_tokens", "price": "3.84" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "eu-north-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.55" }, "completion": { "unit": "per_M_tokens", "price": "4.96" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "eu-west-2", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.2" }, "completion": { "unit": "per_M_tokens", "price": "3.84" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "region": "sa-east-1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1.75", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "3.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-1" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "3.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east-2" }, { "provider": "amazon-bedrock", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "3.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west-2" } ], "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "released_at": "2026-03-18", "max_input_tokens": 202752, "max_output_tokens": 101376, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "open_weights": true }, "docs_url": "https://aws.amazon.com/bedrock/pricing/", "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "antgroup/Ling-2.5-1T", "model_name": "Ling-2.5-1T", "display_name": "Ling-2.5-1T", "vendor": "antgroup", "pricing": [ { "provider": "antgroup", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.588235" }, "completion": { "unit": "per_M_tokens", "price": "1.176471" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-02-16", "max_input_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "作为Ling系列最新的旗舰实时模型，Ling-2.5-1T在模型架构、令牌效率和偏好对齐方面进行了全面升级，旨在将可访问AI的质量提升到一个新高度。", "zh-TW": "作為 Ling 系列最新的旗艦實時模型，Ling-2.5-1T 在模型架構、令牌效率和偏好對齊方面進行了全面升級，旨在將可訪問 AI 的質量提升到新高度。", "ja-JP": "Lingシリーズの最新フラッグシップリアルタイムモデルであるLing-2.5-1Tは、モデルアーキテクチャ、トークン効率、嗜好整合性において包括的なアップグレードを導入し、アクセス可能なAIの品質を新たなレベルに引き上げることを目指しています。", "ru-RU": "Как последняя флагманская модель реального времени в серии Ling, Ling-2.5-1T представляет собой комплексные улучшения архитектуры модели, эффективности токенов и выравнивания предпочтений, направленные на повышение качества доступного ИИ на новый уровень." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Ling-2.5-1T" } ] }, { "slug": "antgroup/Ling-2.6-1T", "model_name": "Ling-2.6-1T", "display_name": "Ling-2.6-1T", "vendor": "antgroup", "pricing": [ { "provider": "antgroup", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.661765" }, "completion": { "unit": "per_M_tokens", "price": "2.647059" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-04-29", "max_input_tokens": 262144, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true, "structured_output": true, "prompt_caching": true, "open_weights": true }, "intro": "Tool-capable chat model for instruction following and agentic application workflows", "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "ling", "parameters": { "supported": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "inclusionAI/Ling-2.6-1T", "inclusionai/ling-2.6-1t", "novita/inclusionai/ling-2.6-1t" ], "intro_i18n": { "zh-CN": "最新的旗舰大语言模型，支持100万令牌上下文窗口，实现从逻辑推理到任务执行的端到端工作流程。", "zh-TW": "最新的旗艦大型語言模型，支持 1M 令牌上下文窗口，實現從邏輯推理到任務執行的端到端工作流程。", "ja-JP": "最新のフラッグシップ大規模言語モデルで、1Mトークンのコンテキストウィンドウをサポートし、論理的推論からタスク実行までのエンドツーエンドのワークフローを可能にします。", "ru-RU": "Последняя флагманская модель крупного языкового ИИ, поддерживающая контекстное окно на 1 миллион токенов и обеспечивающая сквозной рабочий процесс от логического рассуждения до выполнения задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Ling-2.6-1T" } ] }, { "slug": "antgroup/ling-2.6-flash:free", "model_name": "ling-2.6-flash:free", "display_name": "Ling-2.6-flash", "vendor": "antgroup", "pricing": [ { "provider": "antgroup", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.088235" }, "completion": { "unit": "per_M_tokens", "price": "0.264706" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "Ling-2.6-flash" } ], "released_at": "2026-04-22", "max_input_tokens": 262144, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true, "structured_output": true, "prompt_caching": true, "open_weights": true }, "intro": "Efficient model for low-latency assistance, extraction, and routine automation", "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "ling", "knowledge_cutoff": "2025-06", "deprecated": true, "status": "deprecated", "benchmarks": { "intelligence_index": 14.2, "coding_index": 25.3, "agentic_index": 2.3 }, "parameters": { "supported": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Ling-2.6-flash", "inclusionai/ling-2.6-flash", "inclusionai/ling-2.6-flash:free", "ling-2.6-flash-free", "novita/inclusionai/ling-2.6-flash" ], "intro_i18n": { "zh-CN": "Ling-2.6-flash是Ling系列最新一代高性价比模型。采用专家混合（MoE）架构，总参数量为1000亿，每个令牌激活参数为61亿，在推理性能和计算成本之间实现了最佳平衡。", "zh-TW": "Ling-2.6-flash 是 Ling 系列最新一代高性價比模型。採用專家混合（MoE）架構，總參數量為 1000 億，每個令牌激活參數數量為 61 億，在推理性能與計算成本之間實現了最佳平衡。", "ja-JP": "Ling-2.6-flashはLingシリーズの最新世代の高コストパフォーマンスモデルです。Mixture-of-Experts（MoE）アーキテクチャを採用し、総パラメータ数は100B、トークンごとの活性化パラメータ数は6.1Bで、推論性能と計算コストの最適なバランスを実現しています。", "ru-RU": "Ling-2.6-flash — это модель последнего поколения с высокой производительностью и стоимостью в серии Ling. Она использует архитектуру Mixture-of-Experts (MoE) с общим количеством параметров 100 миллиардов и 6,1 миллиарда активированных параметров на токен, достигая оптимального баланса между производительностью вывода и вычислительными затратами." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Ling-2.6-flash" } ] }, { "slug": "antgroup/ling-3.0-flash:thinking", "model_name": "ling-3.0-flash:thinking", "display_name": "Ling-3.0-flash", "vendor": "antgroup", "pricing": [ { "provider": "antgroup", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.058824" }, "completion": { "unit": "per_M_tokens", "price": "0.176471" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "Ling-3.0-flash" } ], "released_at": "2026-07-23", "max_input_tokens": 262144, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "prompt_caching": true, "open_weights": true }, "intro": "Ling-3.0-flash is a 124B-parameter Mixture-of-Experts model with approximately 5.1B parameters active per token. It prioritizes token efficiency and production-scale agentic inference, helping coding and tool-using agents complete more work within constrained latency and serving budgets.", "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "ling", "deprecated": true, "status": "deprecated", "benchmarks": { "intelligence_index": 37.8, "coding_index": 50.6, "agentic_index": 29.3 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Ling-3.0-flash", "inclusionAI/Ling-3.0-flash", "inclusionai/ling-3.0-flash", "inclusionai/ling-3.0-flash:free", "inclusionai/ling-3.0-flash:thinking", "ling-3.0-flash", "ling-3.0-flash-free" ], "intro_i18n": { "zh-CN": "Ling-3.0-flash 是 Ling 系列最新一代高性价比模型。它采用专家混合（MoE）架构，总参数量为 1240 亿，每个 token 激活参数为 51 亿。原生支持 256K 上下文窗口，可扩展至 1M。与上一代 flash 版本相比，Ling-3.0-flash 显著提升了长时任务的稳定性、工具调用的准确性以及对常见 Harness 环境的适应性。", "zh-TW": "Ling-3.0-flash 是 Ling 系列最新一代高性價比模型。它採用了專家混合（MoE）架構，總參數量達到 124B，每個 token 激活參數達 5.1B。原生支持 256K 的上下文窗口，並可擴展至 1M。與之前的 flash 版本相比，Ling-3.0-flash 顯著提升了長期任務穩定性、工具調用準確性以及對常見 Harness 環境的適應性。", "ja-JP": "Ling-3.0-flashは、Lingシリーズの最新世代の高コストパフォーマンスモデルです。Mixture-of-Experts (MoE)アーキテクチャを採用し、総パラメータ数は124B、トークンごとのアクティブパラメータ数は5.1Bです。ネイティブで256Kのコンテキストウィンドウをサポートし、最大1Mまで拡張可能です。前バージョンのflashと比較して、Ling-3.0-flashは長期タスクの安定性、ツール呼び出しの精度、一般的なHarness環境への適応性を大幅に向上させています。", "ru-RU": "Ling-3.0-flash — это новейшая высокопроизводительная модель серии Ling. Она использует архитектуру Mixture-of-Experts (MoE) с общим количеством параметров 124 млрд и 5,1 млрд активных параметров на токен. Модель изначально поддерживает контекстное окно в 256K, которое можно расширить до 1M. По сравнению с предыдущей версией flash, Ling-3.0-flash значительно улучшает стабильность выполнения задач на длинных горизонтах, точность вызова инструментов и адаптацию к стандартным средам Harness." }, "price_history": [ { "date": "2026-08-07", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "antgroup/ring-2.6-1t:free", "model_name": "ring-2.6-1t:free", "display_name": "Ring-2.6-1T", "vendor": "antgroup", "pricing": [ { "provider": "antgroup", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.661765" }, "completion": { "unit": "per_M_tokens", "price": "2.647059" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "Ring-2.6-1T" } ], "released_at": "2026-05-15", "max_input_tokens": 262144, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "pdf_input": true, "prompt_caching": true, "open_weights": true }, "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "ring", "knowledge_cutoff": "2025-12", "deprecated": true, "status": "deprecated", "benchmarks": { "intelligence_index": null, "coding_index": 42.8, "agentic_index": null }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Ring-2.6-1T", "inclusionai/ring-2.6-1t", "inclusionai/ring-2.6-1t:free", "novita/inclusionai/ring-2.6-1t", "ring-2.6-1t-free" ], "intro_i18n": { "zh-CN": "Ring-2.6-1T是一个万亿参数规模的推理模型，每次推理激活约630亿参数。专为代理工作流设计，重点关注代理能力、工具使用和长时间任务执行，在PinchBench、ClawEval、TAU2-Bench和GAIA2-search等基准测试中表现领先。模型在执行质量、延迟和成本方面进行了优化，非常适合高级编程代理、复杂推理管道和大规模自主系统。", "zh-TW": "Ring-2.6-1T 是一個擁有萬億參數規模的推理模型，每次推理激活約 630 億參數。專為代理工作流程設計，專注於代理能力、工具使用和長期任務執行，在 PinchBench、ClawEval、TAU2-Bench 和 GAIA2-search 等基準測試中達到領先性能。該模型在執行質量、延遲和成本方面進行了優化，非常適合高級編程代理、複雜推理管道和大規模自主系統。", "ja-JP": "Ring-2.6-1Tは、推論モデルのトリリオンパラメータ規模で、推論ごとに約63Bのパラメータを活性化します。エージェントワークフロー向けに設計されており、エージェント能力、ツール使用、長期タスク実行に焦点を当てています。PinchBench、ClawEval、TAU2-Bench、GAIA2-searchなどのベンチマークで最高の性能を達成しています。実行品質、レイテンシ、コストの最適化が行われており、高度なコーディングエージェント、複雑な推論パイプライン、大規模な自律システムに適しています。", "ru-RU": "Ring-2.6-1T — это модель для рассуждений масштаба триллиона параметров, активирующая около 63 миллиардов параметров на один вывод. Разработана для рабочих процессов агентов, с акцентом на возможности агентов, использование инструментов и выполнение задач на длинных горизонтах, достигая ведущих результатов на таких эталонах, как PinchBench, ClawEval, TAU2-Bench и GAIA2-search. Модель оптимизирована по качеству выполнения, задержке и стоимости, что делает её подходящей для продвинутых агентов программирования, сложных конвейеров рассуждений и крупномасштабных автономных систем." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Ring-2.6-1T" } ] }, { "slug": "anthropic/claude-2", "model_name": "claude-2", "display_name": "claude-2", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "8" }, "completion": { "unit": "per_M_tokens", "price": "24" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Claude 2 is Anthropic's previous generation model, offering reliable performance for various tasks. This includes Claude 2.0 and Claude 2.1.\n", "max_input_tokens": 200000, "capabilities": { "function_calling": true }, "max_output_tokens": 8191, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic/claude-2" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "claude-2" } ] }, { "slug": "anthropic/claude-2.1", "model_name": "claude-2.1", "display_name": "Claude 2.1", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "8" }, "completion": { "unit": "per_M_tokens", "price": "24" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "capabilities": {}, "released_at": "2023-11-21", "knowledge_cutoff": "2023", "max_input_tokens": 200000, "max_output_tokens": 4096, "model_type": "text_generation", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "intro_i18n": { "zh-CN": "Claude 2 提供关键的企业级改进，包括领先的 20 万 token 上下文窗口、减少幻觉、系统提示支持，以及新测试功能：工具调用。", "zh-TW": "Claude 2 提供企業級關鍵改進，包括領先的 20 萬 token 上下文、降低幻覺、系統提示與新測試功能：工具調用。", "ja-JP": "Claude 2は、200Kトークンのコンテキスト、幻覚の削減、システムプロンプト、ツール呼び出しの新機能など、エンタープライズ向けの主要な改善を提供します。", "ru-RU": "Claude 2 предлагает ключевые улучшения для бизнеса, включая контекст до 200 тысяч токенов, снижение галлюцинаций, системные подсказки и новую функцию тестирования — вызов инструментов." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Claude 2.1" } ] }, { "slug": "anthropic/claude-3-5-haiku", "model_name": "claude-3-5-haiku", "display_name": "Claude 3.5 Haiku", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "truefoundry+helicone-registry+computeprices+portkey+llmdb+llm-prices-www", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.08" }, "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "4" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "helicone-registry", "web_search": "helicone-registry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry+helicone-registry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "helicone-registry", "web_search": "helicone-registry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "computeprices", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "prompt from computeprices conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "computeprices", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "completion from computeprices conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "computeprices", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.08" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "cache_read from computeprices conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "computeprices", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "batch prompt from computeprices conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "computeprices", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "batch completion from computeprices conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "claude-3-5-haiku-20241022", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_output_tokens": 8192, "modalities": { "input": [ "image", "pdf" ], "output": [] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "assistant_prefill": true, "vision": true, "pdf_input": true, "web_search": true, "stream": true, "reasoning": true }, "intro": "Our fastest model. Intelligence at blazing speeds. Multilingual and vision capabilities. 8,192 max output tokens. Training data cut-off: July 2024. API model name: claude-3-5-haiku-20241022", "knowledge_cutoff": "2024-10", "max_input_tokens": 200000, "parameters": { "supported": [ "max_tokens", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "family": "Haiku", "released_at": "2024-10-22", "deprecated": true, "status": "deprecated", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-3-5-haiku-20241022-v1:0", "anthropic/claude-3-5-haiku", "anthropic/claude-3-5-haiku-20241022", "anthropic/claude-3-5-haiku@20241022", "anthropic/claude-3.5-haiku", "claude-3-5-haiku-20241022", "claude-3-5-haiku@20241022", "claude-3.5-haiku", "claude-3.5-haiku-20241022", "eu.anthropic.claude-3-5-haiku-20241022-v1:0", "us.anthropic.claude-3-5-haiku-20241022-v1:0" ], "intro_i18n": { "zh-CN": "Claude 3.5 Haiku 提升了速度、编程准确性和工具使用能力，适用于对速度和工具交互要求较高的场景。", "zh-TW": "Claude 3.5 Haiku 提升了速度、程式碼準確性與工具使用能力，適用於對速度與工具互動有高要求的場景。", "ja-JP": "Claude 3.5 Haiku は、速度、コーディング精度、ツール使用の性能が強化されており、速度とツール連携が求められるシナリオに適しています。", "ru-RU": "Claude 3.5 Haiku отличается повышенной скоростью, точностью программирования и эффективным использованием инструментов, подходит для сценариев с высокими требованиями к скорости и взаимодействию с инструментами." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Claude 3.5 Haiku" } ] }, { "slug": "anthropic/claude-3-5-haiku-latest", "model_name": "claude-3-5-haiku-latest", "display_name": "claude-3-5-haiku-latest", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.08" }, "cache_write": { "unit": "per_M_tokens", "price": "1" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1.6" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "portkey" }, "verification_status": "cross_checked" } } ], "intro": "Fastest, most cost-effective model", "max_input_tokens": 200000, "capabilities": { "vision": true, "function_calling": true, "pdf_input": true }, "released_at": "2024-10-22", "knowledge_cutoff": "2024-07", "max_output_tokens": 8192, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "claude-haiku", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "intro_i18n": { "zh-CN": "Claude 3.5 Haiku 提供快速响应，适用于轻量级任务。", "zh-TW": "Claude 3.5 Haiku 提供快速回應，適用於輕量任務。", "ja-JP": "Claude 3.5 Haikuは、軽量タスク向けに高速な応答を提供します。", "ru-RU": "Claude 3.5 Haiku обеспечивает быстрые ответы для легких задач." }, "model_type": "vision_understanding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "claude-3-5-haiku-latest" } ] }, { "slug": "anthropic/claude-3-5-sonnet", "model_name": "claude-3-5-sonnet", "display_name": "Claude 3.5 Sonnet v2", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" }, "cache_write": { "unit": "per_M_tokens", "price": "3.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "helicone-registry", "web_search": "helicone-registry" }, "tracks": [ { "label": "Batch", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } }, { "label": "Base pricing", "source": "pydantic-prices+helicone-registry", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "helicone-registry", "web_search": "helicone-registry" } } ], "verification_status": "cross_checked" }, "provider_model_id": "claude-3-5-sonnet-20240620", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Claude 3.5 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.", "max_input_tokens": 200000, "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "assistant_prefill": true, "vision": true, "pdf_input": true, "web_search": true, "stream": true, "reasoning": true, "computer_use": true }, "max_output_tokens": 8192, "modalities": { "input": [ "image", "pdf" ], "output": [] }, "model_type": "vision_understanding", "knowledge_cutoff": "2024-10", "parameters": { "supported": [ "max_tokens", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "family": "Sonnet", "released_at": "2024-06-20", "deprecated": true, "deprecation_date": "2026-07-30", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-3-5-sonnet-20240620-v1:0", "anthropic.claude-3-5-sonnet-20241022-v2:0", "anthropic/claude-3-5-sonnet", "anthropic/claude-3-5-sonnet@20240620", "anthropic/claude-3.5-sonnet", "anthropic/claude-3.5-sonnet-20240620", "apac.anthropic.claude-3-5-sonnet-20240620-v1:0", "apac.anthropic.claude-3-5-sonnet-20241022-v2:0", "claude-3-5-sonnet-20240620", "claude-3-5-sonnet-20241022", "claude-3-5-sonnet@20240620", "claude-3-5-sonnet@20241022", "claude-3.5-sonnet", "eu.anthropic.claude-3-5-sonnet-20240620-v1:0", "eu.anthropic.claude-3-5-sonnet-20241022-v2:0", "us-gov.anthropic.claude-3-5-sonnet-20240620-v1:0", "us.anthropic.claude-3-5-sonnet-20240620-v1:0", "us.anthropic.claude-3-5-sonnet-20241022-v2:0" ], "intro_i18n": { "zh-CN": "Claude 3.5 Sonnet 提升了行业标准，在广泛评估中超越竞争对手和 Claude 3 Opus，同时保持中等速度和成本。", "zh-TW": "Claude 3.5 Sonnet 提升了業界標準，在多項評估中超越競爭對手與 Claude 3 Opus，同時維持中階速度與成本。", "ja-JP": "Claude 3.5 Sonnet は業界標準を引き上げ、幅広い評価において競合他社や Claude 3 Opus を上回る性能を発揮しながら、中程度の速度とコストを維持します。", "ru-RU": "Claude 3.5 Sonnet поднимает отраслевой стандарт, превосходя конкурентов и Claude 3 Opus по широкому спектру оценок, сохраняя при этом средний уровень скорости и стоимости." }, "price_history": [ { "date": "2026-07-05", "kind": "listed", "note": "Claude 3.5 Sonnet v2" } ] }, { "slug": "anthropic/claude-3-5-sonnet-latest", "model_name": "claude-3-5-sonnet-latest", "display_name": "claude-3-5-sonnet-latest", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "truefoundry+portkey", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "3.75" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "portkey" }, "verification_status": "cross_checked" } } ], "max_output_tokens": 8192, "modalities": { "input": [ "image", "pdf" ], "output": [] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "assistant_prefill": true, "vision": true, "pdf_input": true }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "claude-3-5-sonnet-latest" } ] }, { "slug": "anthropic/claude-3-7-sonnet-20250219", "model_name": "claude-3-7-sonnet-20250219", "display_name": "claude-3-7-sonnet-20250219", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "litellm+helicone-registry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" }, "cache_write": { "unit": "per_M_tokens", "price": "3.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "provider_model_id": "claude-3.7-sonnet", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 200000, "max_output_tokens": 64000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-02-19", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "web_search": true, "assistant_prefill": true, "stream": true }, "intro": "High-performance model with toggleable extended thinking for complex reasoning tasks. Combines high intelligence with the ability to think through problems step-by-step. Fast latency with 64,000 max output tokens. API model name: claude-3-7-sonnet-20250219", "knowledge_cutoff": "2025-02", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "parameters": { "supported": [ "max_tokens", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "released_at": "2025-02-19", "family": "claude-sonnet", "status": "deprecated", "reasoning_config": { "budget_min": 1024 }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-3-7-sonnet-20240620-v1:0", "anthropic.claude-3-7-sonnet-20250219-v1:0", "anthropic/claude-3-7-sonnet", "anthropic/claude-3-7-sonnet-20250219", "anthropic/claude-3-7-sonnet@20250219", "anthropic/claude-3.7-sonnet", "anthropic/claude-3.7-sonnet:thinking", "apac.anthropic.claude-3-7-sonnet-20250219-v1:0", "claude-3-7-sonnet", "claude-3-7-sonnet@20250219", "claude-3.7-sonnet", "claude-3.7-sonnet:thinking", "eu.anthropic.claude-3-7-sonnet-20250219-v1:0", "us-gov.anthropic.claude-3-7-sonnet-20250219-v1:0", "us.anthropic.claude-3-7-sonnet-20250219-v1:0" ], "intro_i18n": { "zh-CN": "Claude 3.7 Sonnet 是升级版 Sonnet 模型，具备更强的推理和编程能力，适用于企业级复杂任务。", "zh-TW": "Claude 3.7 Sonnet 是升級版的 Sonnet 模型，具備更強的推理與程式能力，適用於企業級複雜任務。", "ja-JP": "Claude 3.7 Sonnet は、推論力とコーディング能力が強化された Sonnet モデルのアップグレード版で、企業レベルの複雑なタスクに適しています。", "ru-RU": "Claude 3.7 Sonnet — обновленная модель Sonnet с улучшенными логическими и программными возможностями, подходящая для сложных корпоративных задач." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "anthropic/claude-3-7-sonnet-latest", "model_name": "claude-3-7-sonnet-latest", "display_name": "Claude Sonnet 3.7", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "pydantic-prices+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" }, "cache_write": { "unit": "per_M_tokens", "price": "3.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "pydantic-prices+portkey", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Claude 3.7 Sonnet is an advanced large language model with improved reasoning, coding, and problem-solving capabilities.", "max_input_tokens": 200000, "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "assistant_prefill": true, "vision": true, "pdf_input": true, "reasoning": true, "stream": true }, "max_output_tokens": 64000, "modalities": { "input": [ "image", "pdf" ], "output": [] }, "model_type": "vision_understanding", "released_at": "2025-02-19", "knowledge_cutoff": "2024-10", "family": "claude-sonnet", "deprecated": true, "parameters": { "supported": [ "max_tokens", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic/claude-3-7-sonnet-latest" ], "intro_i18n": { "zh-CN": "Claude 3.7 Sonnet 是 Anthropic 最新、最强大的模型，适用于高度复杂的任务，在性能、智能、流畅性和理解力方面表现卓越。", "zh-TW": "Claude 3.7 Sonnet 是 Anthropic 最新且最強大的模型，適用於高度複雜任務，具備卓越的效能、智慧、流暢度與理解力。", "ja-JP": "Claude 3.7 Sonnetは、Anthropicの最新かつ最も高性能なモデルで、非常に複雑なタスクにおいて卓越した性能、知性、流暢さ、理解力を発揮します。", "ru-RU": "Claude 3.7 Sonnet — последняя и самая мощная модель от Anthropic для высокосложных задач, превосходящая по производительности, интеллекту, беглости и пониманию." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Claude 3.7 Sonnet" } ] }, { "slug": "anthropic/claude-3-haiku-20240307", "model_name": "claude-3-haiku-20240307", "display_name": "claude-3-haiku-20240307", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.3" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "cache_write_1h", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "cache_write_1h from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "cache_write_1h", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "cache_write_1h from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "claude-3-haiku", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 200000, "max_output_tokens": 4096, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-04-20", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "stream": true }, "intro": "Fastest, most cost-effective model", "modalities": { "input": [ "image" ], "output": [] }, "knowledge_cutoff": "2024-03", "parameters": { "supported": [ "max_tokens", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "released_at": "2024-03-13", "family": "claude-haiku", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-3-haiku-20240307-v1:0", "anthropic/claude-3-haiku", "anthropic/claude-3-haiku-20240307", "anthropic/claude-3-haiku@20240307", "apac.anthropic.claude-3-haiku-20240307-v1:0", "claude-3-haiku", "claude-3-haiku-20240229", "claude-3-haiku@20240307", "eu.anthropic.claude-3-haiku-20240307-v1:0", "us-gov.anthropic.claude-3-haiku-20240307-v1:0", "us.anthropic.claude-3-haiku-20240307-v1:0" ], "intro_i18n": { "zh-CN": "Claude 3 Haiku 是 Anthropic 迄今最快、最紧凑的模型，能为简单查询提供近乎即时的响应。它支持图像输入，具备 200K 上下文窗口，带来流畅自然的 AI 交互体验。", "zh-TW": "Claude 3 Haiku 是 Anthropic 速度最快、體積最小的模型，能即時回應簡單查詢，提供流暢自然的 AI 體驗，並支援圖像輸入與 200K 的上下文視窗。", "ja-JP": "Claude 3 Haiku は Anthropic の中で最も高速かつコンパクトなモデルで、シンプルな質問に対してほぼ即時の応答を提供します。人間らしい自然な AI 体験を実現し、200K のコンテキストウィンドウで画像入力にも対応しています。", "ru-RU": "Claude 3 Haiku — самая быстрая и компактная модель от Anthropic, обеспечивающая почти мгновенные ответы на простые запросы. Обеспечивает плавное, человекоподобное взаимодействие с ИИ и поддерживает ввод изображений с контекстом до 200 тысяч токенов." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "anthropic/claude-3-opus-20240229", "model_name": "claude-3-opus-20240229", "display_name": "claude-3-opus-20240229", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "litellm+truefoundry+computeprices+portkey+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "75" }, "cache_read": { "unit": "per_M_tokens", "price": "1.5" }, "cache_write": { "unit": "per_M_tokens", "price": "18.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "computeprices", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from computeprices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "computeprices", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "75" }, "discarded_charge": { "unit": "per_M_tokens", "price": "25" }, "message": "completion from computeprices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "computeprices", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "cache_read from computeprices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "cache_write_1h", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "30" }, "message": "cache_write_1h from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "computeprices", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "7.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "batch prompt from computeprices conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "computeprices", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "37.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12.5" }, "message": "batch completion from computeprices conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "claude-3-opus", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 200000, "max_output_tokens": 4096, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-01-05", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "stream": true }, "modalities": { "input": [ "image" ], "output": [] }, "knowledge_cutoff": "2023-08", "family": "Opus", "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "released_at": "2024-03-04", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-3-opus-20240229-v1:0", "anthropic/claude-3-opus", "anthropic/claude-3-opus@20240229", "claude-3-opus", "claude-3-opus@20240229", "eu.anthropic.claude-3-opus-20240229-v1:0", "us.anthropic.claude-3-opus-20240229-v1:0" ], "intro_i18n": { "zh-CN": "Claude 3 Opus 是 Anthropic 最强大的 AI 模型，在处理高度复杂任务方面表现卓越。它能流畅应对开放式提示和新颖场景，具备类人理解能力，并支持图像输入和 200K 上下文窗口。", "zh-TW": "Claude 3 Opus 是 Anthropic 最強大的 AI 模型，在處理高度複雜任務時展現最先進的效能，具備開放式提示與新穎情境的流暢應對能力，並支援圖像輸入與 200K 的上下文視窗。", "ja-JP": "Claude 3 Opus は Anthropic の中で最も高性能な AI モデルで、非常に複雑なタスクにおいて最先端のパフォーマンスを発揮します。自由形式のプロンプトや新しいシナリオにも高度な流暢さと人間のような理解力で対応し、200K のコンテキストウィンドウで画像入力にも対応しています。", "ru-RU": "Claude 3 Opus — самая мощная модель от Anthropic с передовыми возможностями для сложных задач. Обеспечивает свободную генерацию и понимание новых сценариев, поддерживает ввод изображений и контекст до 200 тысяч токенов." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "anthropic/claude-3-opus-latest", "model_name": "claude-3-opus-latest", "display_name": "claude-3-opus-latest", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "pydantic-prices+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "75" }, "cache_read": { "unit": "per_M_tokens", "price": "1.5" }, "cache_write": { "unit": "per_M_tokens", "price": "18.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "30" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "pydantic-prices+portkey", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Claude 3 Opus was Anthropic's most powerful model for highly complex tasks. It boasts top-level performance, intelligence, fluency, and understanding.", "max_input_tokens": 200000, "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "assistant_prefill": true, "vision": true }, "max_output_tokens": 4096, "modalities": { "input": [ "image" ], "output": [] }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "claude-3-opus-latest" } ] }, { "slug": "anthropic/claude-3-sonnet", "model_name": "claude-3-sonnet", "display_name": "Claude Sonnet 3", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" }, "cache_write": { "unit": "per_M_tokens", "price": "3.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "portkey" }, "verification_status": "cross_checked" }, "provider_model_id": "claude-3-sonnet-20240229" } ], "intro": "Claude 3 Sonnet is an ideal balance of intelligence and speed for enterprise workloads. Maximum utility at a lower price, dependable, balanced for scaled deployments.", "max_input_tokens": 200000, "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "stream": true }, "max_output_tokens": 4096, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-07-30", "modalities": { "input": [ "image" ], "output": [] }, "released_at": "2024-03-04", "knowledge_cutoff": "2023-08", "family": "claude-sonnet", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-3-sonnet-20240229-v1:0", "anthropic/claude-3-sonnet", "anthropic/claude-3-sonnet@20240229", "apac.anthropic.claude-3-sonnet-20240229-v1:0", "claude-3-sonnet-20240229", "claude-3-sonnet@20240229", "eu.anthropic.claude-3-sonnet-20240229-v1:0", "us.anthropic.claude-3-sonnet-20240229-v1:0" ], "intro_i18n": { "zh-CN": "Claude 3 Sonnet 在智能与速度之间实现平衡，适用于企业级工作负载，具备高性价比。支持图像输入和 200K 上下文窗口，是大规模 AI 部署的可靠选择。", "zh-TW": "Claude 3 Sonnet 在智慧與速度之間取得平衡，適用於企業級工作負載，提供高性價比與可靠的大規模部署能力，並支援圖像輸入與 200K 的上下文視窗。", "ja-JP": "Claude 3 Sonnet は、企業向けのワークロードにおいて知性と速度のバランスを取り、低コストで高い価値を提供します。大規模な AI 導入における信頼性の高い主力モデルとして設計されており、200K のコンテキストウィンドウで画像入力にも対応しています。", "ru-RU": "Claude 3 Sonnet сочетает интеллект и скорость для корпоративных задач, предлагая высокую ценность при низкой стоимости. Надежен для масштабируемого внедрения ИИ и поддерживает ввод изображений с контекстом до 200 тысяч токенов." }, "price_history": [ { "date": "2026-07-05", "kind": "listed", "note": "Claude Sonnet 3" } ] }, { "slug": "anthropic/claude-4-opus-20250514", "model_name": "claude-4-opus-20250514", "display_name": "claude-4-opus-20250514", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "75" }, "cache_read": { "unit": "per_M_tokens", "price": "1.5" }, "cache_write": { "unit": "per_M_tokens", "price": "18.75" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "30" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "web_search": "litellm", "cache_write_1h": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "web_search": "litellm", "cache_write_1h": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-06-15", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "assistant_prefill": true, "parallel_function_calling": true, "stream": true }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "released_at": "2025-06-12", "knowledge_cutoff": "2025-03", "family": "claude-opus", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic/claude-4-opus", "claude-4-opus", "deepinfra/anthropic/claude-4-opus" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "anthropic/claude-4-sonnet-20250514", "model_name": "claude-4-sonnet-20250514", "display_name": "claude-4-sonnet-20250514", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" }, "cache_write": { "unit": "per_M_tokens", "price": "3.75" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "web_search": "litellm", "cache_write_1h": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >200K", "source": "litellm", "charge_sources": { "cache_write": "litellm", "cache_read": "litellm", "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "web_search": "litellm", "cache_write_1h": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "cache_write": "2", "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-06-15", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "web_search": true, "assistant_prefill": true }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "released_at": "2026-04-15", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic/claude-4-sonnet", "claude-4-sonnet", "deepinfra/anthropic/claude-4-sonnet" ], "price_history": [ { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "anthropic/claude-4.5-haiku", "model_name": "claude-4.5-haiku", "display_name": "Claude 4.5 Haiku", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "pdf_input": true, "stream": true }, "intro": "Fast Claude model for responsive assistance, classification, and lightweight agents", "released_at": "2025-10-16", "max_input_tokens": 200000, "max_output_tokens": 64000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "knowledge_cutoff": "2025-10", "family": "claude-haiku", "model_type": "vision_understanding", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "64000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "8192", "new": "64000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "8192", "new": "64000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "64000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "8192", "new": "64000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "64000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "8192", "new": "64000", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "64000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "64000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Claude 4.5 Haiku" } ] }, { "slug": "anthropic/claude-fable-5", "model_name": "claude-fable-5", "display_name": "Claude Fable 5", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "50" }, "cache_read": { "unit": "per_M_tokens", "price": "1" }, "cache_write": { "unit": "per_M_tokens", "price": "12.5" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "20" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "computeprices" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Claude model for creative writing, analysis, and controlled agent workflows", "released_at": "2026-06-07", "max_input_tokens": 1000000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "claude-fable", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "computer_use": true, "parallel_function_calling": true, "assistant_prefill": true, "web_search": true }, "model_type": "deep_thinking", "knowledge_cutoff": "2026-01", "status": "beta", "benchmarks": { "intelligence_index": 62.1, "coding_index": 76.5, "agentic_index": 56.6 }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-fable-5", "anthropic/claude-fable-5", "eu.anthropic.claude-fable-5", "global.anthropic.claude-fable-5", "global.anthropic.claude-fable-5-v1:0", "us.anthropic.claude-fable-5", "vertex/claude-fable-5" ], "intro_i18n": { "zh-CN": "Claude Fable 5 是 Anthropic 最强大的模型——超越 Opus 的新等级，专为最苛刻的推理、代理工作和编程任务而设计，价格高昂。", "zh-TW": "Claude Fable 5 是 Anthropic 最強大的模型——超越 Opus 的新層級，適用於最具挑戰性的推理、代理工作和編程，並以高端價格提供。", "ja-JP": "Claude Fable 5はAnthropicの最強モデルで、Opusを超える新たなレベルの推論、エージェント作業、コーディングを提供し、プレミアム価格で利用可能です。", "ru-RU": "Claude Fable 5 — самая мощная модель Anthropic, новый уровень выше Opus для самых сложных задач рассуждения, агентной работы и кодирования, предлагается по премиальной цене." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "35", "new": "96.7" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "7", "new": "19.34" }, { "date": "2026-07-28", "kind": "price", "provider": "xpersona", "charge": "completion", "old": "18", "new": "18.5" }, { "date": "2026-07-28", "kind": "price", "provider": "xpersona", "charge": "internal_reasoning", "old": "18", "new": "18.5" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-central-1", "charge": "cache_read", "old": "1.1", "new": "1" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-central-1", "charge": "completion", "old": "55", "new": "50" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-central-1", "charge": "prompt", "old": "11", "new": "10" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-central-2", "charge": "cache_read", "old": "1.1", "new": "1" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-central-2", "charge": "completion", "old": "55", "new": "50" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-central-2", "charge": "prompt", "old": "11", "new": "10" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-north-1", "charge": "cache_read", "old": "1.1", "new": "1" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-north-1", "charge": "completion", "old": "55", "new": "50" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-north-1", "charge": "prompt", "old": "11", "new": "10" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-south-1", "charge": "cache_read", "old": "1.1", "new": "1" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-south-1", "charge": "completion", "old": "55", "new": "50" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-south-1", "charge": "prompt", "old": "11", "new": "10" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-south-2", "charge": "cache_read", "old": "1.1", "new": "1" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-south-2", "charge": "completion", "old": "55", "new": "50" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-south-2", "charge": "prompt", "old": "11", "new": "10" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@eu-west-1", "charge": "cache_read", "old": "1.1", "new": "1" } ] }, { "slug": "anthropic/claude-haiku-4-5", "model_name": "claude-haiku-4-5", "display_name": "Claude Haiku 4.5", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.1" }, "cache_write": { "unit": "per_M_tokens", "price": "1.25" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "2" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "helicone-registry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "computeprices" } }, { "label": "Base pricing", "source": "models-dev+litellm+helicone-registry", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "helicone-registry" } } ], "verification_status": "cross_checked" }, "provider_model_id": "claude-haiku-4-5-20251001", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Fast Claude lane for lightweight agents, office tasks, and responsive chat", "released_at": "2025-10-15", "knowledge_cutoff": "2025-02", "max_input_tokens": 200000, "max_output_tokens": 64000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "claude-haiku", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "assistant_prefill": true, "parallel_function_calling": true, "web_search": true, "stream": true }, "model_type": "deep_thinking", "parameters": { "supported": [ "max_tokens", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/haiku-4-5", "deprecation_date": "2026-10-15", "benchmarks": { "intelligence_index": 29.9, "coding_index": 43.9, "agentic_index": 16.5 }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-haiku-4-5", "anthropic.claude-haiku-4-5-20251001-v1:0", "anthropic.claude-haiku-4-5@20251001", "anthropic/claude-haiku-4-5", "anthropic/claude-haiku-4-5-20251001", "anthropic/claude-haiku-4-5@20251001", "anthropic/claude-haiku-4.5", "anthropic/claude-haiku-4.5-20251001", "apac.anthropic.claude-haiku-4-5-20251001-v1:0", "au.anthropic.claude-haiku-4-5-20251001-v1:0", "bedrock/claude-haiku-4-5", "claude-haiku-4-5-20251001", "claude-haiku-4-5@20251001", "claude-haiku-4.5", "eu.anthropic.claude-haiku-4-5-20251001-v1:0", "global.anthropic.claude-haiku-4-5-20251001-v1:0", "jp.anthropic.claude-haiku-4-5-20251001-v1:0", "pa/claude-haiku-4-5-20251001", "us.anthropic.claude-haiku-4-5-20251001-v1:0", "vertex/claude-haiku-4-5", "vertexanthropic/claude-haiku-4-5" ], "intro_i18n": { "zh-CN": "Claude Haiku 4.5 是 Anthropic 的高性能快速模型，在保持高准确率的同时实现极低延迟。", "zh-TW": "Claude Haiku 4.5 是 Anthropic 的高效能快速模型，在保持高準確度的同時提供極低延遲。", "ja-JP": "Claude Haiku 4.5 は Anthropic の高性能高速モデルで、非常に低いレイテンシを維持しながら高い精度を実現します。", "ru-RU": "Claude Haiku 4.5 — высокопроизводительная быстрая модель от Anthropic с очень низкой задержкой и высокой точностью." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "anthropic/claude-mythos-5", "model_name": "claude-mythos-5", "display_name": "claude-mythos-5", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "litellm+computeprices+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "50" }, "cache_read": { "unit": "per_M_tokens", "price": "1" }, "cache_write": { "unit": "per_M_tokens", "price": "12.5" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "20" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://docs.claude.com/en/docs/about-claude/models/overview", "max_input_tokens": 1000000, "max_output_tokens": 128000, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true }, "family": "Mythos", "intro": "Restricted Claude model for advanced cybersecurity and biology research workflows", "released_at": "2026-06-09", "knowledge_cutoff": "2026-01", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "status": "beta", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "price_history": [ { "date": "2026-08-12", "kind": "capability", "note": "computer_use: false→true" }, { "date": "2026-08-11", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-08-11", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-08-11", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-11", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-08-11", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-08-11", "kind": "limit", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Claude Mythos 5" } ] }, { "slug": "anthropic/claude-mythos-preview", "model_name": "claude-mythos-preview", "display_name": "claude-mythos-preview", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "50" }, "cache_read": { "unit": "per_M_tokens", "price": "1" }, "cache_write": { "unit": "per_M_tokens", "price": "12.5" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "20" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://docs.claude.com/en/docs/about-claude/models/overview", "max_input_tokens": 1000000, "max_output_tokens": 128000, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-mythos-preview" ], "price_history": [ { "date": "2026-08-12", "kind": "listed", "note": "claude-mythos-preview" } ] }, { "slug": "anthropic/claude-opus-4-0", "model_name": "claude-opus-4-0", "display_name": "claude-opus-4-0", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "75" }, "cache_read": { "unit": "per_M_tokens", "price": "1.5" }, "cache_write": { "unit": "per_M_tokens", "price": "18.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "30" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "pydantic-prices+portkey", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Most intelligent model for complex tasks", "max_input_tokens": 200000, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-05", "kind": "capability", "note": "vision: true→false" }, { "date": "2026-07-05", "kind": "capability", "note": "function_calling: true→false" }, { "date": "2026-07-05", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-05", "kind": "capability", "note": "prompt_caching: true→false" }, { "date": "2026-07-05", "kind": "capability", "note": "pdf_input: true→false" } ] }, { "slug": "anthropic/claude-opus-4-1", "model_name": "claude-opus-4-1", "display_name": "claude-opus-4-1", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "75" }, "cache_read": { "unit": "per_M_tokens", "price": "1.5" }, "cache_write": { "unit": "per_M_tokens", "price": "18.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "30" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "provider_model_id": "claude-opus-4-1-20250805", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-08-05", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "web_search": true, "assistant_prefill": true, "parallel_function_calling": true, "stream": true }, "intro": "Most intelligent model for complex tasks", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "knowledge_cutoff": "2025-08", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools" ] }, "family": "Opus", "released_at": "2025-08-05", "status": "deprecated", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-opus-4-1-20250805-v1:0", "anthropic/claude-opus-4-1", "anthropic/claude-opus-4-1-20250805", "anthropic/claude-opus-4-1@20250805", "anthropic/claude-opus-4.1", "anthropic/claude-opus-4.1-20250805", "claude-opus-4-1-20250805", "claude-opus-4-1@20250805", "claude-opus-4.1", "eu.anthropic.claude-opus-4-1-20250805-v1:0", "pa/claude-opus-4-1-20250805", "us.anthropic.claude-opus-4-1-20250805-v1:0", "vertex/claude-opus-4-1", "vertexanthropic/claude-opus-4-1" ], "intro_i18n": { "zh-CN": "Opus 4.1 是 Anthropic 的高端模型，专为编程、复杂推理和长时间任务优化。", "zh-TW": "Opus 4.1 是 Anthropic 的高階模型，針對程式設計、複雜推理與長時間任務進行最佳化。", "ja-JP": "Opus 4.1 は、プログラミング、複雑な推論、長時間タスクに最適化された Anthropic のハイエンドモデルです。", "ru-RU": "Opus 4.1 — флагманская модель от Anthropic, оптимизированная для программирования, сложной логики и длительных задач." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "anthropic/claude-opus-4-20250514", "model_name": "claude-opus-4-20250514", "display_name": "claude-opus-4-20250514", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "litellm+truefoundry+helicone-registry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "75" }, "cache_read": { "unit": "per_M_tokens", "price": "1.5" }, "cache_write": { "unit": "per_M_tokens", "price": "18.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "30" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "provider_model_id": "claude-opus-4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 200000, "max_output_tokens": 32000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-06-15", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "web_search": true, "assistant_prefill": true, "stream": true }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "intro": "Our previous flagship model with very high intelligence and capability. Supports extended thinking, multilingual capabilities, and vision processing. Moderately fast latency with 32,000 max output tokens. Training data cut-off: March 2025. API model name: claude-opus-4-20250514", "knowledge_cutoff": "2025-05", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools" ] }, "released_at": "2025-05-22", "family": "claude-opus", "status": "deprecated", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-opus-4-20250514-v1:0", "anthropic/claude-opus-4", "anthropic/claude-opus-4-20250514", "anthropic/claude-opus-4@20250514", "claude-opus-4", "claude-opus-4@20250514", "eu.anthropic.claude-opus-4-20250514-v1:0", "us.anthropic.claude-opus-4-20250514-v1:0", "vertex/claude-opus-4", "vertexanthropic/claude-opus-4" ], "intro_i18n": { "zh-CN": "Opus 4 是 Anthropic 的旗舰模型，专为复杂任务和企业应用设计。", "zh-TW": "Opus 4 是 Anthropic 為複雜任務與企業應用設計的旗艦模型。", "ja-JP": "Opus 4 は、複雑なタスクや企業向けアプリケーションに対応するために設計された Anthropic のフラッグシップモデルです。", "ru-RU": "Opus 4 — флагманская модель от Anthropic, предназначенная для сложных задач и корпоративных приложений." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "anthropic/claude-opus-4-5", "model_name": "claude-opus-4-5", "display_name": "Claude Opus 4.5", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "cache_write": { "unit": "per_M_tokens", "price": "6.25" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "10" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "provider_model_id": "claude-opus-4-5-20251101", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Flagship Claude model for deep reasoning, coding, and long-horizon agents", "released_at": "2025-11-24", "knowledge_cutoff": "2025-05", "max_input_tokens": 200000, "max_output_tokens": 64000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "claude-opus", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "assistant_prefill": true, "web_search": true, "stream": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools" ] }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-opus-4-5-20251101-v1:0", "anthropic/claude-opus-4-5", "anthropic/claude-opus-4-5-20251101", "anthropic/claude-opus-4-5@20251101", "anthropic/claude-opus-4.5", "anthropic/claude-opus-4.5-20251101", "bedrock/claude-opus-4-5", "claude-opus-4-5-20251101", "claude-opus-4-5-20251101:thinking", "claude-opus-4-5@20251101", "claude-opus-4.5", "eu.anthropic.claude-opus-4-5-20251101-v1:0", "global.anthropic.claude-opus-4-5-20251101-v1:0", "global.anthropic.claude-opus-4-5-v1:0", "pa/claude-opus-4-5-20251101", "us.anthropic.claude-opus-4-5-20251101-v1:0", "vertex/claude-opus-4-5", "vertexanthropic/claude-opus-4-5" ], "intro_i18n": { "zh-CN": "Claude Opus 4.5 是 Anthropic 的旗舰模型，结合顶级智能与可扩展性能，适用于复杂、高质量推理任务。", "zh-TW": "Claude Opus 4.5 是 Anthropic 的旗艦模型，結合頂尖智慧與可擴展效能，適用於複雜且高品質的推理任務。", "ja-JP": "Claude Opus 4.5 は Anthropic のフラッグシップモデルで、最高レベルの知性とスケーラブルな性能を兼ね備え、複雑で高品質な推論タスクに最適です。", "ru-RU": "Claude Opus 4.5 — флагманская модель от Anthropic, сочетающая высший интеллект с масштабируемой производительностью для сложных задач, требующих качественного логического вывода." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" } ] }, { "slug": "anthropic/claude-opus-4-6", "model_name": "claude-opus-4-6", "display_name": "Claude Opus 4.6", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "cache_write": { "unit": "per_M_tokens", "price": "6.25" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "10" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "provider_model_id": "claude-opus-4-6-20260205", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "High-end Claude for difficult coding, planning, and slower expert reasoning", "released_at": "2026-02-04", "knowledge_cutoff": "2025-05", "max_input_tokens": 1000000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "claude-opus", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "parallel_function_calling": true, "assistant_prefill": true, "web_search": true, "stream": true }, "model_type": "deep_thinking", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools" ] }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-opus-4-6", "anthropic.claude-opus-4-6-20260205-v1:0", "anthropic.claude-opus-4-6-v1:0", "anthropic/claude-opus-4-6", "anthropic/claude-opus-4.6", "anthropic/claude-opus-4.6:thinking", "bedrock/claude-opus-4-6", "claude-opus-4-6-20260205", "claude-opus-4-6@20260205", "claude-opus-4.6", "eu.anthropic.claude-opus-4-6-v1:0", "global.anthropic.claude-opus-4-6-v1:0", "pa/claude-opus-4-6", "stealth/claude-opus-4.6", "us.anthropic.claude-opus-4-6-v1:0", "vertex/claude-opus-4-6", "vertexanthropic/claude-opus-4-6" ], "intro_i18n": { "zh-CN": "Anthropic 的 Claude Opus 4.6 —— 具备 100 万上下文窗口的旗舰模型，拥有先进推理能力。", "zh-TW": "Anthropic 的 Claude Opus 4.6 —— 支援 100 萬上下文的旗艦模型，擁有先進推理能力。", "ja-JP": "Claude Opus 4.6 by Anthropic — 1Mコンテキストウィンドウを備えたフラッグシップモデルで、高度な推論能力を提供します。", "ru-RU": "Claude Opus 4.6 от Anthropic — флагманская модель с контекстом 1M и усовершенствованными возможностями рассуждения." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "anthropic/claude-opus-4-7", "model_name": "claude-opus-4-7", "display_name": "Claude Opus 4.7", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "cache_write": { "unit": "per_M_tokens", "price": "6.25" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "10" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "provider_model_id": "claude-opus-4-7-20260416", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Stronger Opus tier for advanced software work and high-stakes reasoning", "released_at": "2026-04-14", "knowledge_cutoff": "2026-01", "max_input_tokens": 1000000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "claude-opus", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "parallel_function_calling": true, "assistant_prefill": true, "web_search": true }, "model_type": "deep_thinking", "status": "beta", "benchmarks": { "intelligence_index": 55, "coding_index": 73.6, "agentic_index": 46.3 }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-opus-4-7", "anthropic/claude-opus-4-7", "anthropic/claude-opus-4.7", "anthropic/claude-opus-4.7:thinking", "au.anthropic.claude-opus-4-7", "bedrock/claude-opus-4-7", "claude-opus-4-7-20260416", "claude-opus-4.7", "eu.anthropic.claude-opus-4-7", "global.anthropic.claude-opus-4-7", "global.anthropic.claude-opus-4-7-v1:0", "jp.anthropic.claude-opus-4-7", "stealth/claude-opus-4.7", "us.anthropic.claude-opus-4-7", "vertex/claude-opus-4-7" ], "intro_i18n": { "zh-CN": "Anthropic 的 Claude Opus 4.7 —— 最新 Opus 模型，具备最先进的推理与编码表现。", "zh-TW": "Anthropic 的 Claude Opus 4.7 —— 最新 Opus 模型，具備最先進的推理與程式能力。", "ja-JP": "Claude Opus 4.7 by Anthropic — 最新のOpusモデルで、最先端の推論とコーディング能力を備えています。", "ru-RU": "Claude Opus 4.7 от Anthropic — последняя версия Opus с передовыми возможностями рассуждения и программирования." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "assistant_prefill: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "anthropic/claude-opus-4-8", "model_name": "claude-opus-4-8", "display_name": "Claude Opus 4.8", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "cache_write": { "unit": "per_M_tokens", "price": "6.25" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "10" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "computeprices" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents", "released_at": "2026-05-28", "knowledge_cutoff": "2026-01", "max_input_tokens": 1000000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "claude-opus", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "parallel_function_calling": true, "assistant_prefill": true, "web_search": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1 }, "benchmarks": { "intelligence_index": 57.3, "coding_index": 74.3, "agentic_index": 49.4 }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-opus-4-8", "anthropic/claude-opus-4-8", "anthropic/claude-opus-4.8", "anthropic/claude-opus-4.8:thinking", "au.anthropic.claude-opus-4-8", "bedrock/claude-opus-4-8", "claude-opus-4.8", "eu.anthropic.claude-opus-4-8", "global.anthropic.claude-opus-4-8", "global.anthropic.claude-opus-4-8-v1:0", "jp.anthropic.claude-opus-4-8", "stealth/claude-opus-4.8", "us-gov.anthropic.claude-opus-4-8", "us.anthropic.claude-opus-4-8", "vertex/claude-opus-4-8" ], "intro_i18n": { "zh-CN": "Claude Opus 4.8 是 Anthropic 的旗舰 Opus 模型，在 Opus 4.7 的基础上提升了推理、代理编程和工具使用能力。", "zh-TW": "Claude Opus 4.8 是 Anthropic 的旗艦 Opus 模型，基於 Opus 4.7 進行改進，提升了推理、代理編程和工具使用能力。", "ja-JP": "Claude Opus 4.8はAnthropicの主力Opusモデルで、Opus 4.7を基に推論、エージェントコーディング、ツール使用の面で改良されています。", "ru-RU": "Claude Opus 4.8 — флагманская модель Opus от Anthropic, основанная на Opus 4.7 с улучшениями в области рассуждений, агентного кодирования и использования инструментов." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "assistant_prefill: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "anthropic/claude-opus-5", "model_name": "claude-opus-5", "display_name": "Claude Opus 5", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "cache_write": { "unit": "per_M_tokens", "price": "6.25" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "10" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Strongest Claude Opus model for coding, agents, and professional work", "released_at": "2026-07-24", "knowledge_cutoff": "2026-05", "max_input_tokens": 1000000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "claude-opus", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "parallel_function_calling": true, "assistant_prefill": true, "web_search": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "benchmarks": { "intelligence_index": 63.1, "coding_index": 78, "agentic_index": 59.2 }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-opus-5", "anthropic/claude-opus-5", "au.anthropic.claude-opus-5", "bedrock/claude-opus-5", "eu.anthropic.claude-opus-5", "global.anthropic.claude-opus-5", "jp.anthropic.claude-opus-5", "us.anthropic.claude-opus-5", "vertex/claude-opus-5" ], "intro_i18n": { "zh-CN": "Claude Opus 5 是 Anthropic 最强大的 Opus 模型，专为深度推理、主动编码和长期专业工作而打造。", "zh-TW": "Claude Opus 5 是 Anthropic 最強大的 Opus 模型，專為深度推理、主動編程以及長期專業工作而打造。", "ja-JP": "Claude Opus 5は、深い推論、主体的なコーディング、長期的な専門的作業のために設計されたAnthropicの最強のOpusモデルです。", "ru-RU": "Claude Opus 5 — это самая мощная модель Opus от Anthropic, созданная для глубокого анализа, агентного программирования и долгосрочной профессиональной работы." }, "price_history": [ { "date": "2026-07-25", "kind": "listed", "note": "Claude Opus 5" } ] }, { "slug": "anthropic/claude-sonnet-4-0", "model_name": "claude-sonnet-4-0", "display_name": "claude-sonnet-4-0", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" }, "cache_write": { "unit": "per_M_tokens", "price": "3.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "pydantic-prices+portkey", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "cache_write": "pydantic-prices", "cache_write_1h": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Optimal balance of intelligence, cost, and speed", "max_input_tokens": 200000, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-05", "kind": "capability", "note": "vision: true→false" }, { "date": "2026-07-05", "kind": "capability", "note": "function_calling: true→false" }, { "date": "2026-07-05", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-05", "kind": "capability", "note": "prompt_caching: true→false" }, { "date": "2026-07-05", "kind": "capability", "note": "pdf_input: true→false" } ] }, { "slug": "anthropic/claude-sonnet-4-20250514", "model_name": "claude-sonnet-4-20250514", "display_name": "claude-sonnet-4-20250514", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "litellm+truefoundry+helicone-registry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" }, "cache_write": { "unit": "per_M_tokens", "price": "3.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >200K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_write": "litellm", "cache_read": "litellm" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "helicone-registry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "helicone-registry introduced a ≥200000 tier outside the litellm schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_write": "2", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "max_output_tokens": 64000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-06-15", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "web_search": true, "assistant_prefill": true, "stream": true }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "intro": "High-performance model with high intelligence and balanced performance. Supports extended thinking, multilingual capabilities, and vision processing. Fast latency with 64,000 max output tokens. API model name: claude-sonnet-4-20250514", "knowledge_cutoff": "2025-05", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools" ] }, "released_at": "2025-05-22", "family": "claude-sonnet", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "status": "deprecated", "benchmarks": { "intelligence_index": 29.8, "coding_index": 37.6, "agentic_index": 17.6 }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-sonnet-4-20250514-v1:0", "anthropic/claude-sonnet-4", "anthropic/claude-sonnet-4-20250514", "anthropic/claude-sonnet-4@20250514", "apac.anthropic.claude-sonnet-4-20250514-v1:0", "bedrock/claude-sonnet-4", "claude-sonnet-4", "claude-sonnet-4@20250514", "eu.anthropic.claude-sonnet-4-20250514-v1:0", "global.anthropic.claude-sonnet-4-20250514-v1:0", "us.anthropic.claude-sonnet-4-20250514-v1:0", "vertex/claude-sonnet-4", "vertexanthropic/claude-sonnet-4" ], "intro_i18n": { "zh-CN": "Claude Sonnet 4 是 Anthropic 的混合推理模型，具备思考与非思考能力的结合。", "zh-TW": "Claude Sonnet 4 是 Anthropic 的混合推理模型，具備思考與非思考能力的結合。", "ja-JP": "Claude Sonnet 4 は、思考と非思考の両方の能力を備えた Anthropic のハイブリッド推論モデルです。", "ru-RU": "Claude Sonnet 4 — гибридная модель логического вывода от Anthropic, сочетающая режимы мышления и немышления." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.18", "new": "0.16" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "8.31", "new": "32.3" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "1.65", "new": "6.46" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.06", "new": "0.18" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "3.21", "new": "8.31" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.63", "new": "1.65" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "cache_read", "old": "0.26", "new": "0.29" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "completion", "old": "16.536", "new": "14.493" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "prompt", "old": "3.307", "new": "2.898" }, { "date": "2026-08-03", "kind": "price", "provider": "nano-gpt", "charge": "completion", "old": "14.994", "new": "15" }, { "date": "2026-08-03", "kind": "price", "provider": "nano-gpt", "charge": "prompt", "old": "2.992", "new": "3" }, { "date": "2026-07-25", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.18", "new": "0.06" }, { "date": "2026-07-25", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "8.31", "new": "3.21" }, { "date": "2026-07-25", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "1.65", "new": "0.63" }, { "date": "2026-07-22", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "3.21", "new": "8.31" }, { "date": "2026-07-22", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.63", "new": "1.65" }, { "date": "2026-07-18", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.84", "new": "3.21" }, { "date": "2026-07-18", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.18", "new": "0.63" }, { "date": "2026-07-16", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.06", "new": "0.03" }, { "date": "2026-07-16", "kind": "price", "provider": "api-airforce", "charge": "cache_write", "old": "0.57", "new": "0.21" } ] }, { "slug": "anthropic/claude-sonnet-4-5", "model_name": "claude-sonnet-4-5", "display_name": "Claude Sonnet 4.5", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory+override", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" }, "cache_write": { "unit": "per_M_tokens", "price": "3.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Header anthropic-beta /context-1m-\\d{4}-\\d{2}-\\d{2}/ AND Context >200K", "source": "override", "charge_sources": { "prompt": "override", "completion": "override", "cache_read": "override", "cache_write": "override", "cache_write_1h": "override" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "pydantic-prices", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "pydantic-prices introduced a ≥200000 tier outside the litellm schedule; it was discarded." }, { "kind": "tier_schedule", "source": "helicone-registry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "helicone-registry introduced a ≥200000 tier outside the litellm schedule; it was discarded." }, { "kind": "tier_schedule", "source": "helicone-registry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "helicone-registry introduced a ≥200000 tier outside the litellm schedule; it was discarded." } ], "verification_status": "conflicting" }, "provider_model_id": "claude-sonnet-4-5-20250929", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Header anthropic-beta /context-1m-\\d{4}-\\d{2}-\\d{2}/ AND Context >200K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2", "cache_write_1h": "2" }, "triggers": [ { "kind": "header_matches", "header": "anthropic-beta", "pattern": "context-1m-\\d{4}-\\d{2}-\\d{2}" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "intro": "Balanced Claude model for coding, analysis, agent workflows, and cost control", "released_at": "2025-09-29", "knowledge_cutoff": "2025-07", "max_input_tokens": 1000000, "max_output_tokens": 64000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "claude-sonnet", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "assistant_prefill": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools" ] }, "benchmarks": { "intelligence_index": 37.4, "coding_index": 52.1, "agentic_index": 26.4 }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-sonnet-4-5-20250929-v1:0", "anthropic/claude-sonnet-4-5", "anthropic/claude-sonnet-4-5-20250929", "anthropic/claude-sonnet-4-5@20250929", "anthropic/claude-sonnet-4.5", "anthropic/claude-sonnet-4.5-20250929", "au.anthropic.claude-sonnet-4-5-20250929-v1:0", "bedrock/claude-sonnet-4-5", "claude-sonnet-4-5-20250929", "claude-sonnet-4-5-20250929-v1:0", "claude-sonnet-4-5@20250929", "claude-sonnet-4.5", "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", "global.anthropic.claude-sonnet-4-5-20250929-v1:0", "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", "pa/claude-sonnet-4-5-20250929", "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "vertex/claude-sonnet-4-5", "vertexanthropic/claude-sonnet-4-5" ], "intro_i18n": { "zh-CN": "Claude Sonnet 4.5 是 Anthropic 最新的混合推理模型，专为复杂推理和编程优化。", "zh-TW": "Claude Sonnet 4.5 是 Anthropic 最新的混合推理模型，針對複雜推理與程式設計進行最佳化。", "ja-JP": "Claude Sonnet 4.5 は、複雑な推論とコーディングに最適化された Anthropic の最新ハイブリッド推論モデルです。", "ru-RU": "Claude Sonnet 4.5 — новейшая гибридная модель логического вывода от Anthropic, оптимизированная для сложных рассуждений и программирования." }, "price_history": [ { "date": "2026-07-05", "kind": "limit", "old": "200000", "new": "1000000", "note": "max_input_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "anthropic/claude-sonnet-4-6", "model_name": "claude-sonnet-4-6", "display_name": "Claude Sonnet 4.6", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" }, "cache_write": { "unit": "per_M_tokens", "price": "3.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "6" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Claude workhorse for coding agents, careful analysis, and production cost control", "released_at": "2026-02-17", "knowledge_cutoff": "2025-08", "max_input_tokens": 1000000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "claude-sonnet", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "assistant_prefill": true, "parallel_function_calling": true, "web_search": true, "stream": true }, "model_type": "deep_thinking", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "stop", "temperature", "tool_choice", "tools" ] }, "docs_url": "https://openrouter.ai/anthropic/claude-sonnet-4.6", "benchmarks": { "intelligence_index": 48.4, "coding_index": 63, "agentic_index": 42.1 }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-sonnet-4-6", "anthropic.claude-sonnet-4-6-20260217-v1:0", "anthropic.claude-sonnet-4-6-v1:0", "anthropic/claude-sonnet-4-6", "anthropic/claude-sonnet-4.6", "anthropic/claude-sonnet-4.6:thinking", "au.anthropic.claude-sonnet-4-6", "bedrock/claude-sonnet-4-6", "claude-sonnet-4-6@20260217", "claude-sonnet-4.6", "eu.anthropic.claude-sonnet-4-6", "eu.anthropic.claude-sonnet-4-6-v1:0", "global.anthropic.claude-sonnet-4-6", "global.anthropic.claude-sonnet-4-6-v1:0", "jp.anthropic.claude-sonnet-4-6", "pa/claude-sonnet-4-6", "stealth/claude-sonnet-4.6", "us.anthropic.claude-sonnet-4-6", "us.anthropic.claude-sonnet-4-6-v1:0", "vertex/claude-sonnet-4-6", "vertexanthropic/claude-sonnet-4-6" ], "intro_i18n": { "zh-CN": "Anthropic 的 Claude Sonnet 4.6 —— 最新 Sonnet 模型，在编码与工具使用方面表现更强。", "zh-TW": "Anthropic 的 Claude Sonnet 4.6 —— 最新 Sonnet，具備更卓越的程式與工具使用能力。", "ja-JP": "Claude Sonnet 4.6 by Anthropic — 最新のSonnetモデルで、優れたコーディングとツール使用能力を備えています。", "ru-RU": "Claude Sonnet 4.6 от Anthropic — последняя версия Sonnet с превосходными возможностями в программировании и использовании инструментов." }, "price_history": [ { "date": "2026-07-05", "kind": "limit", "old": "64000", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "anthropic/claude-sonnet-5", "model_name": "claude-sonnet-5", "display_name": "Claude Sonnet 5", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "provider_name": "Anthropic", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "cache_write": { "unit": "per_M_tokens", "price": "2.5" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "4" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "computeprices" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_write_1h": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Everyday Claude agent model for coding, planning, browsing, and general work", "released_at": "2026-06-29", "knowledge_cutoff": "2026-01", "max_input_tokens": 1000000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "claude-sonnet", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "computer_use": true, "parallel_function_calling": true, "assistant_prefill": true, "web_search": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "status": "beta", "benchmarks": { "intelligence_index": 55.3, "coding_index": 71.5, "agentic_index": 49.7 }, "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-sonnet-5", "anthropic/claude-sonnet-5", "anthropic/claude-sonnet-5-free", "anthropic/claude-sonnet-5:thinking", "au.anthropic.claude-sonnet-5", "bedrock/claude-sonnet-5", "eu.anthropic.claude-sonnet-5", "global.anthropic.claude-sonnet-5", "global.anthropic.claude-sonnet-5-v1:0", "jp.anthropic.claude-sonnet-5", "us-gov.anthropic.claude-sonnet-5", "us.anthropic.claude-sonnet-5", "vertex/claude-sonnet-5" ], "intro_i18n": { "zh-CN": "Claude Sonnet 5 是 Anthropic 最具主动性的 Sonnet 模型，专为持续编码、工具使用和长上下文工作流程而设计，具有 Sonnet 级别的速度和效率。", "zh-TW": "Claude Sonnet 5 是 Anthropic 最具代理性的 Sonnet 模型，專為持續編碼、工具使用以及長上下文工作流程而設計，具備 Sonnet 級別的速度和效率。", "ja-JP": "Claude Sonnet 5は、Anthropicが開発した最も主体的なSonnetモデルで、持続的なコーディング、ツールの使用、長いコンテキストのワークフローに対応し、Sonnetクラスの速度と効率を備えています。", "ru-RU": "Claude Sonnet 5 — это самая агентная модель Sonnet от Anthropic, созданная для устойчивого кодирования, использования инструментов и рабочих процессов с длинным контекстом, обеспечивая скорость и эффективность уровня Sonnet." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.17", "new": "0.1" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "cache_write", "old": "1.97", "new": "1.25" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "7.97", "new": "16.14" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "1.59", "new": "3.22" }, { "date": "2026-08-13", "kind": "price", "provider": "tokenrouter", "charge": "cache_write", "old": "2", "new": "2.5" }, { "date": "2026-08-11", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.16", "new": "0.17" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.17", "new": "0.16" }, { "date": "2026-08-05", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.17", "new": "0.18" }, { "date": "2026-08-05", "kind": "price", "provider": "api-airforce", "charge": "cache_write", "old": "1.97", "new": "2.22" }, { "date": "2026-08-05", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "7.97", "new": "8.91" }, { "date": "2026-08-05", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "1.59", "new": "1.77" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "cache_read", "old": "0.197", "new": "0.219" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "completion", "old": "9.874", "new": "11" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "prompt", "old": "1.975", "new": "2.2" }, { "date": "2026-07-28", "kind": "price", "provider": "amazon-bedrock@ap-southeast-2", "charge": "cache_read", "old": "0.2", "new": "0.22" }, { "date": "2026-07-28", "kind": "price", "provider": "amazon-bedrock@ap-southeast-2", "charge": "cache_write", "old": "2.5", "new": "2.75" }, { "date": "2026-07-28", "kind": "price", "provider": "amazon-bedrock@ap-southeast-2", "charge": "cache_write_1h", "old": "4", "new": "4.4" }, { "date": "2026-07-28", "kind": "price", "provider": "amazon-bedrock@ap-southeast-2", "charge": "completion", "old": "10", "new": "11" }, { "date": "2026-07-28", "kind": "price", "provider": "amazon-bedrock@ap-southeast-2", "charge": "prompt", "old": "2", "new": "2.2" }, { "date": "2026-07-27", "kind": "price", "provider": "amazon-bedrock@ap-southeast-4", "charge": "cache_read", "old": "0.2", "new": "0.22" } ] }, { "slug": "anthropic/claude-v1", "model_name": "claude-v1", "display_name": "claude-v1", "vendor": "anthropic", "pricing": [ { "provider": "anthropic", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "8" }, "completion": { "unit": "per_M_tokens", "price": "24" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Retired, here to match price sources", "capabilities": {}, "max_input_tokens": 100000, "max_output_tokens": 8191, "model_type": "text_generation", "endpoints": { "inbound": [ "anthropic-messages", "openai-compatible" ], "outbound": [ "anthropic-messages" ] }, "aliases": [ "anthropic.claude-v1" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "claude-v1" } ] }, { "slug": "baichuan/Baichuan-M2", "model_name": "Baichuan-M2", "display_name": "Baichuan M2", "vendor": "baichuan", "pricing": [ { "provider": "baichuan", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.294118" }, "completion": { "unit": "per_M_tokens", "price": "2.941176" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-08-19", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "baichuan", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "baichuan-m2" ], "intro_i18n": { "zh-CN": "我们推出 Baichuan-M2，这是一款面向真实世界医学推理任务的医学增强型推理模型。我们从真实医学问题出发，并基于大规模验证器系统进行强化学习训练。在保持模型通用能力的同时，Baichuan-M2 在医学有效性上取得了突破性提升。Baichuan-M2 是迄今为止全球最强的开源医疗大模型，性能超越包括 gpt-oss-120b 在内的所有开源模型，并在 HealthBench 基准上领先众多前沿闭源模型。在医学能力上，它是最接近 GPT-5 的开源模型。我们的实践表明，强健的验证器对于将模型能力与现实世界连接至关重要，而端到端的强化学习范式能够从根本上提升模型的医学推理能力。Baichuan-M2 的发布推动了医疗人工智能技术的前沿发展。", "zh-TW": "我們推出 Baichuan-M2，一款經過醫學增強的推理模型，專為真實世界的醫療推理任務設計。我們從真實醫療問題出發，基於大規模驗證器系統進行強化學習訓練。在保持模型通用能力的同時，Baichuan-M2 在醫療效果上取得突破性提升。Baichuan-M2 是目前全球最強的開源醫療模型，全面超越所有開源模型（包含 gpt-oss-120b）以及多款頂尖閉源模型，在 HealthBench 基準測試上名列前茅。它是醫療能力最接近 GPT-5 的開源模型。我們的實踐證明，強大的驗證器對於將模型能力連結到真實世界至關重要，而端到端強化學習方法能從根本提升模型的醫療推理能力。Baichuan-M2 的發布推動了醫療人工智慧領域的技術前沿。", "ja-JP": "Baichuan-M2は、医療分野に特化した推論モデルであり、実世界の医療推論タスクに対応するために設計されています。実際の医療質問を出発点とし、大規模な検証システムに基づく強化学習トレーニングを実施しました。モデルの一般的な能力を維持しつつ、Baichuan-M2の医療効果は画期的な向上を遂げました。Baichuan-M2は、現在世界で最も優れたオープンソースの医療モデルであり、gpt-oss-120bを含むすべてのオープンソースモデルや、最先端のクローズドソースモデルをHealthBenchベンチマークで上回ります。医療能力においてGPT-5に最も近いオープンソースモデルです。我々の実践は、堅牢な検証システムがモデル能力を実世界に結びつける上で重要であり、エンドツーエンドの強化学習アプローチがモデルの医療推論能力を根本的に向上させることを示しています。Baichuan-M2のリリースは、医療人工知能分野の技術の最前線をさらに進化させます。", "ru-RU": "Мы представляем Baichuan-M2 — модель медицинского рассуждения с расширенными возможностями, созданную для решения реальных медицинских задач. Мы начинаем с вопросов, основанных на реальной клинической практике, и проводим обучение с подкреплением на базе крупномасштабной системы верификации. Сохраняя общие способности модели, Baichuan-M2 демонстрирует значительный прорыв в медицинской эффективности. На сегодняшний день это лучшая открытая медицинская модель в мире. Она превосходит все открытые модели, включая gpt-oss-120b, а также многие передовые закрытые модели в бенчмарке HealthBench. По медицинским возможностям это самая близкая к GPT-5 открытая модель. Наша практика показывает, что надежный верификатор имеет решающее значение для связи возможностей модели с реальным миром, а подход обучения с подкреплением от начала до конца принципиально усиливает способность модели к медицинским рассуждениям. Выпуск Baichuan-M2 продвигает передовой уровень технологий в области медицинского искусственного интеллекта." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Baichuan M2" } ] }, { "slug": "baichuan/Baichuan-M2-Plus", "model_name": "Baichuan-M2-Plus", "display_name": "Baichuan M2 Plus", "vendor": "baichuan", "pricing": [ { "provider": "baichuan", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.470588" }, "completion": { "unit": "per_M_tokens", "price": "4.411765" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true }, "released_at": "2025-10-25", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "baichuan-m2-plus" ], "intro_i18n": { "zh-CN": "我们推出 Baichuan-M2，这是一款面向真实世界医学推理任务的医学增强型推理模型。我们从真实医学问题出发，并基于大规模验证器系统进行强化学习训练。在保持模型通用能力的同时，Baichuan-M2 在医学有效性上取得了突破性提升。Baichuan-M2 是迄今为止全球最强的开源医疗大模型，性能超越包括 gpt-oss-120b 在内的所有开源模型，并在 HealthBench 基准上领先众多前沿闭源模型。在医学能力上，它是最接近 GPT-5 的开源模型。我们的实践表明，强健的验证器对于将模型能力与现实世界连接至关重要，而端到端的强化学习范式能够从根本上提升模型的医学推理能力。Baichuan-M2 的发布推动了医疗人工智能技术的前沿发展。", "zh-TW": "我們推出 Baichuan-M2，一款經過醫學增強的推理模型，專為真實世界的醫療推理任務設計。我們從真實醫療問題出發，基於大規模驗證器系統進行強化學習訓練。在保持模型通用能力的同時，Baichuan-M2 在醫療效果上取得突破性提升。Baichuan-M2 是目前全球最強的開源醫療模型，全面超越所有開源模型（包含 gpt-oss-120b）以及多款頂尖閉源模型，在 HealthBench 基準測試上名列前茅。它是醫療能力最接近 GPT-5 的開源模型。我們的實踐證明，強大的驗證器對於將模型能力連結到真實世界至關重要，而端到端強化學習方法能從根本提升模型的醫療推理能力。Baichuan-M2 的發布推動了醫療人工智慧領域的技術前沿。", "ja-JP": "Baichuan-M2は、医療分野に特化した推論モデルであり、実世界の医療推論タスクに対応するために設計されています。実際の医療質問を出発点とし、大規模な検証システムに基づく強化学習トレーニングを実施しました。モデルの一般的な能力を維持しつつ、Baichuan-M2の医療効果は画期的な向上を遂げました。Baichuan-M2は、現在世界で最も優れたオープンソースの医療モデルであり、gpt-oss-120bを含むすべてのオープンソースモデルや、最先端のクローズドソースモデルをHealthBenchベンチマークで上回ります。医療能力においてGPT-5に最も近いオープンソースモデルです。我々の実践は、堅牢な検証システムがモデル能力を実世界に結びつける上で重要であり、エンドツーエンドの強化学習アプローチがモデルの医療推論能力を根本的に向上させることを示しています。Baichuan-M2のリリースは、医療人工知能分野の技術の最前線をさらに進化させます。", "ru-RU": "Мы представляем Baichuan-M2 — модель медицинского рассуждения с расширенными возможностями, созданную для решения реальных медицинских задач. Мы начинаем с вопросов, основанных на реальной клинической практике, и проводим обучение с подкреплением на базе крупномасштабной системы верификации. Сохраняя общие способности модели, Baichuan-M2 демонстрирует значительный прорыв в медицинской эффективности. На сегодняшний день это лучшая открытая медицинская модель в мире. Она превосходит все открытые модели, включая gpt-oss-120b, а также многие передовые закрытые модели в бенчмарке HealthBench. По медицинским возможностям это самая близкая к GPT-5 открытая модель. Наша практика показывает, что надежный верификатор имеет решающее значение для связи возможностей модели с реальным миром, а подход обучения с подкреплением от начала до конца принципиально усиливает способность модели к медицинским рассуждениям. Выпуск Baichuan-M2 продвигает передовой уровень технологий в области медицинского искусственного интеллекта." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Baichuan M2 Plus" } ] }, { "slug": "baichuan/Baichuan-M3", "model_name": "Baichuan-M3", "display_name": "Baichuan M3", "vendor": "baichuan", "pricing": [ { "provider": "baichuan", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.470588" }, "completion": { "unit": "per_M_tokens", "price": "4.411765" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "reasoning": true }, "released_at": "2026-01-21", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "baichuan-m3" ], "intro_i18n": { "zh-CN": "我们推出 Baichuan-M3，这是一款新一代医学增强型大型语言模型，旨在支持临床级医疗辅助。不同于以往仅专注静态问答或浅层角色扮演的方法，Baichuan-M3 通过显式建模临床决策流程来提升真实医疗场景下的可用性与可靠性。它不再只是生成听起来合理的答案、流畅的“医生式提问”或诸如“请尽快就医”之类含糊但高频的建议，而是经过专门训练，能够主动获取关键临床信息、构建连贯的医学推理链，并在整个决策过程中系统性地抑制幻觉式输出。这一设计使模型具备与真实临床流程一致的医学增强能力。在临床问诊、医学幻觉鲁棒性、HealthBench 与 HealthBench-Hard 的评估中，Baichuan-M3 全面超越 OpenAI 最新旗舰模型 GPT-5.2，树立医学增强语言模型的新标杆。", "zh-TW": "我們推出 Baichuan-M3，新一代醫療增強大型語言模型，旨在支援臨床級的醫療輔助。不同於以往僅專注於靜態問答或表層角色扮演的方法，Baichuan-M3 被訓練為能明確建模臨床決策流程，以提升其在真實醫療場景中的可用性與可靠性。它不再僅生成似是而非的答案、流暢的醫生式提問，或高頻但模糊的建議（如「請儘速就醫」），而是經過特別訓練，能主動獲取關鍵臨床資訊、構建連貫的醫療推理路徑，並在整個決策過程中系統性抑制容易產生幻覺的行為。這樣的設計使其具備與臨床工作流程高度契合的內建醫療增強能力。在臨床問診、醫療幻覺穩健性、HealthBench 與 HealthBench-Hard 的評測中，Baichuan-M3 均超越 OpenAI 最新旗艦模型 GPT-5.2，樹立醫療增強語言模型的新標竿。", "ja-JP": "Baichuan-M3は、臨床レベルの医療支援を提供するために設計された新世代の医療強化型大規模言語モデルです。従来の静的な質問応答や表面的なロールプレイングに重点を置いたアプローチとは異なり、Baichuan-M3は臨床的意思決定プロセスを明示的にモデル化するように訓練され、実世界の医療実践における使いやすさと信頼性の向上を目指しています。単に説得力のある回答や流暢な医師のような質問、または「できるだけ早く医療機関を受診してください」といった曖昧な推奨を生成するのではなく、Baichuan-M3は重要な臨床情報を積極的に取得し、一貫した医療推論経路を構築し、意思決定プロセス全体で幻覚を起こしやすい行動を体系的に制約するように訓練されています。この設計により、モデルは実際の臨床ワークフローに一致した医療強化型能力を備えることができます。臨床的な問い合わせ、医療幻覚の耐性、HealthBench、およびHealthBench-Hardの評価において、Baichuan-M3はOpenAIがリリースした最新のフラッグシップモデルGPT-5.2を上回り、医療強化型言語モデルの新たな最先端を確立しました。", "ru-RU": "Мы представляем Baichuan-M3 — модель нового поколения с усиленными медицинскими возможностями, созданную для поддержки клинического уровня медицинской помощи. В отличие от предыдущих подходов, ориентированных в основном на статическое ответы на вопросы или поверхностное ролевое взаимодействие, Baichuan-M3 обучена явному моделированию процесса клинического принятия решений, что повышает ее практическую ценность и надежность в реальных медицинских условиях. Вместо того чтобы просто выдавать правдоподобные ответы, имитировать врачебные вопросы или давать частые, но расплывчатые рекомендации вроде «вам следует как можно скорее обратиться к врачу», Baichuan-M3 обучена активно собирать ключевую клиническую информацию, выстраивать последовательные логические цепочки рассуждений и систематически снижать вероятность галлюцинаций на протяжении всего процесса принятия решений. Такой подход наделяет модель встроенными медицинскими возможностями, согласованными с реальными клиническими рабочими процессами. В оценках по клиническим опросам, устойчивости к медицинским галлюцинациям, HealthBench и HealthBench-Hard, Baichuan-M3 превосходит последнюю флагманскую модель OpenAI — GPT-5.2, устанавливая новый стандарт для языковых моделей с медицинскими улучшениями." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Baichuan M3" } ] }, { "slug": "baichuan/Baichuan-M3-Plus", "model_name": "Baichuan-M3-Plus", "display_name": "Baichuan M3 Plus", "vendor": "baichuan", "pricing": [ { "provider": "baichuan", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.735294" }, "completion": { "unit": "per_M_tokens", "price": "1.323529" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "reasoning": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "我们推出 Baichuan-M3，这是一款新一代医学增强型大型语言模型，旨在支持临床级医疗辅助。不同于以往仅专注静态问答或浅层角色扮演的方法，Baichuan-M3 通过显式建模临床决策流程来提升真实医疗场景下的可用性与可靠性。它不再只是生成听起来合理的答案、流畅的“医生式提问”或诸如“请尽快就医”之类含糊但高频的建议，而是经过专门训练，能够主动获取关键临床信息、构建连贯的医学推理链，并在整个决策过程中系统性地抑制幻觉式输出。这一设计使模型具备与真实临床流程一致的医学增强能力。在临床问诊、医学幻觉鲁棒性、HealthBench 与 HealthBench-Hard 的评估中，Baichuan-M3 全面超越 OpenAI 最新旗舰模型 GPT-5.2，树立医学增强语言模型的新标杆。", "zh-TW": "我們推出 Baichuan-M3，新一代醫療增強大型語言模型，旨在支援臨床級的醫療輔助。不同於以往僅專注於靜態問答或表層角色扮演的方法，Baichuan-M3 被訓練為能明確建模臨床決策流程，以提升其在真實醫療場景中的可用性與可靠性。它不再僅生成似是而非的答案、流暢的醫生式提問，或高頻但模糊的建議（如「請儘速就醫」），而是經過特別訓練，能主動獲取關鍵臨床資訊、構建連貫的醫療推理路徑，並在整個決策過程中系統性抑制容易產生幻覺的行為。這樣的設計使其具備與臨床工作流程高度契合的內建醫療增強能力。在臨床問診、醫療幻覺穩健性、HealthBench 與 HealthBench-Hard 的評測中，Baichuan-M3 均超越 OpenAI 最新旗艦模型 GPT-5.2，樹立醫療增強語言模型的新標竿。", "ja-JP": "Baichuan-M3は、臨床レベルの医療支援を提供するために設計された新世代の医療強化型大規模言語モデルです。従来の静的な質問応答や表面的なロールプレイングに重点を置いたアプローチとは異なり、Baichuan-M3は臨床的意思決定プロセスを明示的にモデル化するように訓練され、実世界の医療実践における使いやすさと信頼性の向上を目指しています。単に説得力のある回答や流暢な医師のような質問、または「できるだけ早く医療機関を受診してください」といった曖昧な推奨を生成するのではなく、Baichuan-M3は重要な臨床情報を積極的に取得し、一貫した医療推論経路を構築し、意思決定プロセス全体で幻覚を起こしやすい行動を体系的に制約するように訓練されています。この設計により、モデルは実際の臨床ワークフローに一致した医療強化型能力を備えることができます。臨床的な問い合わせ、医療幻覚の耐性、HealthBench、およびHealthBench-Hardの評価において、Baichuan-M3はOpenAIがリリースした最新のフラッグシップモデルGPT-5.2を上回り、医療強化型言語モデルの新たな最先端を確立しました。", "ru-RU": "Мы представляем Baichuan-M3 — модель нового поколения с усиленными медицинскими возможностями, созданную для поддержки клинического уровня медицинской помощи. В отличие от предыдущих подходов, ориентированных в основном на статическое ответы на вопросы или поверхностное ролевое взаимодействие, Baichuan-M3 обучена явному моделированию процесса клинического принятия решений, что повышает ее практическую ценность и надежность в реальных медицинских условиях. Вместо того чтобы просто выдавать правдоподобные ответы, имитировать врачебные вопросы или давать частые, но расплывчатые рекомендации вроде «вам следует как можно скорее обратиться к врачу», Baichuan-M3 обучена активно собирать ключевую клиническую информацию, выстраивать последовательные логические цепочки рассуждений и систематически снижать вероятность галлюцинаций на протяжении всего процесса принятия решений. Такой подход наделяет модель встроенными медицинскими возможностями, согласованными с реальными клиническими рабочими процессами. В оценках по клиническим опросам, устойчивости к медицинским галлюцинациям, HealthBench и HealthBench-Hard, Baichuan-M3 превосходит последнюю флагманскую модель OpenAI — GPT-5.2, устанавливая новый стандарт для языковых моделей с медицинскими улучшениями." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Baichuan M3 Plus" } ] }, { "slug": "baichuan/Baichuan2-Turbo", "model_name": "Baichuan2-Turbo", "display_name": "Baichuan 2 Turbo", "vendor": "baichuan", "pricing": [ { "provider": "baichuan", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.176471" }, "completion": { "unit": "per_M_tokens", "price": "1.176471" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "通过搜索增强技术将模型与领域知识和网页知识连接，支持 PDF/Word 上传和 URL 输入，实现及时、全面的检索与专业、准确的输出。", "zh-TW": "透過搜尋增強技術，將模型與領域知識與網路資訊連結。支援 PDF/Word 上傳與網址輸入，實現即時、全面的檢索與專業、準確的輸出。", "ja-JP": "検索拡張を活用して、モデルをドメイン知識やウェブ知識と接続。PDF/WordのアップロードやURL入力に対応し、タイムリーで包括的な情報取得と専門的で正確な出力を実現します。", "ru-RU": "Использует расширение поиска для подключения модели к отраслевым и веб-знаниям. Поддерживает загрузку PDF/Word и ввод URL для своевременного, всестороннего поиска и профессионального, точного вывода." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Baichuan 2 Turbo" } ] }, { "slug": "baichuan/Baichuan3-Turbo", "model_name": "Baichuan3-Turbo", "display_name": "Baichuan 3 Turbo", "vendor": "baichuan", "pricing": [ { "provider": "baichuan", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.764706" }, "completion": { "unit": "per_M_tokens", "price": "1.764706" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true }, "released_at": "2024-02-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "baichuan3-turbo" ], "intro_i18n": { "zh-CN": "专为高频企业场景优化，带来显著提升与高价值。相比 Baichuan2，内容创作提升 20%，知识问答提升 17%，角色扮演提升 40%。整体性能优于 GPT-3.5。", "zh-TW": "針對高頻企業場景進行優化，帶來顯著效能提升。相較於 Baichuan2，內容創作提升 20%，知識問答提升 17%，角色扮演提升 40%。整體表現優於 GPT-3.5。", "ja-JP": "頻度の高い企業シナリオに最適化され、大幅な性能向上と高い価値を提供します。Baichuan2と比較して、コンテンツ生成は20%、知識QAは17%、ロールプレイは40%向上。全体的な性能はGPT-3.5を上回ります。", "ru-RU": "Оптимизирована для частых корпоративных сценариев с существенным приростом ценности. По сравнению с Baichuan2, генерация контента улучшена на 20%, ответы на вопросы — на 17%, ролевые сценарии — на 40%. Общая производительность выше, чем у GPT-3.5." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Baichuan 3 Turbo" } ] }, { "slug": "baichuan/Baichuan3-Turbo-128k", "model_name": "Baichuan3-Turbo-128k", "display_name": "Baichuan 3 Turbo 128k", "vendor": "baichuan", "pricing": [ { "provider": "baichuan", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3.529412" }, "completion": { "unit": "per_M_tokens", "price": "3.529412" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 128000, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": {}, "released_at": "2025-08-08", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "baichuan3-turbo-128k" ], "intro_i18n": { "zh-CN": "拥有 128K 超长上下文窗口，专为高频企业场景优化，带来显著提升与高价值。相比 Baichuan2，内容创作提升 20%，知识问答提升 17%，角色扮演提升 40%。整体性能优于 GPT-3.5。", "zh-TW": "具備 128K 超長上下文視窗，針對高頻企業場景進行優化，帶來顯著效能提升。相較於 Baichuan2，內容創作提升 20%，知識問答提升 17%，角色扮演提升 40%。整體表現優於 GPT-3.5。", "ja-JP": "128Kの超長文コンテキストウィンドウを備え、頻度の高い企業シナリオに最適化され、大幅な性能向上と高い価値を提供します。Baichuan2と比較して、コンテンツ生成は20%、知識QAは17%、ロールプレイは40%向上。全体的な性能はGPT-3.5を上回ります。", "ru-RU": "С ультрадлинным контекстным окном на 128K, оптимизирована для частых корпоративных сценариев с существенным приростом ценности. По сравнению с Baichuan2, генерация контента улучшена на 20%, ответы на вопросы — на 17%, ролевые сценарии — на 40%. Общая производительность выше, чем у GPT-3.5." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Baichuan 3 Turbo 128k" } ] }, { "slug": "baichuan/Baichuan4", "model_name": "Baichuan4", "display_name": "Baichuan 4", "vendor": "baichuan", "pricing": [ { "provider": "baichuan", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "14.705882" }, "completion": { "unit": "per_M_tokens", "price": "14.705882" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true }, "released_at": "2024-02-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "baichuan4" ], "intro_i18n": { "zh-CN": "国内顶尖性能，在中文任务如百科知识、长文本处理和创意生成方面超越海外主流模型。具备行业领先的多模态能力，在权威评测中表现出色。", "zh-TW": "國內頂尖表現，在百科知識、長文本處理與創意生成等中文任務上超越主流海外模型。亦具備業界領先的多模態能力與強勁的基準測試成績。", "ja-JP": "中国国内で最高レベルの性能を持ち、百科事典的知識、長文生成、創造的生成などの中国語タスクで海外の主要モデルを上回ります。業界最先端のマルチモーダル機能と優れたベンチマーク結果も提供します。", "ru-RU": "Лидер по производительности среди отечественных моделей, превосходит ведущие зарубежные модели в задачах на китайском языке, таких как энциклопедические знания, длинные тексты и творческая генерация. Также предлагает передовые мультимодальные возможности и высокие результаты на бенчмарках." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Baichuan 4" } ] }, { "slug": "baichuan/Baichuan4-Air", "model_name": "Baichuan4-Air", "display_name": "Baichuan 4 Air", "vendor": "baichuan", "pricing": [ { "provider": "baichuan", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.144118" }, "completion": { "unit": "per_M_tokens", "price": "0.144118" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-08-19", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "baichuan", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "国内领先模型，在中文任务如知识问答、长文本处理和创意生成方面超越海外主流模型。具备行业领先的多模态能力，在权威评测中表现优异。", "zh-TW": "中國表現最強的模型之一，在知識問答、長文本處理與創意生成等中文任務上超越多個海外主流模型。具備業界領先的多模態能力，在權威基準測試中表現優異。", "ja-JP": "中国国内でトップクラスの性能を誇り、知識、長文生成、創造的生成などの中国語タスクで海外の主要モデルを上回ります。業界最先端のマルチモーダル機能も備え、権威あるベンチマークで高評価を獲得しています。", "ru-RU": "Одна из лучших моделей в Китае, превосходит ведущие зарубежные модели в задачах на китайском языке, таких как энциклопедические знания, длинные тексты и творческая генерация. Также обладает передовыми мультимодальными возможностями с высокими результатами на авторитетных бенчмарках." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Baichuan 4 Air" } ] }, { "slug": "baichuan/Baichuan4-Turbo", "model_name": "Baichuan4-Turbo", "display_name": "Baichuan 4 Turbo", "vendor": "baichuan", "pricing": [ { "provider": "baichuan", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.205882" }, "completion": { "unit": "per_M_tokens", "price": "2.205882" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-08-19", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "baichuan", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "国内领先模型，在中文任务如知识问答、长文本处理和创意生成方面超越海外主流模型。具备行业领先的多模态能力，在权威评测中表现优异。", "zh-TW": "中國表現最強的模型之一，在知識問答、長文本處理與創意生成等中文任務上超越多個海外主流模型。具備業界領先的多模態能力，在權威基準測試中表現優異。", "ja-JP": "中国国内でトップクラスの性能を誇り、知識、長文生成、創造的生成などの中国語タスクで海外の主要モデルを上回ります。業界最先端のマルチモーダル機能も備え、権威あるベンチマークで高評価を獲得しています。", "ru-RU": "Одна из лучших моделей в Китае, превосходит ведущие зарубежные модели в задачах на китайском языке, таких как энциклопедические знания, длинные тексты и творческая генерация. Также обладает передовыми мультимодальными возможностями с высокими результатами на авторитетных бенчмарках." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Baichuan 4 Turbo" } ] }, { "slug": "bfl/flux-dev", "model_name": "flux-dev", "display_name": "FLUX.1 [dev]", "vendor": "bfl", "pricing": [ { "provider": "bfl", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.025" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2024-08-01", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "black-forest-labs/flux-dev" ], "intro_i18n": { "zh-CN": "FLUX Dev 是 FLUX 的开发版本，仅供非商业用途使用。", "zh-TW": "FLUX Dev 是 FLUX 的開發版本，僅供非商業用途。", "ja-JP": "FLUX Devは、非商用利用向けのFLUX開発バージョンです。", "ru-RU": "FLUX Dev — это версия FLUX для разработки, предназначенная для некоммерческого использования." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "FLUX.1 [dev]" } ] }, { "slug": "bfl/flux-kontext-max", "model_name": "flux-kontext-max", "display_name": "FLUX.1 Kontext [max]", "vendor": "bfl", "pricing": [ { "provider": "bfl", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.08" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-05-29", "model_type": "image_generation", "capabilities": { "image_output": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "max_input_tokens": 512, "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "family": "flux", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bfl/flux-kontext-max" ], "intro_i18n": { "zh-CN": "最先进的上下文图像生成与编辑模型，结合文本与图像输入，实现精准一致的结果。", "zh-TW": "最先進的語境圖像生成與編輯技術，結合文字與圖像輸入，實現精準且一致的結果。", "ja-JP": "最先端のコンテキスト画像生成・編集モデルで、テキストと画像を組み合わせて精密かつ一貫性のある結果を生成します。", "ru-RU": "Передовая генерация и редактирование изображений с учётом контекста, объединяющая текст и изображения для точных и согласованных результатов." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "FLUX.1 Kontext [max]" } ] }, { "slug": "bfl/flux-kontext-pro", "model_name": "flux-kontext-pro", "display_name": "FLUX.1 Kontext [pro]", "vendor": "bfl", "pricing": [ { "provider": "bfl", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-05-29", "model_type": "image_generation", "capabilities": { "image_output": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "max_input_tokens": 512, "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "family": "flux", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bfl/flux-kontext-pro" ], "intro_i18n": { "zh-CN": "最先进的上下文图像生成与编辑模型，结合文本与图像输入，实现精准一致的结果。", "zh-TW": "最先進的語境圖像生成與編輯技術，結合文字與圖像輸入，實現精準且一致的結果。", "ja-JP": "最先端のコンテキスト画像生成・編集モデルで、テキストと画像を組み合わせて精密かつ一貫性のある結果を生成します。", "ru-RU": "Передовая генерация и редактирование изображений с учётом контекста, объединяющая текст и изображения для точных и согласованных результатов." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "FLUX.1 Kontext [pro]" } ] }, { "slug": "bfl/FLUX-pro", "model_name": "FLUX-pro", "display_name": "FLUX.1 [pro]", "vendor": "bfl", "pricing": [ { "provider": "bfl", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.025" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "flux-pro" } ], "released_at": "2024-08-01", "model_type": "image_generation", "capabilities": { "image_output": true }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "black-forest-labs/FLUX-pro", "black-forest-labs/flux-pro", "flux-pro" ], "intro_i18n": { "zh-CN": "FLUX Pro 是专业级图像生成模型，输出高质量图像。", "zh-TW": "FLUX Pro 是專業級 FLUX 模型，專為高品質圖像輸出設計。", "ja-JP": "FLUX Proは、高品質な画像出力を実現するプロフェッショナル向けFLUXモデルです。", "ru-RU": "FLUX Pro — профессиональная модель FLUX для генерации изображений высокого качества." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "FLUX.1 [pro]" } ] }, { "slug": "bfl/flux-pro-1.1", "model_name": "flux-pro-1.1", "display_name": "FLUX1.1 [pro] ", "vendor": "bfl", "pricing": [ { "provider": "bfl", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2024-10-02", "model_type": "image_generation", "capabilities": { "image_output": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "max_input_tokens": 512, "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "family": "flux", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bfl/flux-pro-1.1" ], "intro_i18n": { "zh-CN": "升级版专业图像生成模型，图像质量卓越，提示词遵循精准。", "zh-TW": "升級版專業級圖像生成模型，具備卓越圖像品質與精準提示遵循能力。", "ja-JP": "画像品質とプロンプトの精度に優れた、アップグレードされたプロフェッショナル画像生成モデルです。", "ru-RU": "Обновлённая профессиональная модель генерации изображений с отличным качеством и точным следованием подсказкам." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "FLUX1.1 [pro] " } ] }, { "slug": "bfl/flux-pro-1.1-ultra", "model_name": "flux-pro-1.1-ultra", "display_name": "FLUX1.1 [pro] Ultra", "vendor": "bfl", "pricing": [ { "provider": "bfl", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2024-11-06", "model_type": "image_generation", "capabilities": { "image_output": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "max_input_tokens": 512, "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "family": "flux", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bfl/flux-pro-1.1-ultra" ], "intro_i18n": { "zh-CN": "超高分辨率图像生成，支持 4MP 输出，10 秒内生成清晰图像。", "zh-TW": "支援 4MP 輸出的超高解析度圖像生成，10 秒內產出清晰圖像。", "ja-JP": "400 万画素の超高解像度画像を 10 秒で生成するモデルです。", "ru-RU": "Генерация изображений сверхвысокого разрешения с выходом 4 МП, создаёт чёткие изображения за 10 секунд." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "FLUX1.1 [pro] Ultra" } ] }, { "slug": "bytedance/deepseek-v3-2-251201", "model_name": "deepseek-v3-2-251201", "display_name": "deepseek-v3-2-251201", "vendor": "bytedance", "pricing": [ { "provider": "volcengine", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 98304, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "assistant_prefill": true }, "intro": "DeepSeek chat model for instruction following, coding, and analysis", "released_at": "2025-12-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "deepseek/deepseek-v3.2-251201" ] }, { "slug": "bytedance/doubao-1-5-lite-32k", "model_name": "doubao-1-5-lite-32k", "display_name": "Doubao 1.5 Lite 32k", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.044118" }, "completion": { "unit": "per_M_tokens", "price": "0.088235" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-1.5-lite-32k" } ], "max_input_tokens": 32768, "max_output_tokens": 12288, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true }, "released_at": "2025-01-22", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Doubao-1.5-lite-32k", "doubao-1.5-lite-32k" ], "intro_i18n": { "zh-CN": "Doubao-1.5-lite 是一款全新轻量级模型，响应速度极快，兼具卓越质量与低延迟。", "zh-TW": "Doubao-1.5-lite 是一款全新輕量級模型，具備極速回應能力，提供頂級品質與低延遲表現。", "ja-JP": "Doubao-1.5-lite は、超高速応答を実現する新しい軽量モデルで、最高水準の品質と低遅延を提供します。", "ru-RU": "Doubao-1.5-lite — новая облегчённая модель с ультрабыстрым откликом, обеспечивающая высокое качество и низкую задержку." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao 1.5 Lite 32k" } ] }, { "slug": "bytedance/doubao-1-5-pro-256k", "model_name": "doubao-1-5-pro-256k", "display_name": "Doubao 1.5 Pro 256k", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.735294" }, "completion": { "unit": "per_M_tokens", "price": "1.323529" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-1.5-pro-256k" } ], "max_input_tokens": 256000, "max_output_tokens": 12288, "model_type": "text_generation", "capabilities": { "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-03-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Doubao-1.5-pro-256k", "doubao-1.5-pro-256k" ], "intro_i18n": { "zh-CN": "Doubao-1.5-pro-256k 是 Doubao-1.5-Pro 的全面升级版，整体性能提升 10%。支持 256k 上下文窗口和最多 12k 输出 token，性能更强、窗口更大，适用于更广泛的场景。", "zh-TW": "Doubao-1.5-pro-256k 是 Doubao-1.5-Pro 的全面升級版，整體效能提升 10%。支援 256k 上下文視窗與最多 12k 輸出字元，提供更高效能、更大視窗與更廣泛應用價值。", "ja-JP": "Doubao-1.5-pro-256k は Doubao-1.5-Pro の包括的なアップグレード版で、全体的な性能が10%向上しています。256kのコンテキストウィンドウと最大12kの出力トークンに対応し、より高性能で広範なユースケースに対応する価値の高いモデルです。", "ru-RU": "Doubao-1.5-pro-256k — комплексное обновление модели Doubao-1.5-Pro, повышающее общую производительность на 10%. Поддерживает контекстное окно 256k и до 12k токенов вывода, обеспечивая высокую производительность, расширенное окно и отличную ценность для широкого спектра задач." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao 1.5 Pro 256k" } ] }, { "slug": "bytedance/doubao-1-5-pro-32k", "model_name": "doubao-1-5-pro-32k", "display_name": "Doubao 1.5 Pro 32k", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.117647" }, "completion": { "unit": "per_M_tokens", "price": "0.294118" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-1.5-pro-32k" } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "text_generation", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true }, "intro": "Flagship model for demanding analysis, coding, and production agent workflows", "released_at": "2025-08-05", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Doubao-1.5-pro-32k", "doubao-1.5-pro-32k" ], "intro_i18n": { "zh-CN": "Doubao-1.5-pro 是新一代旗舰模型，全面升级，在知识、编程和推理方面表现出色。", "zh-TW": "Doubao-1.5-pro 是新一代旗艦模型，全面升級，在知識、程式設計與推理方面表現出色。", "ja-JP": "Doubao-1.5-pro は次世代のフラッグシップモデルで、知識、コーディング、推論の各分野で優れた性能を発揮します。", "ru-RU": "Doubao-1.5-pro — флагманская модель нового поколения с улучшениями по всем направлениям, превосходящая в знаниях, программировании и рассуждении." }, "price_history": [ { "date": "2026-08-06", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao 1.5 Pro 32k" } ] }, { "slug": "bytedance/doubao-1-5-vision-pro-32k", "model_name": "doubao-1-5-vision-pro-32k", "display_name": "Doubao 1.5 Vision Pro 32k", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.441176" }, "completion": { "unit": "per_M_tokens", "price": "1.323529" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-1.5-vision-pro-32k" } ], "released_at": "2025-01-15", "max_input_tokens": 32768, "max_output_tokens": 12288, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "vision": true, "image_output": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Doubao-1.5-vision-pro-32k", "doubao-1.5-vision-pro-32k" ], "intro_i18n": { "zh-CN": "Doubao-1.5-vision-pro 是升级版多模态模型，支持任意分辨率和极端长宽比图像，提升视觉推理、文档识别、细节理解与指令遵循能力。", "zh-TW": "Doubao-1.5-vision-pro 是升級版多模態模型，支援任意解析度與極端長寬比的圖像，強化視覺推理、文件識別、細節理解與指令遵循。", "ja-JP": "Doubao-1.5-vision-pro はアップグレードされたマルチモーダルモデルで、あらゆる解像度や極端なアスペクト比の画像に対応し、視覚的推論、文書認識、細部理解、指示の追従性を強化します。", "ru-RU": "Doubao-1.5-vision-pro — обновлённая мультимодальная модель, поддерживающая изображения любого разрешения и экстремальных соотношений сторон, улучшая визуальное рассуждение, распознавание документов, понимание деталей и следование инструкциям." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao 1.5 Vision Pro 32k" } ] }, { "slug": "bytedance/doubao-embedding", "model_name": "doubao-embedding", "display_name": "doubao-embedding", "vendor": "bytedance", "pricing": [ { "provider": "volcengine", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 4096, "model_type": "text_embedding", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "bytedance/doubao-embedding-large", "model_name": "doubao-embedding-large", "display_name": "doubao-embedding-large", "vendor": "bytedance", "pricing": [ { "provider": "volcengine", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 4096, "model_type": "text_embedding", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "bytedance/doubao-embedding-large-text-240915", "model_name": "doubao-embedding-large-text-240915", "display_name": "doubao-embedding-large-text-240915", "vendor": "bytedance", "pricing": [ { "provider": "volcengine", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 4096, "model_type": "text_embedding", "capabilities": { "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [] }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "bytedance/doubao-embedding-large-text-250515", "model_name": "doubao-embedding-large-text-250515", "display_name": "doubao-embedding-large-text-250515", "vendor": "bytedance", "pricing": [ { "provider": "volcengine", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 4096, "model_type": "text_embedding", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "bytedance/doubao-embedding-text-240715", "model_name": "doubao-embedding-text-240715", "display_name": "doubao-embedding-text-240715", "vendor": "bytedance", "pricing": [ { "provider": "volcengine", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 4096, "model_type": "text_embedding", "capabilities": { "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [] }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "bytedance/Doubao-lite-32k", "model_name": "Doubao-lite-32k", "display_name": "Doubao Lite 32k", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.044118" }, "completion": { "unit": "per_M_tokens", "price": "0.088235" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-lite-32k" } ], "max_input_tokens": 32768, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "prompt_caching": true }, "released_at": "2026-08-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "doubao-lite-32k" ], "intro_i18n": { "zh-CN": "豆包-lite 提供超快响应和更高性价比，适用于多种场景，支持 32K 上下文推理与微调。", "zh-TW": "Doubao-lite 提供超快速回應與更高性價比，適用於多種場景，支援 32K 上下文推理與微調。", "ja-JP": "Doubao-lite は、超高速な応答と優れたコストパフォーマンスを提供し、さまざまなシナリオに柔軟に対応します。推論とファインチューニングに対応した32Kコンテキストをサポートします。", "ru-RU": "Doubao-lite обеспечивает сверхбыстрые ответы и отличное соотношение цены и качества, предлагая гибкие варианты для различных сценариев. Поддерживает контекст объемом 32K для вывода и дообучения." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao Lite 32k" } ] }, { "slug": "bytedance/Doubao-pro-32k", "model_name": "Doubao-pro-32k", "display_name": "Doubao Pro 32k", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.117647" }, "completion": { "unit": "per_M_tokens", "price": "0.294118" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-pro-32k" } ], "max_input_tokens": 32768, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true }, "released_at": "2024-06-06", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "doubao-pro-32k" ], "intro_i18n": { "zh-CN": "旗舰性能最强模型，擅长复杂任务，在参考问答、摘要、创作、分类和角色扮演方面表现出色。支持 32K 上下文推理与微调。", "zh-TW": "旗艦級最佳表現模型，擅長參考問答、摘要、創作、分類與角色扮演。支援 32K 上下文推理與微調。", "ja-JP": "複雑なタスクに最適な高性能フラッグシップモデルで、参照型QA、要約、創作、分類、ロールプレイに強みを持ちます。推論とファインチューニングに対応した32Kコンテキストをサポートします。", "ru-RU": "Флагманская модель с наилучшей производительностью для сложных задач, превосходно справляется с вопросно-ответными задачами, суммированием, созданием контента, классификацией и ролевыми сценариями. Поддерживает контекст объемом 32K для вывода и дообучения." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao Pro 32k" } ] }, { "slug": "bytedance/doubao-seed-1-6", "model_name": "doubao-seed-1-6", "display_name": "Doubao Seed 1.6", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.117647" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.176471" }, "prompt_0_128_infinity": { "unit": "per_M_tokens", "price": "0.352941" }, "completion_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "0.294118" }, "completion_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "1.176471" }, "completion_0_032_0_128_0_infinity": { "unit": "per_M_tokens", "price": "2.352941" }, "completion_0_128_infinity_0_infinity": { "unit": "per_M_tokens", "price": "3.529412" }, "cache_read": { "unit": "per_M_tokens", "price": "0.023529" } }, "provenance": { "base_charges": { "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_infinity": "lobehub-modelbank", "completion_0_0_032_0_0_0002": "lobehub-modelbank", "completion_0_0_032_0_0002_infinity": "lobehub-modelbank", "completion_0_032_0_128_0_infinity": "lobehub-modelbank", "completion_0_128_infinity_0_infinity": "lobehub-modelbank", "cache_read": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-seed-1.6" } ], "max_input_tokens": 256000, "max_output_tokens": 32000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "intro": "Multimodal reasoning model for visual analysis, planning, and tool use", "released_at": "2025-08-15", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "seed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "doubao-seed-1.6", "volcengine/doubao-seed-1-6" ], "intro_i18n": { "zh-CN": "Doubao-Seed-1.6 是一款全新多模态深度推理模型，支持自动、思考与非思考模式。在非思考模式下，其性能显著优于 Doubao-1.5-pro/250115。支持 256k 上下文窗口和最多 16k 输出 token。", "zh-TW": "Doubao-Seed-1.6 是一款全新多模態深度推理模型，具備自動、思考與非思考模式。在非思考模式下，效能顯著超越 Doubao-1.5-pro/250115。支援 256k 上下文視窗與最多 16k 輸出字元。", "ja-JP": "Doubao-Seed-1.6 は、自動、思考、非思考モードを備えた新しいマルチモーダル深層推論モデルです。非思考モードでは、Doubao-1.5-pro/250115 を大きく上回る性能を発揮します。256kのコンテキストウィンドウと最大16kの出力トークンに対応します。", "ru-RU": "Doubao-Seed-1.6 — новая мультимодальная модель глубокого рассуждения с режимами авто, мышления и без мышления. В режиме без мышления значительно превосходит Doubao-1.5-pro/250115. Поддерживает контекст до 256k и до 16k токенов вывода." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao Seed 1.6" } ] }, { "slug": "bytedance/doubao-seed-1-6-flash", "model_name": "doubao-seed-1-6-flash", "display_name": "Doubao Seed 1.6 Flash", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.022059" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.044118" }, "prompt_0_128_infinity": { "unit": "per_M_tokens", "price": "0.088235" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "0.220588" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "0.441176" }, "completion_0_128_infinity": { "unit": "per_M_tokens", "price": "0.882353" }, "cache_read": { "unit": "per_M_tokens", "price": "0.004412" } }, "provenance": { "base_charges": { "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_infinity": "lobehub-modelbank", "cache_read": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-seed-1.6-flash" } ], "max_input_tokens": 256000, "max_output_tokens": 32000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "intro": "Multimodal reasoning model for visual analysis, planning, and tool use", "released_at": "2025-08-15", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "seed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "doubao-seed-1.6-flash", "volcengine/doubao-seed-1-6-flash" ], "intro_i18n": { "zh-CN": "Doubao-Seed-1.6-flash 是一款超快多模态深度推理模型，TPOT 低至 10ms，支持文本与图像输入，在文本理解上超越前代 lite 模型，在视觉方面媲美主流 pro 模型。支持 256k 上下文窗口和最多 16k 输出 token。", "zh-TW": "Doubao-Seed-1.6-flash 是一款極速多模態深度推理模型，TPOT 低至 10ms。支援文字與圖像，文字理解超越前代 lite 模型，視覺能力媲美競品 pro 模型。支援 256k 上下文視窗與最多 16k 輸出字元。", "ja-JP": "Doubao-Seed-1.6-flash は、TPOTが10msと非常に低い超高速マルチモーダル深層推論モデルです。テキストと画像の両方に対応し、テキスト理解では従来のliteモデルを上回り、視覚では競合のproモデルに匹敵します。256kのコンテキストウィンドウと最大16kの出力トークンに対応します。", "ru-RU": "Doubao-Seed-1.6-flash — ультрабыстрая мультимодальная модель глубокого рассуждения с TPOT до 10 мс. Поддерживает текст и изображения, превосходит предыдущую lite-модель в понимании текста и сопоставима с pro-моделями в области зрения. Поддерживает контекстное окно 256k и до 16k токенов вывода." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao Seed 1.6 Flash" } ] }, { "slug": "bytedance/doubao-seed-1-6-vision", "model_name": "doubao-seed-1-6-vision", "display_name": "Doubao Seed 1.6 Vision", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.117647" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.352941" }, "prompt_0_128_infinity": { "unit": "per_M_tokens", "price": "0.705882" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "1.176471" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "2.352941" }, "completion_0_128_infinity": { "unit": "per_M_tokens", "price": "3.529412" }, "cache_read": { "unit": "per_M_tokens", "price": "0.023529" } }, "provenance": { "base_charges": { "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_infinity": "lobehub-modelbank", "cache_read": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-seed-1.6-vision" } ], "max_input_tokens": 256000, "max_output_tokens": 32000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "intro": "ByteDance Seed multimodal model for image understanding, visual reasoning, and tool-assisted tasks", "released_at": "2025-08-15", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "seed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "doubao-seed-1.6-vision", "volcengine/doubao-seed-1-6-vision" ], "intro_i18n": { "zh-CN": "Doubao-Seed-1.6-vision 是一款视觉深度推理模型，具备更强的多模态理解与推理能力，适用于教育、图像审核、安检和 AI 搜索问答等场景。支持 256k 上下文窗口和最多 64k 输出 token。", "zh-TW": "Doubao-Seed-1.6-vision 是一款視覺深度推理模型，針對教育、圖像審查、檢測/安防與 AI 搜尋問答等場景提供更強的多模態理解與推理能力。支援 256k 上下文視窗與最多 64k 輸出字元。", "ja-JP": "Doubao-Seed-1.6-vision は、教育、画像レビュー、検査・セキュリティ、AI検索QAなどにおいて、より強力なマルチモーダル理解と推論を提供する視覚的深層推論モデルです。256kのコンテキストウィンドウと最大64kの出力トークンに対応します。", "ru-RU": "Doubao-Seed-1.6-vision — визуальная модель глубокого рассуждения с улучшенным мультимодальным пониманием и логикой для образования, анализа изображений, инспекции/безопасности и визуального поиска с вопросами и ответами. Поддерживает контекст до 256k и до 64k токенов вывода." }, "price_history": [ { "date": "2026-08-10", "kind": "listed", "note": "Doubao Seed 1.6 Vision" } ] }, { "slug": "bytedance/doubao-seed-1-8", "model_name": "doubao-seed-1-8", "display_name": "Doubao Seed 1.8", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.117647" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.176471" }, "prompt_0_128_0_256": { "unit": "per_M_tokens", "price": "0.352941" }, "completion_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "0.294118" }, "completion_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "1.176471" }, "completion_0_032_0_128_0_infinity": { "unit": "per_M_tokens", "price": "2.352941" }, "completion_0_128_0_256_0_infinity": { "unit": "per_M_tokens", "price": "3.529412" }, "cache_read": { "unit": "per_M_tokens", "price": "0.023529" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.0025" } }, "provenance": { "base_charges": { "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_256": "lobehub-modelbank", "completion_0_0_032_0_0_0002": "lobehub-modelbank", "completion_0_0_032_0_0002_infinity": "lobehub-modelbank", "completion_0_032_0_128_0_infinity": "lobehub-modelbank", "completion_0_128_0_256_0_infinity": "lobehub-modelbank", "cache_read": "lobehub-modelbank", "cache_write_1h": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-seed-1.8" } ], "released_at": "2025-12-18", "max_input_tokens": 256000, "max_output_tokens": 64000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true, "stream": true }, "intro": "Multimodal reasoning model for visual analysis, planning, and tool use", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "seed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bytedance/doubao-seed-1.8", "doubao-seed-1.8", "volcengine/doubao-seed-1-8", "volcengine/doubao-seed-1.8" ], "intro_i18n": { "zh-CN": "豆包 Seed-1.8 拥有更强的多模态理解与智能体能力，支持文本/图像/视频输入与上下文缓存，在复杂任务中表现出色。", "zh-TW": "豆包 Seed-1.8 擁有更強的多模態理解與智能體能力，支援文字／圖片／影片輸入與上下文快取，在複雜任務中展現優異表現。", "ja-JP": "Doubao-Seed-1.8は、マルチモーダル理解とエージェント機能が強化されており、テキスト・画像・動画の入力とコンテキストキャッシュをサポートします。複雑なタスクにおいても優れたパフォーマンスを発揮します。", "ru-RU": "Doubao-Seed-1.8 обладает улучшенным мультимодальным пониманием и агентными возможностями, поддерживает ввод текста, изображений и видео, а также кэширование контекста, обеспечивая высокую эффективность при выполнении сложных задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Doubao Seed 1.8" } ] }, { "slug": "bytedance/doubao-seed-2-0-code", "model_name": "doubao-seed-2-0-code", "display_name": "Doubao Seed 2.0 Code", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.470588" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.705882" }, "prompt_0_128_0_256": { "unit": "per_M_tokens", "price": "1.411765" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "2.352941" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "3.529412" }, "completion_0_128_0_256": { "unit": "per_M_tokens", "price": "7.058824" }, "cache_read": { "unit": "per_M_tokens", "price": "0.094118" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.0025" } }, "provenance": { "base_charges": { "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_256": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_0_256": "lobehub-modelbank", "cache_read": "lobehub-modelbank", "cache_write_1h": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-seed-2.0-code" } ], "released_at": "2026-02-15", "max_input_tokens": 256000, "max_output_tokens": 128000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": "2025-01", "family": "seed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bytedance/doubao-seed-2.0-code", "doubao-seed-2.0-code", "volcengine/doubao-seed-2-0-code", "volcengine/doubao-seed-2.0-code" ], "intro_i18n": { "zh-CN": "Doubao-Seed-2.0-code 针对代理编程进行了深度优化，支持多模态输入和 256k 上下文窗口，适用于编程、视觉理解和代理工作流。", "zh-TW": "Doubao-Seed-2.0-code 深度優化於代理編程，支持多模態輸入和 256k 上下文窗口，適合編程、視覺理解和代理工作流程。", "ja-JP": "Doubao-Seed-2.0-codeはエージェントコーディングに深く最適化されており、マルチモーダル入力と256kのコンテキストウィンドウをサポートし、コーディング、ビジョン理解、エージェントワークフローに適しています。", "ru-RU": "Doubao-Seed-2.0-code глубоко оптимизирован для агентного кодирования, поддерживает мультимодальные входные данные и контекстное окно до 256k, подходящее для кодирования, понимания визуальной информации и рабочих процессов агентов." }, "price_history": [ { "date": "2026-07-06", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao Seed 2.0 Code" } ] }, { "slug": "bytedance/doubao-seed-2-0-lite", "model_name": "doubao-seed-2-0-lite", "display_name": "Doubao Seed 2.0 Lite", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.088235" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.132353" }, "prompt_0_128_0_256": { "unit": "per_M_tokens", "price": "0.264706" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "0.529412" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "0.794118" }, "completion_0_128_0_256": { "unit": "per_M_tokens", "price": "1.588235" }, "cache_read": { "unit": "per_M_tokens", "price": "0.017647" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.0025" } }, "provenance": { "base_charges": { "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_256": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_0_256": "lobehub-modelbank", "cache_read": "lobehub-modelbank", "cache_write_1h": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-seed-2.0-lite" } ], "released_at": "2026-02-15", "max_input_tokens": 256000, "max_output_tokens": 128000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true, "stream": true }, "intro": "Multimodal reasoning model for visual analysis, planning, and tool use", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": "2026-02", "family": "seed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bytedance/doubao-seed-2.0-lite", "doubao-seed-2.0-lite", "volcengine/doubao-seed-2-0-lite", "volcengine/doubao-seed-2.0-lite" ], "intro_i18n": { "zh-CN": "Doubao-Seed-2.0-lite 是一款全新的多模态深度推理模型，性价比更高，是常见任务的强力选择，支持高达 256k 的上下文窗口。", "zh-TW": "Doubao-Seed-2.0-lite 是一款全新的多模態深度推理模型，提供更高的性價比，是常見任務的強力選擇，支持高達 256k 的上下文窗口。", "ja-JP": "Doubao-Seed-2.0-liteは新しいマルチモーダル深層推論モデルで、優れた価値を提供し、一般的なタスクに適した強力な選択肢で、最大256kのコンテキストウィンドウを備えています。", "ru-RU": "Doubao-Seed-2.0-lite — это новая мультимодальная модель глубокого рассуждения, обеспечивающая лучшую ценность и отличный выбор для общих задач, с контекстным окном до 256k." }, "price_history": [ { "date": "2026-07-06", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao Seed 2.0 Lite" } ] }, { "slug": "bytedance/doubao-seed-2-0-mini", "model_name": "doubao-seed-2-0-mini", "display_name": "Doubao Seed 2.0 Mini", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.029412" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.058824" }, "prompt_0_128_0_256": { "unit": "per_M_tokens", "price": "0.117647" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "0.294118" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "0.588235" }, "completion_0_128_0_256": { "unit": "per_M_tokens", "price": "1.176471" }, "cache_read": { "unit": "per_M_tokens", "price": "0.005882" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.0025" } }, "provenance": { "base_charges": { "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_256": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_0_256": "lobehub-modelbank", "cache_read": "lobehub-modelbank", "cache_write_1h": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-seed-2.0-mini" } ], "released_at": "2026-02-15", "max_input_tokens": 256000, "max_output_tokens": 128000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true, "stream": true }, "intro": "Multimodal reasoning model for visual analysis, planning, and tool use", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": "2026-02", "family": "seed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bytedance/doubao-seed-2.0-mini", "doubao-seed-2.0-mini", "volcengine/doubao-seed-2-0-mini", "volcengine/doubao-seed-2.0-mini" ], "intro_i18n": { "zh-CN": "Doubao-Seed-2.0-mini 是一款轻量级模型，响应快速且性能优异，适合小型任务和高并发场景。", "zh-TW": "Doubao-Seed-2.0-mini 是一款輕量級模型，響應快速且性能卓越，適合小型任務和高併發場景。", "ja-JP": "Doubao-Seed-2.0-miniは軽量モデルで、高速応答と高性能を実現し、小規模タスクや高並列シナリオに適しています。", "ru-RU": "Doubao-Seed-2.0-mini — это легковесная модель с быстрым откликом и высокой производительностью, подходящая для небольших задач и сценариев с высокой конкуренцией." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Doubao Seed 2.0 Mini" } ] }, { "slug": "bytedance/doubao-seed-2-0-pro", "model_name": "doubao-seed-2-0-pro", "display_name": "Doubao Seed 2.0 Pro", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.470588" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.705882" }, "prompt_0_128_0_256": { "unit": "per_M_tokens", "price": "1.411765" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "2.352941" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "3.529412" }, "completion_0_128_0_256": { "unit": "per_M_tokens", "price": "7.058824" }, "cache_read": { "unit": "per_M_tokens", "price": "0.094118" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.0025" } }, "provenance": { "base_charges": { "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_256": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_0_256": "lobehub-modelbank", "cache_read": "lobehub-modelbank", "cache_write_1h": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-seed-2.0-pro" } ], "released_at": "2026-02-15", "max_input_tokens": 256000, "max_output_tokens": 128000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true, "stream": true }, "intro": "Multimodal reasoning model for visual analysis, planning, and tool use", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "knowledge_cutoff": "2026-02", "family": "seed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bytedance/doubao-seed-2.0-pro", "doubao-seed-2.0-pro", "volcengine/doubao-seed-2-0-pro", "volcengine/doubao-seed-2.0-pro" ], "intro_i18n": { "zh-CN": "Doubao-Seed-2.0-pro 是字节跳动的旗舰级 Agent 通用模型，在复杂任务规划和执行能力上实现了全方位飞跃。", "zh-TW": "Doubao-Seed-2.0-pro 是字節跳動的旗艦級 Agent 通用模型，在複雜任務規劃和執行能力上實現了全方位的飛躍。", "ja-JP": "Doubao-Seed-2.0-proはByteDanceのフラッグシップエージェント汎用モデルで、複雑なタスクの計画と実行能力において全方位的な飛躍を遂げています。", "ru-RU": "Doubao-Seed-2.0-pro — это флагманская универсальная модель агента от ByteDance, обеспечивающая всесторонние прорывы в планировании и выполнении сложных задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Doubao Seed 2.0 Pro" } ] }, { "slug": "bytedance/doubao-seed-2-1-pro", "model_name": "doubao-seed-2-1-pro", "display_name": "Doubao Seed 2.1 Pro", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.882353" }, "completion": { "unit": "per_M_tokens", "price": "4.411765" }, "cache_read": { "unit": "per_M_tokens", "price": "0.176471" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.0025" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank", "cache_write_1h": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-seed-2.1-pro" } ], "released_at": "2026-06-23", "max_input_tokens": 256000, "max_output_tokens": 128000, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "intro": "Higher-capability model in the Doubao Seed 2.1 family for agentic coding, long-context analysis, complex instruction following, and productivity workflows. Supports a 256k context window and up to 128k output tokens. Note: privacy and logging guarantees may be limited.", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "seed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bytedance/doubao-seed-2-1-pro", "bytedance/doubao-seed-2.1-pro", "doubao-seed-2.1-pro", "volcengine/doubao-seed-2.1-pro" ], "intro_i18n": { "zh-CN": "Doubao-Seed-2.1-pro 是字节跳动新一代旗舰级通用模型，针对编码、代理规划和长链任务执行进行了优化，并具备原生多模态理解能力。", "zh-TW": "Doubao-Seed-2.1-pro 是字節跳動新一代的旗艦代理通用模型，針對編碼、代理規劃和長鏈任務執行進行了優化，並具備原生多模態理解能力。", "ja-JP": "Doubao-Seed-2.1-proはByteDanceの次世代フラッグシップエージェント汎用モデルであり、コーディング、エージェント計画、長期タスクの実行に最適化され、ネイティブなマルチモーダル理解を備えています。", "ru-RU": "Doubao-Seed-2.1-pro — это флагманская универсальная модель нового поколения от ByteDance, оптимизированная для программирования, агентного планирования и выполнения задач с длинной цепочкой, с встроенным мультимодальным пониманием." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Doubao Seed 2.1 Pro" } ] }, { "slug": "bytedance/doubao-seed-2-1-turbo", "model_name": "doubao-seed-2-1-turbo", "display_name": "Doubao Seed 2.1 Turbo", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.441176" }, "completion": { "unit": "per_M_tokens", "price": "2.205882" }, "cache_read": { "unit": "per_M_tokens", "price": "0.088235" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.0025" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank", "cache_write_1h": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "doubao-seed-2.1-turbo" } ], "released_at": "2026-06-23", "max_input_tokens": 256000, "max_output_tokens": 128000, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "intro": "Fast, lower-cost model in the Doubao Seed 2.1 family for everyday chat, coding assistance, document work, and high-throughput productivity tasks. Supports a 256k context window and up to 128k output tokens. Note: privacy and logging guarantees may be limited.", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "seed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bytedance/doubao-seed-2-1-turbo", "bytedance/doubao-seed-2.1-turbo", "doubao-seed-2.1-turbo", "volcengine/doubao-seed-2.1-turbo" ], "intro_i18n": { "zh-CN": "Doubao-Seed-2.1-turbo 在高并发生产场景中实现了效率与性能的平衡，具备强大的推理和代理能力。", "zh-TW": "Doubao-Seed-2.1-turbo 在高併發生產場景中平衡了效率與性能，具備強大的推理和代理能力。", "ja-JP": "Doubao-Seed-2.1-turboは効率と性能のバランスを取り、高い同時実行性が求められる生産シナリオにおいて強力な推論能力とエージェント機能を提供します。", "ru-RU": "Doubao-Seed-2.1-turbo сочетает эффективность и производительность для высококонкурентных производственных сценариев с мощными возможностями рассуждения и агентного взаимодействия." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Doubao Seed 2.1 Turbo" } ] }, { "slug": "bytedance/doubao-seed-code", "model_name": "doubao-seed-code", "display_name": "Doubao Seed Code", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.176471" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.205882" }, "prompt_0_128_0_256": { "unit": "per_M_tokens", "price": "0.411765" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "1.176471" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "1.764706" }, "completion_0_128_0_256": { "unit": "per_M_tokens", "price": "2.352941" }, "cache_read": { "unit": "per_M_tokens", "price": "0.035294" }, "cache_write": { "unit": "per_M_tokens", "price": "0.0025" } }, "provenance": { "base_charges": { "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "prompt_0_128_0_256": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank", "completion_0_128_0_256": "lobehub-modelbank", "cache_read": "lobehub-modelbank", "cache_write": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 256000, "max_output_tokens": 32000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true, "stream": true }, "intro": "Coding model for repository understanding, refactors, and agentic engineering tasks", "released_at": "2025-11-11", "knowledge_cutoff": "2025-01", "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bytedance/doubao-seed-code", "volcengine/doubao-seed-code" ], "intro_i18n": { "zh-CN": "Doubao-Seed-Code 针对代理式编程深度优化，支持多模态输入（文本/图像/视频）和 256k 上下文窗口，兼容 Anthropic API，适用于编程、视觉理解与代理工作流。", "zh-TW": "Doubao-Seed-Code 專為代理式程式設計深度優化，支援多模態輸入（文字/圖片/影片）與 256k 上下文視窗，兼容 Anthropic API，適用於程式設計、視覺理解與代理工作流程。", "ja-JP": "Doubao-Seed-Code は、エージェント型コーディングに最適化されたモデルで、マルチモーダル入力（テキスト／画像／動画）と256kのコンテキストウィンドウに対応し、Anthropic APIと互換性があります。コーディング、視覚理解、エージェントワークフローに適しています。", "ru-RU": "Doubao-Seed-Code глубоко оптимизирован для агентного программирования, поддерживает мультимодальный ввод (текст/изображение/видео) и контекстное окно 256k, совместим с API Anthropic и подходит для программирования, понимания изображений и рабочих процессов агентов." }, "price_history": [ { "date": "2026-08-10", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao Seed Code" } ] }, { "slug": "bytedance/doubao-seed-evolving", "model_name": "doubao-seed-evolving", "display_name": "Doubao Seed Evolving", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.882353" }, "completion": { "unit": "per_M_tokens", "price": "4.411765" }, "cache_read": { "unit": "per_M_tokens", "price": "0.176471" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.0025" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "cache_read": "lobehub-modelbank", "cache_write_1h": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-06-23", "max_input_tokens": 256000, "max_output_tokens": 128000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "image_output": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "intro": "Rolling ByteDance Seed model for rapidly updated reasoning, coding, and agent capabilities", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "seed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "bytedance/doubao-seed-evolving", "volcengine/doubao-seed-evolving" ], "intro_i18n": { "zh-CN": "Doubao Seed Evolving 采用自我进化机制，每周持续更新，确保模型性能始终处于前沿水平。", "zh-TW": "Doubao Seed Evolving 採用自我進化機制，通過每週持續更新，保持模型性能處於最前沿。", "ja-JP": "Doubao Seed Evolvingは自己進化メカニズムを採用し、毎週の継続的なアップデートによってモデル性能を最先端に保ちます。", "ru-RU": "Doubao Seed Evolving использует механизм саморазвития с еженедельными обновлениями, чтобы поддерживать производительность модели на передовом уровне." }, "price_history": [ { "date": "2026-08-12", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-08-10", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Doubao Seed Evolving" } ] }, { "slug": "bytedance/doubao-seedance-1-0-pro-250528", "model_name": "doubao-seedance-1-0-pro-250528", "display_name": "Seedance 1.0 Pro", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_M_tokens", "price": "2.205882" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-05-28", "model_type": "video_generation", "capabilities": { "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Seedance 1.0 Pro 是一个支持多镜头叙事的视频生成基础模型，能够在多个维度上表现出色。该模型在语义理解和指令执行方面取得了突破，能够生成1080P高清视频，画面流畅、细节丰富、风格多样，并具有电影级视觉美感。", "zh-TW": "Seedance 1.0 Pro 是一款支持多鏡頭敘事的影片生成基礎模型，能在多個維度上展現強大性能。該模型在語義理解和指令執行方面實現突破，能生成1080P高清影片，具備流暢的動作、豐富的細節、多樣的風格以及電影級的視覺美感。", "ja-JP": "Seedance 1.0 Proは、マルチショットストーリーテリングをサポートする動画生成基盤モデルです。複数の次元で優れた性能を発揮します。このモデルは、意味理解と指示追従において画期的な進歩を遂げ、滑らかな動き、豊かなディテール、多様なスタイル、映画レベルの視覚美学を備えた1080P高解像度動画を生成することが可能です。", "ru-RU": "Seedance 1.0 Pro — это базовая модель генерации видео, поддерживающая многокадровое повествование. Она демонстрирует высокую производительность по нескольким параметрам. Модель достигает прорыва в семантическом понимании и следовании инструкциям, что позволяет ей создавать видео в формате 1080P с плавным движением, богатыми деталями, разнообразными стилями и визуальной эстетикой кинематографического уровня." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Seedance 1.0 Pro" } ] }, { "slug": "bytedance/doubao-seedance-1-0-pro-fast-251015", "model_name": "doubao-seedance-1-0-pro-fast-251015", "display_name": "Seedance 1.0 Pro Fast", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_M_tokens", "price": "0.617647" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-10-15", "model_type": "video_generation", "capabilities": { "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Seedance 1.0 Pro Fast 是一个综合模型，旨在降低成本的同时最大化性能，在视频生成质量、速度和价格之间实现卓越平衡。它继承了 Seedance 1.0 Pro 的核心优势，同时提供更快的生成速度和更具竞争力的价格，为创作者带来效率与成本的双重优化。", "zh-TW": "Seedance 1.0 Pro Fast 是一款綜合模型，旨在降低成本的同時最大化性能，實現影片生成品質、速度與價格的卓越平衡。它繼承了 Seedance 1.0 Pro 的核心優勢，並提供更快的生成速度和更具競爭力的價格，為創作者帶來效率與成本的雙重優化。", "ja-JP": "Seedance 1.0 Pro Fastは、コストを最小化しながら性能を最大化することを目的とした包括的なモデルで、動画生成品質、速度、価格の優れたバランスを実現します。Seedance 1.0 Proの主要な強みを継承しつつ、より高速な生成速度と競争力のある価格を提供し、クリエイターに効率とコストの二重最適化をもたらします。", "ru-RU": "Seedance 1.0 Pro Fast — это универсальная модель, разработанная для минимизации затрат при максимизации производительности, достигая отличного баланса между качеством генерации видео, скоростью и ценой. Она наследует основные преимущества Seedance 1.0 Pro, предлагая при этом более высокую скорость генерации и более конкурентоспособные цены, обеспечивая создателям двойную оптимизацию эффективности и стоимости." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Seedance 1.0 Pro Fast" } ] }, { "slug": "bytedance/doubao-seedance-1-5-pro-251215", "model_name": "doubao-seedance-1-5-pro-251215", "display_name": "Seedance 1.5 Pro", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "video_output_false": { "unit": "per_M_tokens", "price": "1.176471" }, "video_output_true": { "unit": "per_M_tokens", "price": "2.352941" } }, "provenance": { "base_charges": { "video_output_false": "lobehub-modelbank", "video_output_true": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-12-15", "model_type": "video_generation", "capabilities": { "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "字节跳动的 Seedance 1.5 Pro 支持文本生成视频、图像生成视频（首帧、首尾帧）以及与视觉同步的音频生成。", "zh-TW": "由字節跳動推出的 Seedance 1.5 Pro 支持文字轉影片、圖像轉影片（第一幀、首尾幀）以及與視覺同步的音頻生成。", "ja-JP": "ByteDanceのSeedance 1.5 Proは、テキストから動画、画像から動画（初期フレーム、初期+最終フレーム）、および視覚と同期した音声生成をサポートします。", "ru-RU": "Seedance 1.5 Pro от ByteDance поддерживает текст-видео, изображение-видео (первый кадр, первый+последний кадр) и генерацию аудио, синхронизированного с визуальными эффектами." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Seedance 1.5 Pro" } ] }, { "slug": "bytedance/doubao-seedance-2-0-260128", "model_name": "doubao-seedance-2-0-260128", "display_name": "Seedance 2.0", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_M_tokens", "price": "5.441176" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-01-28", "model_type": "video_generation", "capabilities": { "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "字节跳动的Seedance 2.0是最强大的视频生成模型，支持多模态参考视频生成、视频编辑、视频扩展、文本转视频和图像转视频，并同步音频。", "zh-TW": "字節跳動的Seedance 2.0是最強大的影像生成模型，支持多模態參考影像生成、影像編輯、影像擴展、文字生成影像及影像生成影像，並同步音頻。", "ja-JP": "ByteDanceのSeedance 2.0は、最も強力なビデオ生成モデルで、マルチモーダル参照ビデオ生成、ビデオ編集、ビデオ拡張、テキストからビデオ、画像からビデオへの変換を同期音声付きでサポートします。", "ru-RU": "Seedance 2.0 от ByteDance — самая мощная модель генерации видео, поддерживающая мультимодальную генерацию видео по ссылке, редактирование видео, расширение видео, преобразование текста в видео и изображения в видео с синхронизированным звуком." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Seedance 2.0" } ] }, { "slug": "bytedance/doubao-seedance-2-0-fast-260128", "model_name": "doubao-seedance-2-0-fast-260128", "display_name": "Seedance 2.0 Fast", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_M_tokens", "price": "6.764706" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-01-28", "model_type": "video_generation", "capabilities": { "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "字节跳动的Seedance 2.0 Fast提供与Seedance 2.0相同的功能，但生成速度更快，价格更具竞争力。", "zh-TW": "字節跳動的Seedance 2.0 Fast提供與Seedance 2.0相同的功能，但生成速度更快，價格更具競爭力。", "ja-JP": "ByteDanceのSeedance 2.0 Fastは、Seedance 2.0と同じ機能を提供しながら、より高速な生成速度と競争力のある価格を実現します。", "ru-RU": "Seedance 2.0 Fast от ByteDance предлагает те же возможности, что и Seedance 2.0, с более высокой скоростью генерации и более конкурентоспособной ценой." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Seedance 2.0 Fast" } ] }, { "slug": "bytedance/doubao-seedream-4-0-250828", "model_name": "doubao-seedream-4-0-250828", "display_name": "Seedream 4.0", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.029412" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-09-09", "model_type": "image_generation", "capabilities": { "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Seedream 4.0 是字节跳动 Seed 推出的图像生成模型，支持文本与图像输入，具备高度可控的高质量图像生成能力。可根据文本提示生成图像。", "zh-TW": "Seedream 4.0 是字節跳動 Seed 團隊推出的圖像生成模型，支援文字與圖像輸入，實現高度可控、高品質的圖像生成。可根據文字提示生成圖像。", "ja-JP": "Seedream 4.0 は ByteDance Seed による画像生成モデルで、テキストと画像入力に対応し、高品質かつ制御性の高い画像生成を実現します。テキストプロンプトから画像を生成します。", "ru-RU": "Seedream 4.0 — модель генерации изображений от ByteDance Seed, поддерживающая ввод текста и изображений с высококачественной и управляемой генерацией. Генерирует изображения по текстовым подсказкам." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Seedream 4.0" } ] }, { "slug": "bytedance/doubao-seedream-4-5-251128", "model_name": "doubao-seedream-4-5-251128", "display_name": "Seedream 4.5", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.036765" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-11-28", "model_type": "image_generation", "capabilities": { "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Seedream 4.5是字节跳动最新的多模态图像模型，集成了文本生成图像、图像生成图像和批量图像生成功能，同时具备常识和推理能力。与之前的4.0版本相比，生成质量显著提升，编辑一致性和多图融合效果更好。它对视觉细节的控制更加精确，能够更自然地生成小文字和小面部，并实现更和谐的布局和色彩，提升整体美感。", "zh-TW": "Seedream 4.5 是字節跳動最新的多模態圖像模型，整合了文本生成圖像、圖像生成圖像和批量圖像生成功能，同時融入了常識和推理能力。與之前的 4.0 版本相比，生成質量顯著提升，編輯一致性和多圖融合效果更好。它對視覺細節的控制更加精確，能更自然地生成小字和小臉，並實現更和諧的佈局和色彩，提升整體美感。", "ja-JP": "Seedream 4.5はByteDanceの最新マルチモーダル画像モデルで、テキストから画像生成、画像間変換、バッチ画像生成機能を統合し、常識と推論能力を組み込んでいます。前バージョン4.0と比較して、生成品質が大幅に向上し、編集の一貫性や複数画像の融合が改善されています。視覚的な詳細の制御がより正確になり、小さなテキストや顔を自然に生成し、レイアウトや色彩の調和が向上し、全体的な美観が強化されています。", "ru-RU": "Seedream 4.5 — это последняя мультимодальная модель изображений от ByteDance, объединяющая возможности преобразования текста в изображение, изображения в изображение и пакетной генерации изображений, а также включающая здравый смысл и способности к рассуждению. По сравнению с предыдущей версией 4.0, она обеспечивает значительно улучшенное качество генерации, лучшую согласованность редактирования и слияние нескольких изображений. Модель предлагает более точный контроль над визуальными деталями, естественно воспроизводя мелкий текст и лица, а также достигает более гармоничного макета и цветовой палитры, улучшая общую эстетику." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Seedream 4.5" } ] }, { "slug": "bytedance/doubao-seedream-5-0-260128", "model_name": "doubao-seedream-5-0-260128", "display_name": "Seedream 5.0 Lite", "vendor": "bytedance", "pricing": [ { "provider": "bytedance", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.032353" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-01-28", "model_type": "image_generation", "capabilities": { "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Doubao-Seedream-5.0-lite是字节跳动最新的图像生成模型。首次集成在线检索功能，能够结合实时网络信息，提升生成图像的时效性。模型智能性也得到升级，能够精确解析复杂指令和视觉内容。此外，它在专业场景中的全球知识覆盖、参考一致性和生成质量方面均有提升，更好地满足企业级视觉创作需求。", "zh-TW": "Doubao-Seedream-5.0-lite 是字節跳動最新的圖像生成模型。首次整合了在線檢索功能，能夠結合實時網絡信息，提升生成圖像的時效性。模型的智能性也得到了升級，能夠精確解讀複雜指令和視覺內容。此外，它在專業場景中的全球知識覆蓋、參考一致性和生成質量方面均有改進，更好地滿足企業級視覺創作需求。", "ja-JP": "Doubao-Seedream-5.0-liteはByteDanceの最新画像生成モデルです。初めてオンライン検索機能を統合し、リアルタイムのウェブ情報を取り入れることで生成画像のタイムリー性を向上させています。モデルの知能もアップグレードされ、複雑な指示や視覚コンテンツを正確に解釈できるようになりました。また、専門的なシナリオでのグローバルな知識カバレッジ、一貫性、生成品質が向上し、企業レベルの視覚制作ニーズにより適合しています。", "ru-RU": "Doubao-Seedream-5.0-lite — это последняя модель генерации изображений от ByteDance. Впервые она интегрирует возможности онлайн-поиска, что позволяет использовать информацию в реальном времени и улучшать актуальность создаваемых изображений. Интеллект модели также был обновлен, что позволяет точно интерпретировать сложные инструкции и визуальный контент. Кроме того, она предлагает улучшенное покрытие глобальных знаний, согласованность ссылок и качество генерации в профессиональных сценариях, лучше удовлетворяя потребности корпоративного визуального творчества." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Seedream 5.0 Lite" } ] }, { "slug": "bytedance/glm-4-7-251222", "model_name": "glm-4-7-251222", "display_name": "glm-4-7-251222", "vendor": "bytedance", "pricing": [ { "provider": "volcengine", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 204800, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "bytedance/kimi-k2-thinking-251104", "model_name": "kimi-k2-thinking-251104", "display_name": "kimi-k2-thinking-251104", "vendor": "bytedance", "pricing": [ { "provider": "volcengine", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 229376, "max_output_tokens": 32768, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "cohere/c4ai-aya-expanse-32b", "model_name": "c4ai-aya-expanse-32b", "display_name": "Aya Expanse 32B", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+truefoundry+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "cross_checked" } } ], "intro": "Open multilingual model optimized for generation across 23 languages", "released_at": "2024-10-24", "max_input_tokens": 128000, "max_output_tokens": 4000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "open_weights": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Aya Expanse 是一款高性能的 320 亿参数多语言模型，结合指令微调、数据套利、偏好训练和模型融合，性能媲美单语模型，支持 23 种语言。", "zh-TW": "Aya Expanse 是一款高效能的 320 億參數多語言模型，透過指令微調、資料仲裁、偏好訓練與模型融合，達到媲美單語模型的表現。支援 23 種語言。", "ja-JP": "Aya Expanseは、32Bパラメータの高性能多言語モデルで、指示チューニング、データアービトラージ、好みの学習、モデル統合を活用し、単言語モデルに匹敵する性能を実現しています。23言語に対応しています。", "ru-RU": "Aya Expanse — это высокопроизводительная многоязычная модель с 32 миллиардами параметров, использующая настройку по инструкциям, арбитраж данных, обучение предпочтениям и объединение моделей, чтобы конкурировать с монолингвальными моделями. Поддерживает 23 языка." }, "price_history": [ { "date": "2026-07-02", "kind": "listed", "note": "Aya Expanse 32B" } ] }, { "slug": "cohere/c4ai-aya-vision-32b", "model_name": "c4ai-aya-vision-32b", "display_name": "Aya Vision 32B", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+truefoundry+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "prompt from lobehub-modelbank conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from lobehub-modelbank conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Open multilingual vision model for OCR, visual reasoning, and image question answering", "released_at": "2025-03-04", "max_input_tokens": 16000, "max_output_tokens": 4000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "capabilities": { "vision": true, "open_weights": true, "pdf_input": true }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Aya Vision 是一款先进的多模态模型，在语言、文本和视觉基准测试中表现出色。该 320 亿参数版本专注于顶级多语言性能，支持 23 种语言。", "zh-TW": "Aya Vision 是一款先進的多模態模型，在語言、文字與視覺基準測試中表現優異。此 320 億參數版本專注於頂級多語言效能，支援 23 種語言。", "ja-JP": "Aya Visionは、最先端のマルチモーダルモデルで、言語、テキスト、ビジョンの主要ベンチマークで高い性能を発揮します。23言語に対応しており、この32Bバージョンは多言語性能に特化しています。", "ru-RU": "Aya Vision — это передовая мультимодальная модель, демонстрирующая высокие результаты на ключевых языковых, текстовых и визуальных бенчмарках. Поддерживает 23 языка. Версия с 32 миллиардами параметров ориентирована на выдающуюся многоязычную производительность." }, "price_history": [ { "date": "2026-07-02", "kind": "listed", "note": "Aya Vision 32B" } ] }, { "slug": "cohere/command", "model_name": "command", "display_name": "command", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 4096, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": {}, "intro": "Command is an instruction-following conversational model that performs language tasks with high quality, more reliably and with a longer context than our base generative models.", "modalities": { "input": [ "text" ], "output": [] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere/command" ] }, { "slug": "cohere/command-a", "model_name": "command-a", "display_name": "Command A", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases.\nCompared to other leading proprietary and open-weights models Command A delivers maximum performance with minimum hardware costs, excelling on business-critical agentic and multilingual tasks.", "capabilities": { "function_calling": true, "structured_output": true, "open_weights": true, "stream": true }, "released_at": "2025-03-13", "knowledge_cutoff": "2024-08", "max_input_tokens": 256000, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "command-a", "model_type": "text_generation", "deprecated": true, "benchmarks": { "intelligence_index": 22.8, "coding_index": 27.8, "agentic_index": 9.2 }, "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere/command-a" ], "intro_i18n": { "zh-CN": "Command A 是 Cohere 迄今为止最强大的模型，擅长工具使用、智能体、RAG 和多语言场景。支持 256K 上下文长度，仅需两块 GPU 即可运行，吞吐量比 Command R+ 08-2024 提高 150%。", "zh-TW": "Command A 是 Cohere 目前最強大的模型，擅長工具使用、代理任務、RAG 與多語言應用。具備 256K 上下文長度，僅需兩張 GPU 即可運行，吞吐量比 Command R+ 08-2024 高出 150%。", "ja-JP": "Command AはCohere史上最も強力なモデルであり、ツール使用、エージェント、RAG、多言語ユースケースに優れています。256Kのコンテキスト長を持ち、わずか2つのGPUで動作し、Command R+（2024年8月版）と比べて150%のスループット向上を実現します。", "ru-RU": "Command A — самая мощная модель Cohere на сегодняшний день, превосходно справляющаяся с использованием инструментов, агентами, RAG и многоязычными задачами. Поддерживает контекст длиной 256K, работает всего на двух GPU и обеспечивает на 150% большую пропускную способность по сравнению с Command R+ 08-2024." }, "price_history": [ { "date": "2026-07-15", "kind": "limit", "old": "8000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Command A" } ] }, { "slug": "cohere/command-a-03-2025", "model_name": "command-a-03-2025", "display_name": "Command A", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+litellm+truefoundry+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Cohere command model for multilingual enterprise agents, tools, and chat", "released_at": "2025-03-13", "knowledge_cutoff": "2024-06", "max_input_tokens": 256000, "max_output_tokens": 8000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "command-a", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "model_type": "text_generation", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere/command-a-03-2025" ], "intro_i18n": { "zh-CN": "Command A 是我们迄今为止最强大的模型，擅长工具使用、智能体、RAG 和多语言场景。支持 256K 上下文窗口，仅需两块 GPU 即可运行，吞吐量比 Command R+ 08-2024 提高 150%。", "zh-TW": "Command A 是我們目前最強大的模型，擅長工具使用、代理任務、RAG 與多語言場景。具備 256K 上下文視窗，僅需兩張 GPU 即可運行，吞吐量比 Command R+ 08-2024 高出 150%。", "ja-JP": "Command Aはこれまでで最も高性能なモデルであり、ツール使用、エージェント、RAG、多言語シナリオに優れています。256Kのコンテキストウィンドウを持ち、わずか2つのGPUで動作し、Command R+（2024年8月版）と比べて150%のスループット向上を実現します。", "ru-RU": "Command A — наша самая мощная модель на сегодняшний день, превосходно справляющаяся с использованием инструментов, агентами, RAG и многоязычными задачами. Поддерживает контекст до 256K, работает на двух GPU и обеспечивает на 150% большую пропускную способность по сравнению с Command R+ 08-2024." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "cohere/command-a-plus-05-2026", "model_name": "command-a-plus-05-2026", "display_name": "Command A Plus", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "prompt from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Cohere's stronger command model for multilingual agents and enterprise workflows", "released_at": "2026-05-20", "knowledge_cutoff": "2025-04", "max_input_tokens": 128000, "max_output_tokens": 64000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "command-a", "reasoning_config": { "budget_min": 1 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Command A+ 是 Cohere 的首个专家混合模型，将视觉输入支持、代理能力、推理能力和世界级翻译能力集成于一体。支持 48 种语言，可在 1× B200 或 2× H100 GPU 上运行。", "zh-TW": "Command A+ 是 Cohere 的首款專家混合模型，將視覺輸入支持、代理性、推理和世界級翻譯能力結合於一體。它支持 48 種語言，並可在 1× B200 或 2× H100 GPU 上運行。", "ja-JP": "Command A+は、Cohereの初のMixture of Expertsモデルで、ビジョン入力サポート、エージェント機能、推論、そして世界クラスの翻訳能力を1つのモデルに統合しています。48言語をサポートし、1× B200または2× H100 GPUで動作可能です。", "ru-RU": "Command A+ — это первая модель Mixture of Experts от Cohere, объединяющая поддержку визуального ввода, агентность, рассуждение и мирового уровня возможности перевода в одной модели. Она поддерживает 48 языков и может работать на 1× B200 или 2× H100 GPU." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "cohere/command-a-reasoning-08-2025", "model_name": "command-a-reasoning-08-2025", "display_name": "Command A Reasoning", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+truefoundry+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "prompt from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Cohere reasoning model for multilingual enterprise agents, tools, and complex workflows", "released_at": "2025-08-21", "knowledge_cutoff": "2024-06", "max_input_tokens": 256000, "max_output_tokens": 32000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "command-a", "reasoning_config": { "budget_min": 1 }, "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "cohere/command-a-translate-08-2025", "model_name": "command-a-translate-08-2025", "display_name": "Command A Translate", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+truefoundry+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "prompt from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Translation model for multilingual conversion, localization, and cross-language workflows", "released_at": "2025-08-28", "knowledge_cutoff": "2024-06", "max_input_tokens": 8000, "max_output_tokens": 8000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "command-a", "capabilities": { "function_calling": true, "structured_output": true, "open_weights": true, "stream": true }, "model_type": "text_generation", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "cohere/command-a-vision-07-2025", "model_name": "command-a-vision-07-2025", "display_name": "Command A Vision", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+truefoundry+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "prompt from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Cohere vision model for multilingual document analysis, OCR, and image understanding", "released_at": "2025-07-31", "knowledge_cutoff": "2024-06", "max_input_tokens": 128000, "max_output_tokens": 8000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "command-a", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "vision_understanding", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "cohere/command-light", "model_name": "command-light", "display_name": "command-light", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 4096, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "cohere/command-light-nightly", "model_name": "command-light-nightly", "display_name": "command-light-nightly", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Command Light Nightly" } ] }, { "slug": "cohere/command-nightly", "model_name": "command-nightly", "display_name": "command-nightly", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 4096, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-02", "kind": "capability", "note": "function_calling: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" } ] }, { "slug": "cohere/command-r", "model_name": "command-r", "display_name": "command-r", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+pydantic-prices+portkey+pricetoken", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "pricetoken", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "prompt from pricetoken conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pricetoken", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from pricetoken conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 128000, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "function_calling": true, "structured_output": true, "stream": true, "open_weights": true }, "intro": "Command-R is a 35B parameter model that performs conversational language tasks at a higher quality, more reliably, and with a longer context than previous models. It can be used for complex workflows like code generation, retrieval augmented generation (RAG), tool use, and agents.", "released_at": "2024-03-01", "deprecated": true, "status": "deprecated", "deprecation_date": "2026-08-19", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "Command", "knowledge_cutoff": "2024-04", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere.command-r-v1:0", "cohere/command-r" ], "intro_i18n": { "zh-CN": "Command R 是一款针对聊天和长上下文任务优化的大语言模型，适用于动态交互和知识管理。", "zh-TW": "Command R 是一款針對聊天與長上下文任務優化的大型語言模型，適合動態互動與知識管理。", "ja-JP": "Command Rは、チャットや長文コンテキストタスクに最適化されたLLMであり、動的な対話や知識管理に適しています。", "ru-RU": "Command R — LLM, оптимизированная для чатов и задач с длинным контекстом, идеально подходящая для динамичного взаимодействия и управления знаниями." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "cohere/command-r-08-2024", "model_name": "command-r-08-2024", "display_name": "Command R", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+litellm+truefoundry+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Cohere retrieval model for long-context chat and enterprise RAG workflows", "released_at": "2024-08-30", "knowledge_cutoff": "2024-06", "max_input_tokens": 128000, "max_output_tokens": 4000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "command-r", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "open_weights": true, "stream": true }, "model_type": "text_generation", "parameters": { "unsupported": [ "temperature" ] }, "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere/command-r-08-2024" ], "intro_i18n": { "zh-CN": "command-r-08-2024 是 2024 年 8 月发布的 Command R 模型更新版本。", "zh-TW": "command-r-08-2024 是 2024 年 8 月發布的 Command R 模型更新版本。", "ja-JP": "command-r-08-2024は、2024年8月にリリースされたCommand Rの更新版です。", "ru-RU": "command-r-08-2024 — обновлённая модель Command R, выпущенная в августе 2024 года." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "cohere/command-r-plus", "model_name": "command-r-plus", "display_name": "command-r-plus", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+pydantic-prices+portkey+pricetoken", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 128000, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "function_calling": true, "structured_output": true, "stream": true, "open_weights": true }, "intro": "Command R+ is a new, 104B-parameter LLM from Cohere. It's useful for roleplay, general consumer usecases, and Retrieval Augmented Generation (RAG).", "released_at": "2024-08-01", "deprecated": true, "status": "deprecated", "deprecation_date": "2026-08-19", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2024-04", "family": "command-r", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere.command-r-plus-v1:0", "cohere/command-r-plus" ], "intro_i18n": { "zh-CN": "Command R+ 是一款高性能大语言模型，专为真实企业场景和复杂应用设计。", "zh-TW": "Command R+ 是一款高效能的大型語言模型，專為真實企業場景與複雜應用而設計。", "ja-JP": "Command R+は、実際のエンタープライズシナリオや複雑なアプリケーションに対応する高性能LLMです。", "ru-RU": "Command R+ — высокопроизводительная LLM, предназначенная для реальных корпоративных сценариев и сложных приложений." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "cohere/command-r-plus-08-2024", "model_name": "command-r-plus-08-2024", "display_name": "Command R+", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+litellm+truefoundry+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from ai-model-directory conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.6" }, "message": "completion from ai-model-directory conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Cohere's RAG workhorse for long-context enterprise search and tool use", "released_at": "2024-08-30", "knowledge_cutoff": "2024-06", "max_input_tokens": 128000, "max_output_tokens": 4000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "command-r", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "model_type": "text_generation", "parameters": { "unsupported": [ "temperature" ] }, "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere/command-r-plus-08-2024" ], "intro_i18n": { "zh-CN": "Command R+ 是一款遵循指令的聊天模型，质量更高、可靠性更强、上下文窗口更长，特别适用于复杂的 RAG 工作流和多步骤工具使用。", "zh-TW": "Command R+ 是一款遵循指令的聊天模型，品質更高、穩定性更強，並具備比前代模型更長的上下文視窗。最適合用於複雜的 RAG 工作流程與多步驟工具使用。", "ja-JP": "Command R+は、従来モデルよりも高品質で信頼性が高く、長いコンテキストウィンドウを持つ命令追従型チャットモデルです。複雑なRAGワークフローや多段階のツール使用に最適です。", "ru-RU": "Command R+ — модель чата, следящая за инструкциями, с более высоким качеством, надёжностью и увеличенным окном контекста по сравнению с предыдущими версиями. Идеальна для сложных RAG-процессов и многошагового использования инструментов." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "cohere/command-r7b", "model_name": "command-r7b", "display_name": "command-r7b", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.0375" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "intro": "Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning and multiple steps.", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "command-r7b" } ] }, { "slug": "cohere/command-r7b-12-2024", "model_name": "command-r7b-12-2024", "display_name": "Command R7B", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+litellm+truefoundry+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.0375" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Cohere retrieval model for long-context chat and enterprise RAG workflows", "released_at": "2024-12-02", "knowledge_cutoff": "2024-06", "max_input_tokens": 128000, "max_output_tokens": 4000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "command-r", "capabilities": { "function_calling": true, "structured_output": true, "open_weights": true, "stream": true }, "docs_url": "https://docs.cohere.com/v2/docs/command-r7b", "model_type": "text_generation", "parameters": { "unsupported": [ "temperature" ] }, "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere/command-r7b-12-2024" ], "intro_i18n": { "zh-CN": "command-r7b-12-2024 是 2024 年 12 月发布的小型高效更新版本，擅长 RAG、工具使用和需要复杂多步骤推理的智能体任务。", "zh-TW": "command-r7b-12-2024 是 2024 年 12 月發布的小型高效更新版本，擅長需要複雜多步推理的 RAG、工具使用與代理任務。", "ja-JP": "command-r7b-12-2024は、2024年12月にリリースされた小型かつ効率的なアップデートであり、複雑な多段階推論を必要とするRAG、ツール使用、エージェントタスクに優れています。", "ru-RU": "command-r7b-12-2024 — компактное и эффективное обновление, выпущенное в декабре 2024 года. Отлично справляется с задачами RAG, использования инструментов и агентов, требующих сложного многошагового рассуждения." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "cohere/command-r7b-arabic-02-2025", "model_name": "command-r7b-arabic-02-2025", "display_name": "Command R7B Arabic", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+truefoundry+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.0375" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Open Command R model optimized for Arabic enterprise chat, RAG, and cultural knowledge", "released_at": "2025-02-27", "knowledge_cutoff": "2024-06", "max_input_tokens": 128000, "max_output_tokens": 4000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "command-r", "capabilities": { "function_calling": true, "structured_output": true, "open_weights": true, "stream": true }, "model_type": "text_generation", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "cohere/embed-english-light-v2.0", "model_name": "embed-english-light-v2.0", "display_name": "embed-english-light-v2.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 1024, "deprecated": true, "model_type": "text_embedding", "deprecation_date": "2026-04-04", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "cohere/embed-english-light-v3.0", "model_name": "embed-english-light-v3.0", "display_name": "embed-english-light-v3.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 1024, "model_type": "multimodal_embedding", "capabilities": { "vision": true }, "modalities": { "input": [ "text", "image" ], "output": [ "embedding" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" } ] }, { "slug": "cohere/embed-english-v2.0", "model_name": "embed-english-v2.0", "display_name": "embed-english-v2.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 4096, "deprecated": true, "model_type": "text_embedding", "deprecation_date": "2026-04-04", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "cohere/embed-english-v3.0", "model_name": "embed-english-v3.0", "display_name": "embed-english-v3.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_input": { "unit": "per_image", "price": "0.0001" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 1024, "model_type": "multimodal_embedding", "capabilities": { "vision": true }, "modalities": { "input": [ "text", "image" ], "output": [ "embedding" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere/embed-english-v3.0" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" } ] }, { "slug": "cohere/embed-multilingual-light-v3.0", "model_name": "embed-multilingual-light-v3.0", "display_name": "embed-multilingual-light-v3.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "100" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "100" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 1024, "model_type": "multimodal_embedding", "capabilities": { "vision": true }, "modalities": { "input": [ "text", "image" ], "output": [ "embedding" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" } ] }, { "slug": "cohere/embed-multilingual-v2.0", "model_name": "embed-multilingual-v2.0", "display_name": "embed-multilingual-v2.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 768, "deprecated": true, "model_type": "text_embedding", "deprecation_date": "2026-04-04", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "cohere/embed-multilingual-v3.0", "model_name": "embed-multilingual-v3.0", "display_name": "embed-multilingual-v3.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 1024, "model_type": "multimodal_embedding", "capabilities": { "vision": true }, "modalities": { "input": [ "text", "image" ], "output": [ "embedding" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere/embed-multilingual-v3.0" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" } ] }, { "slug": "cohere/embed-v4.0", "model_name": "embed-v4.0", "display_name": "embed-v4.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "litellm+pydantic-prices+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.12" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 128000, "model_type": "multimodal_embedding", "capabilities": { "vision": true, "pdf_input": true }, "intro": "Embed v4.0 is a state-of-the-art embedding model designed for precise retrieval across noisy, multilingual, and multimodal data.", "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "embedding" ] }, "released_at": "2025-04-15", "max_output_tokens": 1536, "family": "cohere-embed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere/embed-v4.0" ], "intro_i18n": { "zh-CN": "一个可将文本、图像或混合内容分类或转换为嵌入向量的模型。", "zh-TW": "一款可將文字、圖像或混合內容分類或轉換為嵌入向量的模型。", "ja-JP": "テキスト、画像、または混合コンテンツを分類または埋め込みに変換するモデルです。", "ru-RU": "Модель, преобразующая текст, изображения или смешанный контент в эмбеддинги для классификации или других задач." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "cohere/north-mini-code-1-0", "model_name": "north-mini-code-1-0", "display_name": "North Mini Code", "vendor": "cohere", "pricing": [ { "provider": "cohere", "provider_name": "Cohere", "official": true, "source": "models-dev+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Cohere coding model for practical software engineering and agentic edits", "released_at": "2026-06-09", "knowledge_cutoff": "2025-09", "max_input_tokens": 256000, "max_output_tokens": 64000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "north", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "open_weights": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "cohere/rerank-english-v2.0", "model_name": "rerank-english-v2.0", "display_name": "rerank-english-v2.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_request", "price": "0.002" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_request", "price": "0.002" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1000" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_output_tokens": 4096, "model_type": "text_rerank", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "rerank-english-v2.0" } ] }, { "slug": "cohere/rerank-english-v3.0", "model_name": "rerank-english-v3.0", "display_name": "rerank-english-v3.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_request", "price": "0.002" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_request", "price": "0.002" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2000" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 4096, "modalities": { "input": [ "text" ], "output": [] }, "model_type": "text_rerank", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "rerank-english-v3.0" } ] }, { "slug": "cohere/rerank-multilingual-v2.0", "model_name": "rerank-multilingual-v2.0", "display_name": "rerank-multilingual-v2.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_request", "price": "0.002" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_request", "price": "0.002" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1000" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_output_tokens": 4096, "model_type": "text_rerank", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "rerank-multilingual-v2.0" } ] }, { "slug": "cohere/rerank-multilingual-v3.0", "model_name": "rerank-multilingual-v3.0", "display_name": "rerank-multilingual-v3.0", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_request", "price": "0.002" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_request", "price": "0.002" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2000" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 4096, "modalities": { "input": [ "text" ], "output": [] }, "model_type": "text_rerank", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "rerank-multilingual-v3.0" } ] }, { "slug": "cohere/rerank-v3.5", "model_name": "rerank-v3.5", "display_name": "Cohere Rerank 3.5", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_request", "price": "0.002" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_request", "price": "0.002" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2000" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 4096, "modalities": { "input": [ "text" ], "output": [] }, "model_type": "text_rerank", "capabilities": {}, "intro": "Reranking model for improving retrieval quality in search and recommendation systems", "released_at": "2024-12-02", "max_output_tokens": 4096, "family": "o", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "cohere/rerank-v3.5" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Cohere Rerank 3.5" } ] }, { "slug": "cohere/rerank-v4.0-pro", "model_name": "rerank-v4.0-pro", "display_name": "rerank-v4.0-pro", "vendor": "cohere", "pricing": [ { "provider": "cohere", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_request", "price": "0.0025" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "portkey" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_request", "price": "0.0025" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2500" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_rerank", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-09", "kind": "delisted", "note": "rerank-v4.0-pro" }, { "date": "2026-07-09", "kind": "listed", "note": "rerank-v4.0-pro" }, { "date": "2026-07-03", "kind": "listed", "note": "rerank-v4.0-pro" } ] }, { "slug": "deepseek/deepseek-chat", "model_name": "deepseek-chat", "display_name": "DeepSeek Chat", "vendor": "deepseek", "pricing": [ { "provider": "deepseek", "provider_name": "DeepSeek", "official": true, "source": "models-dev+litellm+pydantic-prices+helicone-registry+portkey+llmdb+pricetoken+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.14" }, "completion": { "unit": "per_M_tokens", "price": "0.28" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0028" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.28" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.42" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.028" }, "message": "cache_read from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.28" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.42" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.028" }, "message": "cache_read from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.135" }, "message": "prompt from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.55" }, "message": "completion from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.035" }, "message": "cache_read from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.56" }, "message": "prompt from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.68" }, "message": "completion from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.07" }, "message": "cache_read from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.28" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.42" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.028" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.27" }, "message": "prompt from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.1" }, "message": "completion from llm-prices-www conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "DeepSeek chat model for instruction following, coding, and analysis", "released_at": "2025-12-01", "knowledge_cutoff": "2025-09", "max_input_tokens": 1000000, "max_output_tokens": 384000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "deepseek", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "parallel_function_calling": true, "assistant_prefill": true, "stream": true }, "docs_url": "https://api-docs.deepseek.com/quick_start/pricing", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "parameters": { "supported": [ "frequency_penalty", "function_call", "functions", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "stream", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "deprecated": true, "status": "deprecated", "aliases": [ "deepseek/deepseek-chat" ], "intro_i18n": { "zh-CN": "一个结合了通用能力和代码能力的新开源模型。它保留了聊天模型的通用对话能力和编码模型的强大编程能力，并具有更好的偏好对齐。DeepSeek-V2.5 还改进了写作和指令遵循能力。", "zh-TW": "一款結合通用能力與程式能力的開源模型。它保留了聊天模型的通用對話能力和程式模型的強大編程能力，並且在偏好對齊方面表現更佳。DeepSeek-V2.5 還改進了寫作和指令遵循能力。", "ja-JP": "一般的な対話能力とコード能力を組み合わせた新しいオープンソースモデルです。チャットモデルの一般的な対話能力と、コーダーモデルの強力なコーディング能力を保持し、より良い嗜好調整を実現しています。DeepSeek-V2.5は、文章作成や指示の追従能力も向上させています。", "ru-RU": "Новая модель с открытым исходным кодом, объединяющая общие и кодовые способности. Она сохраняет общий диалоговый стиль чат-модели и сильные навыки кодирования кодовой модели, с улучшенной согласованностью предпочтений. DeepSeek-V2.5 также улучшает навыки письма и следование инструкциям." }, "price_history": [ { "date": "2026-07-25", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-07", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "deepseek/deepseek-coder", "model_name": "deepseek-coder", "display_name": "deepseek-coder", "vendor": "deepseek", "pricing": [ { "provider": "deepseek", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.14" }, "completion": { "unit": "per_M_tokens", "price": "0.28" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 128000, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "assistant_prefill": true }, "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "deepseek/deepseek-coder" ], "price_history": [ { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "deepseek/deepseek-r1", "model_name": "deepseek-r1", "display_name": "deepseek-r1", "vendor": "deepseek", "pricing": [ { "provider": "deepseek", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.55" }, "completion": { "unit": "per_M_tokens", "price": "2.19" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 65536, "max_output_tokens": 8192, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "parallel_function_calling": true, "open_weights": true, "stream": true }, "intro": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools", "released_at": "2025-08-05", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2024-12", "family": "deepseek-thinking", "deprecated": true, "status": "deprecated", "reasoning_config": { "mandatory": true, "budget_min": 128 }, "docs_url": "https://techcommunity.microsoft.com/blog/machinelearningblog/deepseek-r1-improved-performance-higher-limits-and-transparent-pricing/4386367", "benchmarks": { "intelligence_index": 18.6, "coding_index": 24.6, "agentic_index": 3.1 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "360/deepseek-r1", "DeepSeek-R1", "Pro/deepseek-ai/DeepSeek-R1", "accounts/fireworks/models/deepseek-r1", "deepinfra/deepseek-ai/DeepSeek-R1", "deepseek-ai/DeepSeek-R1", "deepseek-ai/deepseek-r1", "deepseek-r1-2025-01-20", "deepseek-r1:free", "deepseek/deepseek-r1", "hf:deepseek-ai/DeepSeek-R1", "novita/deepseek/deepseek-r1", "public/deepseek-r1" ], "intro_i18n": { "zh-CN": "360 部署的 DeepSeek-R1 在后训练阶段应用大规模强化学习，在极少标注数据下显著提升推理能力，在数学、编程和自然语言推理任务上可与 OpenAI o1 相媲美。", "zh-TW": "360 部署的 DeepSeek-R1 在後訓練階段應用大規模強化學習，僅需極少標註資料即可大幅提升推理能力，在數學、程式碼與自然語言推理任務上與 OpenAI o1 表現相當。", "ja-JP": "360が展開するDeepSeek-R1は、ポストトレーニングで大規模な強化学習を活用し、最小限のラベルで推論能力を大幅に向上させます。数学、コード、自然言語推論タスクにおいてOpenAI o1と同等の性能を発揮します。", "ru-RU": "DeepSeek-R1, развернутая компанией 360, использует масштабное обучение с подкреплением на этапе дообучения, значительно улучшая логическое мышление при минимальной разметке. Сопоставима с OpenAI o1 в задачах по математике, программированию и языковому рассуждению." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "berget", "charge": "completion", "old": "2.8840816", "new": "2.880833975" }, { "date": "2026-08-14", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.807542848", "new": "0.806633513" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.3717464", "new": "2.37250576" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-13", "kind": "price", "provider": "berget", "charge": "completion", "old": "2.88640205", "new": "2.8840816" }, { "date": "2026-08-13", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.808192574", "new": "0.807542848" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.37211728", "new": "2.3717464" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59302932", "new": "0.5929366" }, { "date": "2026-08-12", "kind": "price", "provider": "berget", "charge": "completion", "old": "2.888370075", "new": "2.88640205" }, { "date": "2026-08-12", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.808743621", "new": "0.808192574" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.37192448", "new": "2.37211728" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59298112", "new": "0.59302932" }, { "date": "2026-08-11", "kind": "price", "provider": "berget", "charge": "completion", "old": "2.8900896", "new": "2.888370075" }, { "date": "2026-08-11", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.809225088", "new": "0.808743621" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.37120624", "new": "2.37192448" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59280156", "new": "0.59298112" }, { "date": "2026-08-10", "kind": "price", "provider": "berget", "charge": "completion", "old": "2.889652925", "new": "2.8900896" }, { "date": "2026-08-10", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.809102819", "new": "0.809225088" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.37103408", "new": "2.37120624" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59275852", "new": "0.59280156" } ] }, { "slug": "deepseek/deepseek-reasoner", "model_name": "deepseek-reasoner", "display_name": "DeepSeek Reasoner", "vendor": "deepseek", "pricing": [ { "provider": "deepseek", "provider_name": "DeepSeek", "official": true, "source": "models-dev+litellm+pydantic-prices+helicone-registry+portkey+llmdb+pricetoken+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.14" }, "completion": { "unit": "per_M_tokens", "price": "0.28" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0028" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.28" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "internal_reasoning": "models-dev", "cache_write": "portkey" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.28" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.42" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.028" }, "message": "cache_read from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.28" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.42" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.028" }, "message": "cache_read from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.135" }, "message": "prompt from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.55" }, "message": "completion from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.035" }, "message": "cache_read from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.56" }, "message": "prompt from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.68" }, "message": "completion from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.07" }, "message": "cache_read from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.28" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.42" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.028" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.55" }, "message": "prompt from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.19" }, "message": "completion from llm-prices-www conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "DeepSeek reasoning model for multi-step analysis, math, coding, and tools", "released_at": "2025-12-01", "knowledge_cutoff": "2025-09", "max_input_tokens": 1000000, "max_output_tokens": 384000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "deepseek-thinking", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true, "stream": true }, "docs_url": "https://api-docs.deepseek.com/quick_start/pricing", "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "parameters": { "supported": [ "frequency_penalty", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "stream", "temperature", "top_logprobs", "top_p" ] }, "deprecated": true, "status": "deprecated", "aliases": [ "deepseek/deepseek-reasoner" ], "intro_i18n": { "zh-CN": "一个专注于复杂逻辑推理任务的 DeepSeek 推理模型。", "zh-TW": "一款專注於複雜邏輯推理任務的 DeepSeek 推理模型。", "ja-JP": "複雑な論理的推論タスクに特化したDeepSeekの推論モデルです。", "ru-RU": "Модель DeepSeek, ориентированная на выполнение сложных логических задач." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "deepseek/deepseek-v3", "model_name": "deepseek-v3", "display_name": "deepseek-v3", "vendor": "deepseek", "pricing": [ { "provider": "deepseek", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.27" }, "completion": { "unit": "per_M_tokens", "price": "1.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.07" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 65536, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "web_search": true, "assistant_prefill": true, "parallel_function_calling": true, "open_weights": true, "stream": true }, "intro": "DeepSeek chat model for instruction following, coding, and analysis", "released_at": "2025-08-13", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2024-10", "family": "deepseek", "deprecated": true, "status": "deprecated", "docs_url": "https://techcommunity.microsoft.com/blog/machinelearningblog/announcing-deepseek-v3-on-azure-ai-foundry-and-github/4390438", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "DeepSeek-V3", "Pro/deepseek-ai/DeepSeek-V3", "accounts/fireworks/models/deepseek-v3", "deepinfra/deepseek-ai/DeepSeek-V3", "deepseek-ai/DeepSeek-V3", "deepseek/deepseek-v3", "hf:deepseek-ai/DeepSeek-V3", "public/deepseek-v3" ], "intro_i18n": { "zh-CN": "字节跳动火山引擎的开放部署目前是最稳定的；推荐使用。已自动升级至最新版本（250324）。", "zh-TW": "字節跳動火山引擎的開放部署目前是最穩定的；推薦使用。已自動升級至最新版本（250324）。", "ja-JP": "ByteDance Volcengineのオープンデプロイメントは現在最も安定しており、推奨されています。最新リリース（250324）に自動アップグレードされています。", "ru-RU": "Открытое развертывание ByteDance Volcengine в настоящее время является самым стабильным; рекомендуется. Автоматически обновлено до последней версии (250324)." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.74", "new": "3.22" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.18", "new": "0.81" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.1858732", "new": "1.18625288" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.2964683", "new": "0.29656322" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18605864", "new": "1.1858732" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29651466", "new": "0.2964683" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18596224", "new": "1.18605864" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29649056", "new": "0.29651466" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18560312", "new": "1.18596224" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29640078", "new": "0.29649056" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18551704", "new": "1.18560312" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29637926", "new": "0.29640078" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18564704", "new": "1.18551704" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29641176", "new": "0.29637926" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18566624", "new": "1.18564704" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29641656", "new": "0.29641176" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18557384", "new": "1.18566624" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29639346", "new": "0.29641656" }, { "date": "2026-08-06", "kind": "price", "provider": "deepinfra", "charge": "prompt", "old": "0.38", "new": "0.32" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.18387152", "new": "1.18557384" } ] }, { "slug": "deepseek/deepseek-v3-2-exp", "model_name": "deepseek-v3-2-exp", "display_name": "DeepSeek/DeepSeek-V3.2-Exp", "vendor": "deepseek", "pricing": [ { "provider": "deepseek", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.27" }, "completion": { "unit": "per_M_tokens", "price": "0.41" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" }, "provider_model_id": "deepseek-v3.2-exp" } ], "intro": "DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures.", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "assistant_prefill": true, "parallel_function_calling": true, "stream": true, "web_search": true }, "released_at": "2025-09-29", "max_input_tokens": 128000, "max_output_tokens": 32000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "deepseek", "knowledge_cutoff": "2025-07", "reasoning_config": { "mandatory": false, "budget_min": 128 }, "model_type": "deep_thinking", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.6, "top_p": 0.95 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "DeepSeek-V3.2-Exp", "deepseek-ai/DeepSeek-V3.2-Exp", "deepseek-ai/deepseek-v3.2-exp", "deepseek-v3.2-exp", "deepseek/deepseek-v3.2-exp" ], "intro_i18n": { "zh-CN": "DeepSeek V3.2 Exp 使用混合推理架构，支持思考模式和非思考模式。", "zh-TW": "DeepSeek V3.2 Exp 採用混合推理架構，支持思考模式和非思考模式。", "ja-JP": "DeepSeek V3.2 Expは、ハイブリッド推論アーキテクチャを使用し、思考モードと非思考モードの両方をサポートします。", "ru-RU": "DeepSeek V3.2 Exp использует гибридную архитектуру рассуждений и поддерживает как режимы мышления, так и немышления." }, "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "128000", "new": "163840", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "32000", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "163840", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "65536", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "163840", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "65536", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "128000", "new": "163840", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "32000", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "163840", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "65536", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "128000", "new": "163840", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "32000", "new": "65536", "note": "max_output_tokens" } ] }, { "slug": "deepseek/DeepSeek-V3.1-Terminus:thinking", "model_name": "DeepSeek-V3.1-Terminus:thinking", "display_name": "DeepSeek/DeepSeek-V3.1-Terminus", "vendor": "deepseek", "pricing": [ { "provider": "deepseek", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.27" }, "completion": { "unit": "per_M_tokens", "price": "0.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.13" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "aggregator_only" }, "provider_model_id": "deepseek-v3.1-terminus" } ], "intro": "DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities.", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "parallel_function_calling": true, "stream": true }, "released_at": "2025-09-22", "max_input_tokens": 128000, "max_output_tokens": 32000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "deepseek", "knowledge_cutoff": "2025-03", "reasoning_config": { "mandatory": false, "budget_min": 128 }, "model_type": "deep_thinking", "deprecated": true, "benchmarks": { "intelligence_index": null, "coding_index": 43.5, "agentic_index": null }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "DeepSeek-V3.1-Terminus", "Pro/deepseek-ai/DeepSeek-V3.1-Terminus", "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus", "deepseek-ai/DeepSeek-V3.1-Terminus", "deepseek-ai/DeepSeek-V3.1-Terminus:thinking", "deepseek-v3.1-terminus", "deepseek/deepseek-v3.1-terminus", "deepseek/deepseek-v3.1-terminus:exacto", "hf:deepseek-ai/DeepSeek-V3.1-Terminus", "siliconflow/deepseek-v3.1-terminus" ], "intro_i18n": { "zh-CN": "DeepSeek-V3.1-Terminus 是 V3.1 的更新版本，定位为混合代理大模型。该版本修复了用户反馈的问题，提升了稳定性、语言一致性，并减少了中英文混杂和异常字符。它集成了思维模式与非思维模式，并配备聊天模板以实现灵活切换。同时还提升了代码代理和搜索代理的性能，使工具使用和多步骤任务更加可靠。", "zh-TW": "DeepSeek-V3.1-Terminus 是 V3.1 版本的更新模型，定位為混合代理型大型語言模型。修復了用戶回報的問題，提升穩定性與語言一致性，減少中英混雜與異常字符。整合思考與非思考模式，並提供聊天模板以靈活切換。強化了程式代理與搜尋代理的表現，提升工具使用與多步任務的可靠性。", "ja-JP": "DeepSeek-V3.1-Terminusは、ハイブリッドエージェントLLMとして位置づけられたV3.1の改良版です。ユーザーから報告された問題を修正し、安定性と言語の一貫性を向上。中英混在や異常文字を削減。思考モードと非思考モードをチャットテンプレートで柔軟に切り替え可能。Code AgentとSearch Agentの性能も向上し、ツール使用やマルチステップタスクの信頼性が高まりました。", "ru-RU": "DeepSeek-V3.1-Terminus — обновлённая модель V3.1, позиционируемая как гибридная агентная LLM. Исправляет ошибки, сообщённые пользователями, повышает стабильность, согласованность языка и снижает количество смешанных китайско-английских и аномальных символов. Интегрирует режимы размышления и без размышлений с шаблонами чата для гибкого переключения. Также улучшает производительность агентов кода и поиска для более надёжного использования инструментов и многошаговых задач." }, "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "32000", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "65536", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "65536", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "32000", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "65536", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "32000", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "65536", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "32000", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-07-25", "kind": "limit", "old": "8192", "new": "65536", "note": "max_output_tokens" } ] }, { "slug": "deepseek/deepseek-v3.2", "model_name": "deepseek-v3.2", "display_name": "deepseek-v3.2", "vendor": "deepseek", "pricing": [ { "provider": "deepseek", "official": true, "source": "litellm+pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.28" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2288" }, "message": "prompt from pydantic-prices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3432" }, "message": "completion from pydantic-prices conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 163840, "max_output_tokens": 163840, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "assistant_prefill": true, "parallel_function_calling": true, "open_weights": true, "stream": true, "image_output": true }, "intro": "DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance.", "released_at": "2025-12-03", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "deepseek", "knowledge_cutoff": "2024-12", "deprecated": true, "status": "deprecated", "reasoning_config": { "mandatory": false, "budget_min": 128 }, "docs_url": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-deepseek-v3-2-and-deepseek-v3-2-speciale-in-microsoft-foundry/4477549", "benchmarks": { "intelligence_index": null, "coding_index": 44.2, "agentic_index": null }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "DeepSeek-V3.2", "Pro/deepseek-ai/DeepSeek-V3.2", "TEE/deepseek-v3.2", "deepinfra/deepseek-ai/DeepSeek-V3.2", "deepseek-ai/DeepSeek-V3.2", "deepseek-ai/deepseek-v3-2", "deepseek-v3-2", "deepseek/deepseek-v3-2", "deepseek/deepseek-v3.2", "deepseek/deepseek-v3.2:thinking", "hf:deepseek-ai/DeepSeek-V3.2", "novita/deepseek-v3.2", "novita/deepseek/deepseek-v3.2", "paratera/deepseek-v3.2", "siliconflow/deepseek-v3.2", "sophnet/deepseek-v3.2", "vertex/deepseek-v3.2" ], "intro_i18n": { "zh-CN": "deepseek-v3.2 引入稀疏注意力机制，旨在提升处理长文本时的训练与推理效率，且价格低于 deepseek-v3.1。", "zh-TW": "deepseek-v3.2 採用稀疏注意力機制，旨在提升處理長文本時的訓練與推理效率，成本低於 deepseek-v3.1。", "ja-JP": "deepseek-v3.2 はスパースアテンション機構を導入し、長文処理における学習と推論の効率を向上させています。また、deepseek-v3.1 より低価格で提供されます。", "ru-RU": "deepseek-v3.2 использует разреженный механизм внимания, что повышает эффективность обучения и инференса при обработке длинных текстов. Стоимость ниже, чем у deepseek-v3.1." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.41", "new": "0.64" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.27", "new": "0.44" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.44470245", "new": "0.44484483" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.2964683", "new": "0.29656322" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.19605", "new": "0.19405" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.1023", "new": "1.0943" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.3921", "new": "0.3881" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.44477199", "new": "0.44470245" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29651466", "new": "0.2964683" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.19405", "new": "0.19605" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.0943", "new": "1.1023" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.3881", "new": "0.3921" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.44473584", "new": "0.44477199" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29649056", "new": "0.29651466" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.43277", "new": "0.19405" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.64446", "new": "1.0943" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.86554", "new": "0.3881" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.44460117", "new": "0.44473584" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.29640078", "new": "0.29649056" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.44456889", "new": "0.44460117" } ] }, { "slug": "deepseek/deepseek-v4-flash", "model_name": "deepseek-v4-flash", "display_name": "DeepSeek V4 Flash", "vendor": "deepseek", "pricing": [ { "provider": "deepseek", "provider_name": "DeepSeek", "official": true, "source": "models-dev+litellm+pydantic-prices+portkey+llmdb+lobehub-modelbank+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.14" }, "completion": { "unit": "per_M_tokens", "price": "0.28" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0028" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.28" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "internal_reasoning": "models-dev", "cache_write": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.05", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4.5", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.028" }, "message": "cache_read from llm-prices-www conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding", "released_at": "2026-07-31", "knowledge_cutoff": "2025-05", "max_input_tokens": 1000000, "max_output_tokens": 384000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "deepseek-flash", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true, "parallel_function_calling": true, "stream": true, "web_search": true }, "docs_url": "https://api-docs.deepseek.com/quick_start/pricing", "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "reasoning_config": { "mandatory": false, "budget_min": 128 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_logprobs", "top_p" ] }, "aliases": [ "DeepSeek-V4-Flash", "TEE/deepseek-v4-flash", "accounts/fireworks/models/deepseek-v4-flash", "cline-pass/deepseek-v4-flash", "deepinfra/deepseek-ai/DeepSeek-V4-Flash", "deepseek-ai/DeepSeek-V4-Flash", "deepseek-ai/deepseek-v4-flash", "deepseek-v4-flash-free", "deepseek-v4-flash:free", "deepseek/deepseek-v4-flash", "deepseek/deepseek-v4-flash-20260731", "deepseek/deepseek-v4-flash:free", "deepseek/deepseek-v4-flash:thinking", "doubleword/deepseek-v4-flash", "novita/deepseek/deepseek-v4-flash" ], "intro_i18n": { "zh-CN": "DeepSeek-V4-Flash 是 DeepSeek-V4 系列中 MoE 语言模型的预览版本。总参数规模为 2840 亿，激活参数规模为 130 亿，支持 1M 令牌超长上下文。该模型采用结合 CSA 和 HCA 的混合注意力架构，并引入 mHC 和 Muon 优化器，以提高长上下文推理效率、训练稳定性和整体性能。", "zh-TW": "DeepSeek-V4-Flash 是 DeepSeek-V4 系列中的 MoE 語言模型預覽版。總參數大小為 2840 億，激活參數大小為 130 億，支持 1M 令牌超長上下文。該模型採用結合 CSA 和 HCA 的混合注意力架構，並引入 mHC 和 Muon 優化器以提高長上下文推理效率、訓練穩定性和整體性能。", "ja-JP": "DeepSeek-V4-FlashはDeepSeek-V4シリーズのMoE言語モデルのプレビュー版です。総パラメータサイズは2840億、アクティブパラメータサイズは130億で、1Mトークンの超長コンテキストをサポートします。このモデルはCSAとHCAを組み合わせたハイブリッドアテンションアーキテクチャを使用し、mHCとMuon Optimizerを導入して長コンテキスト推論効率、トレーニングの安定性、全体的な性能を向上させています。", "ru-RU": "DeepSeek-V4-Flash — это предварительная версия языковой модели MoE из серии DeepSeek-V4. Общий размер параметров составляет 284 миллиарда, размер активных параметров — 13 миллиардов, и она поддерживает ультрадлинный контекст на 1 миллион токенов. Модель использует гибридную архитектуру внимания, объединяющую CSA и HCA, и вводит mHC и Muon Optimizer для повышения эффективности рассуждений на длинных контекстах, стабильности обучения и общей производительности." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.26", "new": "0.44" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.13", "new": "0.22" }, { "date": "2026-08-14", "kind": "price", "provider": "crossmodel", "charge": "cache_read", "old": "0.004", "new": "0.015" }, { "date": "2026-08-14", "kind": "price", "provider": "crossmodel", "charge": "cache_write", "old": "0.16", "new": "0.45" }, { "date": "2026-08-14", "kind": "price", "provider": "crossmodel", "charge": "completion", "old": "0.32", "new": "1.35" }, { "date": "2026-08-14", "kind": "price", "provider": "crossmodel", "charge": "prompt", "old": "0.16", "new": "0.45" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.2964683", "new": "0.29656322" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14823415", "new": "0.14828161" }, { "date": "2026-08-13", "kind": "price", "provider": "alibaba", "charge": "completion", "old": "0.294118", "new": "0.4" }, { "date": "2026-08-13", "kind": "price", "provider": "alibaba", "charge": "prompt", "old": "0.147059", "new": "0.2" }, { "date": "2026-08-13", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.25", "new": "0.26" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.29651466", "new": "0.2964683" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14825733", "new": "0.14823415" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.0685", "new": "0.0694" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "completion", "old": "0.304", "new": "0.2776" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.137", "new": "0.1388" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.29649056", "new": "0.29651466" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.14824528", "new": "0.14825733" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.10173", "new": "0.0685" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "completion", "old": "0.36692", "new": "0.304" } ] }, { "slug": "deepseek/deepseek-v4-pro", "model_name": "deepseek-v4-pro", "display_name": "DeepSeek V4 Pro", "vendor": "deepseek", "pricing": [ { "provider": "deepseek", "provider_name": "DeepSeek", "official": true, "source": "models-dev+litellm+pydantic-prices+portkey+llmdb+lobehub-modelbank+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.435" }, "completion": { "unit": "per_M_tokens", "price": "0.87" }, "cache_read": { "unit": "per_M_tokens", "price": "0.003625" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.87" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "internal_reasoning": "models-dev", "cache_write": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.435" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.74" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.87" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.48" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.003625" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0145" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.003625" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.435" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4.5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.87" }, "discarded_charge": { "unit": "per_M_tokens", "price": "13.5", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.435" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.74" }, "message": "prompt from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.87" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.48" }, "message": "completion from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.003625" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.145" }, "message": "cache_read from llm-prices-www conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes", "released_at": "2026-08-12", "max_input_tokens": 1000000, "max_output_tokens": 384000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "deepseek-thinking", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true, "parallel_function_calling": true, "stream": true, "web_search": true }, "docs_url": "https://api-docs.deepseek.com/quick_start/pricing", "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "knowledge_cutoff": "2025-05", "reasoning_config": { "mandatory": false, "budget_min": 128 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 1 } }, "aliases": [ "DeepSeek-V4-Pro", "accounts/fireworks/models/deepseek-v4-pro", "cline-pass/deepseek-v4-pro", "deepinfra/deepseek-ai/DeepSeek-V4-Pro", "deepseek-ai/DeepSeek-V4-Pro", "deepseek-ai/deepseek-v4-pro", "deepseek-v4-pro:free", "deepseek/deepseek-v4-pro", "deepseek/deepseek-v4-pro:thinking", "doubleword/deepseek-v4-pro", "fireworks/deepseek-v4-pro", "lightning-ai/deepseek-v4-pro", "nebius/deepseek-ai/deepseek-v4-pro", "tensorx/deepseek-v4-pro" ], "intro_i18n": { "zh-CN": "DeepSeek-V4-Pro 是 DeepSeek-V4 系列中的旗舰 MoE 语言模型，拥有 1.6T 总参数、49B 激活参数，原生支持 100 万 tokens 的超长上下文。该模型采用创新的混合注意力架构，结合压缩稀疏注意力（CSA）与高度压缩注意力（HCA），在 1M 上下文下仅需 DeepSeek-V3.2 的 27% 单 token 推理 FLOPs 和 10% KV 缓存。模型还引入流形约束超连接（mHC）增强层间信号传播稳定性，并采用 Muon 优化器加速收敛。DeepSeek-V4-Pro 在超过 32T 高质量多样化 tokens 上预训练，后训练采用「领域专家独立培养 + 在线策略蒸馏统一整合」的两阶段范式。其最大推理强度模式 DeepSeek-V4-Pro-Max 在编程基准上取得顶尖表现，并在推理与 Agentic 任务上大幅缩小与领先闭源模型的差距，是目前最强的开源模型之一，支持 Non-think、Think High、Think Max 三种推理强度模式", "zh-TW": "DeepSeek-V4-Pro 是 DeepSeek-V4 系列中的旗艦 MoE 語言模型，擁有 1.6T 總參數和 49B 活躍參數，原生支持超長上下文達 100 萬個 token。該模型採用創新的混合注意力架構，結合壓縮稀疏注意力（CSA）和高度壓縮注意力（HCA），僅需 DeepSeek-V3.2 每 token 推理 FLOPs 的 27% 和 1M 上下文 KV 緩存的 10%。此外，它引入了流形約束超連接（mHC）以增強層間信號傳播穩定性，並使用 Muon 優化器加速收斂。DeepSeek-V4-Pro 在超過 32T 高質量多樣化 token 上進行預訓練，並通過獨立領域專家培養和在線策略蒸餾的兩階段範式進行後訓練以實現統一整合。其最大推理強度模式 DeepSeek-V4-Pro-Max 在編碼基準測試中表現卓越，並顯著縮小了與領先的閉源模型在推理和代理任務上的差距，使其成為當今最強大的開源模型之一，支持 Non-think、Think High 和 Think Max 推理強度模式。", "ja-JP": "DeepSeek-V4-ProはDeepSeek-V4シリーズのフラッグシップMoE言語モデルで、総パラメータ数1.6T、アクティブパラメータ数49Bを持ち、1百万トークンの超長文コンテキストをネイティブにサポートします。このモデルは、Compressed Sparse Attention (CSA)とHighly Compressed Attention (HCA)を組み合わせた革新的なハイブリッドアテンションアーキテクチャを採用し、DeepSeek-V3.2のトークンごとの推論FLOPsの27%と1MコンテキストでのKVキャッシュの10%のみを必要とします。また、Manifold-Constrained Hyper Connections (mHC)を導入して層間信号伝播の安定性を向上させ、Muonオプティマイザを使用して収束を加速します。DeepSeek-V4-Proは32T以上の高品質で多様なトークンで事前学習され、独立したドメインエキスパートの育成とオンラインポリシー蒸留による統合の2段階パラダイムでポストトレーニングが行われています。最大推論強度モードのDeepSeek-V4-Pro-Maxは、コーディングベンチマークで最高のパフォーマンスを達成し、推論およびエージェント的タスクにおいて主要なクローズドソースモデルとのギャップを大幅に縮小し、現在最も強力なオープンソースモデルの1つとなっています。Non-think、Think High、Think Maxの推論強度モードをサポートします。", "ru-RU": "DeepSeek-V4-Pro — флагманская модель MoE в серии DeepSeek-V4 с общим количеством параметров 1,6 трлн и 49 млрд активных параметров, которая нативно поддерживает ультрадлинный контекст в 1 миллион токенов. Модель использует инновационную гибридную архитектуру внимания, объединяющую Compressed Sparse Attention (CSA) и Highly Compressed Attention (HCA), требующую всего 27% FLOPs на токен по сравнению с DeepSeek-V3.2 и 10% KV-кэша при контексте 1 млн. Также она вводит Манипулируемые Гиперсвязи (mHC) для повышения стабильности передачи сигналов между слоями и использует оптимизатор Muon для ускорения сходимости. DeepSeek-V4-Pro предварительно обучена на более чем 32 трлн высококачественных разнообразных токенов с последующим обучением по двухэтапной парадигме: культивация независимых доменных экспертов и онлайн-дистилляция политики для унифицированной интеграции. Режим максимальной интенсивности рассуждений DeepSeek-V4-Pro-Max достигает лучших результатов в кодировочных тестах и значительно сокращает разрыв с ведущими закрытыми моделями в задачах рассуждений и агентности, делая её одной из самых мощных моделей с открытым исходным кодом на сегодняшний день, поддерживающей режимы рассуждений Non-think, Think High и Think Max." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "2.83", "new": "5.18" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "1.42", "new": "2.58" }, { "date": "2026-08-14", "kind": "price", "provider": "crossmodel", "charge": "cache_read", "old": "0.005", "new": "0.045" }, { "date": "2026-08-14", "kind": "price", "provider": "crossmodel", "charge": "cache_write", "old": "0.47", "new": "1.35" }, { "date": "2026-08-14", "kind": "price", "provider": "crossmodel", "charge": "completion", "old": "0.94", "new": "4.05" }, { "date": "2026-08-14", "kind": "price", "provider": "crossmodel", "charge": "prompt", "old": "0.47", "new": "1.35" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.5576196", "new": "3.55875864" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.7788098", "new": "1.77937932" }, { "date": "2026-08-13", "kind": "price", "provider": "alibaba", "charge": "completion", "old": "3.529412", "new": "4.8" }, { "date": "2026-08-13", "kind": "price", "provider": "alibaba", "charge": "prompt", "old": "1.764706", "new": "2.4" }, { "date": "2026-08-13", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.84", "new": "2.83" }, { "date": "2026-08-13", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.42", "new": "1.42" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.806", "new": "0.756562" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "3.274", "new": "3.0526" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "1.612", "new": "1.513124" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.55817592", "new": "3.5576196" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.77908796", "new": "1.7788098" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.003625", "new": "0.09855" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "0.87", "new": "2.336" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.435", "new": "1.168" } ] }, { "slug": "google/antigravity-preview-05-2026", "model_name": "antigravity-preview-05-2026", "display_name": "antigravity-preview-05-2026", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "prompt_caching": true, "function_calling": true, "reasoning": true, "vision": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "antigravity-preview-05-2026" } ] }, { "slug": "google/aqa", "model_name": "aqa", "display_name": "Model that performs Attributed Question Answering.", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "llmdb", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "web_search": "llmdb" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 7168, "max_output_tokens": 1024, "capabilities": { "prompt_caching": true }, "released_at": "2026-08-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Model that performs Attributed Question Answering." } ] }, { "slug": "google/automl-vision-image-object-detection", "model_name": "automl-vision-image-object-detection", "display_name": "automl-vision-image-object-detection", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.000556111" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/automl-vision-image-object-detection" } ], "modalities": { "input": [ "image" ], "output": [ "text" ] }, "model_type": "image_generation", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/automl-vision-image-object-detection" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "automl-vision-image-object-detection" } ] }, { "slug": "google/chat-bison", "model_name": "chat-bison", "display_name": "chat-bison", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 4096, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "chat-bison" } ] }, { "slug": "google/chat-bison-32k", "model_name": "chat-bison-32k", "display_name": "chat-bison-32k", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 8192, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "chat-bison-32k" } ] }, { "slug": "google/chat-bison-32k@002", "model_name": "chat-bison-32k@002", "display_name": "chat-bison-32k@002", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 8192, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "chat-bison-32k@002" } ] }, { "slug": "google/chat-bison@001", "model_name": "chat-bison@001", "display_name": "chat-bison@001", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 4096, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "chat-bison@001" } ] }, { "slug": "google/chat-bison@002", "model_name": "chat-bison@002", "display_name": "chat-bison@002", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 4096, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "chat-bison@002" } ] }, { "slug": "google/chirp-2", "model_name": "chirp-2", "display_name": "chirp-2", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0002666666666666667" } }, "provenance": { "base_charges": { "audio_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/chirp-2" } ], "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "model_type": "speech_recognition", "capabilities": { "audio_input": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/chirp-2" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "chirp-2" } ] }, { "slug": "google/chirp-3", "model_name": "chirp-3", "display_name": "chirp-3", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.000266666666666667" } }, "provenance": { "base_charges": { "audio_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/chirp-3" } ], "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "model_type": "speech_recognition", "capabilities": { "audio_input": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/chirp-3" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "chirp-3" } ] }, { "slug": "google/code-bison", "model_name": "code-bison", "display_name": "code-bison", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 1024, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "code-bison" } ] }, { "slug": "google/code-bison-32k@002", "model_name": "code-bison-32k@002", "display_name": "code-bison-32k@002", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 1024, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "code-bison-32k@002" } ] }, { "slug": "google/code-bison@001", "model_name": "code-bison@001", "display_name": "code-bison@001", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 1024, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "code-bison@001" } ] }, { "slug": "google/code-bison@002", "model_name": "code-bison@002", "display_name": "code-bison@002", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 1024, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "code-bison@002" } ] }, { "slug": "google/code-gecko", "model_name": "code-gecko", "display_name": "code-gecko", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 64, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "code-gecko" } ] }, { "slug": "google/code-gecko-latest", "model_name": "code-gecko-latest", "display_name": "code-gecko-latest", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 64, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "code-gecko-latest" } ] }, { "slug": "google/code-gecko@001", "model_name": "code-gecko@001", "display_name": "code-gecko@001", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 64, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "code-gecko@001" } ] }, { "slug": "google/code-gecko@002", "model_name": "code-gecko@002", "display_name": "code-gecko@002", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 64, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "code-gecko@002" } ] }, { "slug": "google/codechat-bison", "model_name": "codechat-bison", "display_name": "codechat-bison", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 1024, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "codechat-bison" } ] }, { "slug": "google/codechat-bison-32k", "model_name": "codechat-bison-32k", "display_name": "codechat-bison-32k", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 8192, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "codechat-bison-32k" } ] }, { "slug": "google/codechat-bison-32k@002", "model_name": "codechat-bison-32k@002", "display_name": "codechat-bison-32k@002", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 8192, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "codechat-bison-32k@002" } ] }, { "slug": "google/codechat-bison@001", "model_name": "codechat-bison@001", "display_name": "codechat-bison@001", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 1024, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "codechat-bison@001" } ] }, { "slug": "google/codechat-bison@002", "model_name": "codechat-bison@002", "display_name": "codechat-bison@002", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 1024, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "codechat-bison@002" } ] }, { "slug": "google/codechat-bison@latest", "model_name": "codechat-bison@latest", "display_name": "codechat-bison@latest", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" }, "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 1024, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "codechat-bison@latest" } ] }, { "slug": "google/content-moderation", "model_name": "content-moderation", "display_name": "content-moderation", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.0015" } }, "provenance": { "base_charges": { "image_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/content-moderation" } ], "modalities": { "input": [ "image" ], "output": [ "text" ] }, "model_type": "safety_detection", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/content-moderation" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "content-moderation" } ] }, { "slug": "google/deep-research-max-preview-04-2026", "model_name": "deep-research-max-preview-04-2026", "display_name": "Deep Research Max Preview (Apr-21-2026)", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write_1h": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+truefoundry", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write_1h": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "models-dev", "threshold": 200000, "inclusive": false, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "threshold": 200000, "inclusive": true, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "invalid_source_tier", "source": "models-dev", "message": "tier threshold 200000 exceeds model context window 131072." }, { "code": "invalid_source_tier", "source": "truefoundry", "message": "tier threshold 200000 exceeds model context window 131072." } ] } ], "intro": "Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports", "released_at": "2026-04-21", "knowledge_cutoff": "2025-01", "max_input_tokens": 131072, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text", "image" ] }, "family": "gemini-pro", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "pdf_input": true, "image_output": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-25", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-25", "kind": "limit", "old": "1048576", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "deep-research-max-preview-04-2026" } ] }, { "slug": "google/deep-research-preview-04-2026", "model_name": "deep-research-preview-04-2026", "display_name": "Deep Research Preview (Apr-21-2026)", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write_1h": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+truefoundry", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write_1h": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "models-dev", "threshold": 200000, "inclusive": false, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "threshold": 200000, "inclusive": true, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "invalid_source_tier", "source": "models-dev", "message": "tier threshold 200000 exceeds model context window 131072." }, { "code": "invalid_source_tier", "source": "truefoundry", "message": "tier threshold 200000 exceeds model context window 131072." } ] } ], "intro": "Agentic model for autonomous multi-step research, synthesis, and cited reports", "released_at": "2026-04-21", "knowledge_cutoff": "2025-01", "max_input_tokens": 131072, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text", "image" ] }, "family": "gemini-pro", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "pdf_input": true, "image_output": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-25", "kind": "limit", "old": "1048576", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "deep-research-preview-04-2026" } ] }, { "slug": "google/deep-research-pro-preview-12-2025", "model_name": "deep-research-pro-preview-12-2025", "display_name": "deep-research-pro-preview-12-2025", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "image_output": { "unit": "per_image", "price": "0.134" }, "image_input": { "unit": "per_image", "price": "0.0011" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm", "cache_write_1h": "truefoundry", "cache_read": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+truefoundry", "charge_sources": { "prompt": "litellm", "completion": "litellm", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm", "cache_write_1h": "truefoundry", "cache_read": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "threshold": 200000, "inclusive": true, "message": "tier threshold 200000 exceeds model context window 65536; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "invalid_source_tier", "source": "truefoundry", "message": "tier threshold 200000 exceeds model context window 65536." } ] }, { "provider": "google-vertex", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "image_output": { "unit": "per_image", "price": "0.134" }, "image_input": { "unit": "per_image", "price": "0.0011" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_output": "litellm", "image_input": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://ai.google.dev/gemini-api/docs/pricing", "max_input_tokens": 65536, "max_output_tokens": 32768, "model_type": "image_generation", "capabilities": { "vision": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 1000, "tpm": 4000000 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "released_at": "2026-08-14", "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "google/deep-research-pro-preview-12-2025-gt-128k", "model_name": "deep-research-pro-preview-12-2025-gt-128k", "display_name": "deep-research-pro-preview-12-2025-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "18" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "deep-research-pro-preview-12-2025-gt-128k" } ] }, { "slug": "google/deep-research-pro-preview-12-2025-lte-128k", "model_name": "deep-research-pro-preview-12-2025-lte-128k", "display_name": "deep-research-pro-preview-12-2025-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "deep-research-pro-preview-12-2025-lte-128k" } ] }, { "slug": "google/embedding-001", "model_name": "embedding-001", "display_name": "embedding-001", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.025" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_embedding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "embedding-001" } ] }, { "slug": "google/face-detector", "model_name": "face-detector", "display_name": "face-detector", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.0015" } }, "provenance": { "base_charges": { "image_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/face-detector" } ], "modalities": { "input": [ "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/face-detector" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "face-detector" } ] }, { "slug": "google/gemini-1-5-flash-8b", "model_name": "gemini-1-5-flash-8b", "display_name": "Gemini 1.5 Flash-8B", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "truefoundry+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0375" }, "message": "prompt from llm-prices-www conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "completion from llm-prices-www conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gemini-1.5-flash-8b" } ], "max_output_tokens": 8192, "modalities": { "input": [ "doc", "image", "pdf" ], "output": [] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "vision": true, "pdf_input": true, "reasoning": true }, "max_input_tokens": 1000000, "released_at": "2024-10-03", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemini-1.5-flash-8b", "google/gemini-1.5-flash-8b" ], "intro_i18n": { "zh-CN": "Gemini 1.5 Flash 8B 是一款高效多模态模型，适用于广泛应用场景。", "zh-TW": "Gemini 1.5 Flash 8B 是一款高效率的多模態模型，適用於廣泛應用的擴展場景。", "ja-JP": "Gemini 1.5 Flash 8B は、幅広い応用に対応する効率的なマルチモーダルモデルです。", "ru-RU": "Gemini 1.5 Flash 8B — эффективная мультимодальная модель для масштабируемого применения." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.5 Flash-8B" } ] }, { "slug": "google/gemini-1.0-pro", "model_name": "gemini-1.0-pro", "display_name": "gemini-1.0-pro", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.125" }, "image_input": { "unit": "per_image", "price": "0.0025" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.0-pro" } ] }, { "slug": "google/gemini-1.0-pro-001", "model_name": "gemini-1.0-pro-001", "display_name": "Gemini 1.0 Pro 001 (Tuning)", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.125" }, "image_input": { "unit": "per_image", "price": "0.0025" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "parallel_function_calling": true }, "released_at": "2023-12-06", "max_input_tokens": 32768, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Gemini 1.0 Pro 001（调优版）为复杂任务提供稳定、可调性能。", "zh-TW": "Gemini 1.0 Pro 001（調校版）在處理複雜任務時提供穩定且可調整的效能。", "ja-JP": "Gemini 1.0 Pro 001（チューニング）は、複雑なタスクに対して安定かつ調整可能な性能を提供します。", "ru-RU": "Gemini 1.0 Pro 001 (Tuning) обеспечивает стабильную и настраиваемую производительность для сложных задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.0 Pro 001 (Tuning)" } ] }, { "slug": "google/gemini-1.0-pro-002", "model_name": "gemini-1.0-pro-002", "display_name": "Gemini 1.0 Pro 002 (Tuning)", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.125" }, "image_input": { "unit": "per_image", "price": "0.0025" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "parallel_function_calling": true }, "released_at": "2023-12-06", "max_input_tokens": 32768, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Gemini 1.0 Pro 002（调优版）为复杂任务提供强大的多模态支持。", "zh-TW": "Gemini 1.0 Pro 002（調校版）在處理複雜任務時提供強大的多模態支援。", "ja-JP": "Gemini 1.0 Pro 002（チューニング）は、複雑なタスクに対して強力なマルチモーダル対応を提供します。", "ru-RU": "Gemini 1.0 Pro 002 (Tuning) обеспечивает мощную мультимодальную поддержку для сложных задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.0 Pro 002 (Tuning)" } ] }, { "slug": "google/gemini-1.0-pro-vision", "model_name": "gemini-1.0-pro-vision", "display_name": "gemini-1.0-pro-vision", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "image_input": { "unit": "per_image", "price": "0.0025" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_output_tokens": 2048, "modalities": { "input": [ "image" ], "output": [] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "parallel_function_calling": true, "vision": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.0-pro-vision" } ] }, { "slug": "google/gemini-1.0-pro-vision-001", "model_name": "gemini-1.0-pro-vision-001", "display_name": "gemini-1.0-pro-vision-001", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.375" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "image_input": { "unit": "per_image", "price": "0.0025" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Google's first-generation advanced multimodal model that can understand text, code, and images. It provides strong reasoning capabilities and follows instructions effectively.", "max_input_tokens": 32768, "capabilities": { "function_calling": true, "parallel_function_calling": true, "vision": true }, "max_output_tokens": 2048, "modalities": { "input": [ "image" ], "output": [] }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.0-pro-vision-001" } ] }, { "slug": "google/gemini-1.0-ultra", "model_name": "gemini-1.0-ultra", "display_name": "gemini-1.0-ultra", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.125" }, "image_input": { "unit": "per_image", "price": "0.0025" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 2048, "model_type": "text_generation", "capabilities": { "function_calling": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.0-ultra" } ] }, { "slug": "google/gemini-1.0-ultra-001", "model_name": "gemini-1.0-ultra-001", "display_name": "gemini-1.0-ultra-001", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.125" }, "image_input": { "unit": "per_image", "price": "0.0025" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 2048, "model_type": "text_generation", "capabilities": { "function_calling": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.0-ultra-001" } ] }, { "slug": "google/gemini-1.5-flash", "model_name": "gemini-1.5-flash", "display_name": "gemini-1.5-flash", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm+pydantic-prices+truefoundry+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01875" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "pydantic-prices" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from pydantic-prices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from llm-prices-www conflicts with litellm; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "litellm", "threshold": 128000, "inclusive": false, "message": "tier threshold 128000 exceeds model context window 8192; it was discarded." }, { "kind": "tier_schedule", "source": "pydantic-prices", "threshold": 128000, "inclusive": true, "message": "tier threshold 128000 exceeds model context window 8192; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "threshold": 128000, "inclusive": true, "message": "tier threshold 128000 exceeds model context window 8192; it was discarded." } ], "verification_status": "conflicting" }, "warnings": [ { "code": "invalid_source_tier", "source": "litellm", "message": "tier threshold 128000 exceeds model context window 8192." }, { "code": "invalid_source_tier", "source": "pydantic-prices", "message": "tier threshold 128000 exceeds model context window 8192." }, { "code": "invalid_source_tier", "source": "truefoundry", "message": "tier threshold 128000 exceeds model context window 8192." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.01875" }, "image_input": { "unit": "per_image", "price": "0.00002" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "threshold": 128000, "inclusive": true, "message": "tier threshold 128000 exceeds model context window 8192; it was discarded." } ], "verification_status": "conflicting" }, "warnings": [ { "code": "invalid_source_tier", "source": "truefoundry", "message": "tier threshold 128000 exceeds model context window 8192." } ] } ], "docs_url": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal", "max_input_tokens": 8192, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2025-09-29", "rate_limits": { "rpm": 10000, "tpm": 10000000 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true }, "intro": "A faster, more cost-effective variant of Gemini 1.5 that maintains strong capabilities while optimizing for performance and cost efficiency. Suitable for production deployments requiring high throughput.", "max_output_tokens": 8192, "modalities": { "input": [ "doc", "image", "pdf" ], "output": [] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-1.5-flash" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "limit", "new": "8192", "note": "max_output_tokens" } ] }, { "slug": "google/gemini-1.5-flash-001", "model_name": "gemini-1.5-flash-001", "display_name": "Gemini 1.5 Flash 001", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01875" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥128K", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Context ≥128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.01875" }, "image_input": { "unit": "per_image", "price": "0.00002" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Context ≥128K", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "completion from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.05" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥128K", "factor": "1", "charge_factors": { "prompt": "13.333333", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "8" } } } ], "max_output_tokens": 8192, "modalities": { "input": [ "doc", "image", "pdf" ], "output": [] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "parallel_function_calling": true, "structured_output": true, "vision": true, "pdf_input": true, "prompt_caching": true }, "knowledge_cutoff": "2024-05", "max_input_tokens": 1008192, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Gemini 1.5 Flash 001 是一款高效多模态模型，适用于广泛应用场景。", "zh-TW": "Gemini 1.5 Flash 001 是一款高效率的多模態模型，適用於廣泛應用的擴展場景。", "ja-JP": "Gemini 1.5 Flash 001 は、幅広い応用に対応する効率的なマルチモーダルモデルです。", "ru-RU": "Gemini 1.5 Flash 001 — эффективная мультимодальная модель для масштабируемого применения." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.5 Flash 001" } ] }, { "slug": "google/gemini-1.5-flash-001-gt-128k", "model_name": "gemini-1.5-flash-001-gt-128k", "display_name": "gemini-1.5-flash-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-001-gt-128k" } ] }, { "slug": "google/gemini-1.5-flash-001-lte-128k", "model_name": "gemini-1.5-flash-001-lte-128k", "display_name": "gemini-1.5-flash-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-001-lte-128k" } ] }, { "slug": "google/gemini-1.5-flash-002", "model_name": "gemini-1.5-flash-002", "display_name": "Gemini 1.5 Flash 002", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01875" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥128K", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Context ≥128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.01875" }, "image_input": { "unit": "per_image", "price": "0.00002" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Context ≥128K", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "completion from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.05" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥128K", "factor": "1", "charge_factors": { "prompt": "13.333333", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "8" } } } ], "max_output_tokens": 8192, "modalities": { "input": [ "doc", "image", "pdf" ], "output": [] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "parallel_function_calling": true, "structured_output": true, "vision": true, "pdf_input": true, "prompt_caching": true }, "released_at": "2024-09-25", "knowledge_cutoff": "2024-05", "max_input_tokens": 1008192, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Gemini 1.5 Flash 002 是一款高效多模态模型，适用于大规模部署。", "zh-TW": "Gemini 1.5 Flash 002 是一款高效率的多模態模型，專為大規模部署而打造。", "ja-JP": "Gemini 1.5 Flash 002 は、広範な展開を目的とした効率的なマルチモーダルモデルです。", "ru-RU": "Gemini 1.5 Flash 002 — эффективная мультимодальная модель, созданная для широкого внедрения." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.5 Flash 002" } ] }, { "slug": "google/gemini-1.5-flash-002-gt-128k", "model_name": "gemini-1.5-flash-002-gt-128k", "display_name": "gemini-1.5-flash-002-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-002-gt-128k" } ] }, { "slug": "google/gemini-1.5-flash-002-lte-128k", "model_name": "gemini-1.5-flash-002-lte-128k", "display_name": "gemini-1.5-flash-002-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-002-lte-128k" } ] }, { "slug": "google/gemini-1.5-flash-128k", "model_name": "gemini-1.5-flash-128k", "display_name": "Gemini 1.5 Flash", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.5 Flash" } ] }, { "slug": "google/gemini-1.5-flash-8b-001-gt-128k", "model_name": "gemini-1.5-flash-8b-001-gt-128k", "display_name": "gemini-1.5-flash-8b-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-8b-001-gt-128k" } ] }, { "slug": "google/gemini-1.5-flash-8b-001-lte-128k", "model_name": "gemini-1.5-flash-8b-001-lte-128k", "display_name": "gemini-1.5-flash-8b-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.0375" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-8b-001-lte-128k" } ] }, { "slug": "google/gemini-1.5-flash-8b-128k", "model_name": "gemini-1.5-flash-8b-128k", "display_name": "Gemini 1.5 Flash-8B", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.5 Flash-8B" } ] }, { "slug": "google/gemini-1.5-flash-8b-gt-128k", "model_name": "gemini-1.5-flash-8b-gt-128k", "display_name": "gemini-1.5-flash-8b-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-8b-gt-128k" } ] }, { "slug": "google/gemini-1.5-flash-8b-latest-gt-128k", "model_name": "gemini-1.5-flash-8b-latest-gt-128k", "display_name": "gemini-1.5-flash-8b-latest-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-8b-latest-gt-128k" } ] }, { "slug": "google/gemini-1.5-flash-8b-latest-lte-128k", "model_name": "gemini-1.5-flash-8b-latest-lte-128k", "display_name": "gemini-1.5-flash-8b-latest-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.0375" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-8b-latest-lte-128k" } ] }, { "slug": "google/gemini-1.5-flash-8b-lte-128k", "model_name": "gemini-1.5-flash-8b-lte-128k", "display_name": "gemini-1.5-flash-8b-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.0375" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-8b-lte-128k" } ] }, { "slug": "google/gemini-1.5-flash-gt-128k", "model_name": "gemini-1.5-flash-gt-128k", "display_name": "gemini-1.5-flash-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-gt-128k" } ] }, { "slug": "google/gemini-1.5-flash-latest", "model_name": "gemini-1.5-flash-latest", "display_name": "Gemini 1.5 Flash", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥128K", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Context ≥128K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_output_tokens": 8192, "modalities": { "input": [ "doc", "image", "pdf" ], "output": [] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "vision": true, "pdf_input": true }, "knowledge_cutoff": "2024-05", "max_input_tokens": 1008192, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Gemini 1.5 Flash 是 Google 最新的多模态 AI 模型，处理速度快，支持文本、图像与视频输入，适用于高效任务扩展。", "zh-TW": "Gemini 1.5 Flash 是 Google 最新的多模態 AI 模型，具備快速處理能力，支援文字、圖像與影片輸入，能高效擴展至各類任務。", "ja-JP": "Gemini 1.5 Flash は、Google による最新のマルチモーダル AI モデルで、テキスト・画像・動画入力に対応し、タスク全体の効率的なスケーリングを実現します。", "ru-RU": "Gemini 1.5 Flash — новейшая мультимодальная модель ИИ от Google с быстрой обработкой, поддержкой текста, изображений и видео для эффективного масштабирования задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.5 Flash" } ] }, { "slug": "google/gemini-1.5-flash-latest-gt-128k", "model_name": "gemini-1.5-flash-latest-gt-128k", "display_name": "gemini-1.5-flash-latest-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-latest-gt-128k" } ] }, { "slug": "google/gemini-1.5-flash-latest-lte-128k", "model_name": "gemini-1.5-flash-latest-lte-128k", "display_name": "gemini-1.5-flash-latest-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-latest-lte-128k" } ] }, { "slug": "google/gemini-1.5-flash-lte-128k", "model_name": "gemini-1.5-flash-lte-128k", "display_name": "gemini-1.5-flash-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-lte-128k" } ] }, { "slug": "google/gemini-1.5-flash-preview-0514", "model_name": "gemini-1.5-flash-preview-0514", "display_name": "gemini-1.5-flash-preview-0514", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-flash-preview-0514" } ] }, { "slug": "google/gemini-1.5-pro", "model_name": "gemini-1.5-pro", "display_name": "Gemini 1.5 Pro", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "pydantic-prices+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "tracks": [ { "label": "Context ≥128K", "source": "pydantic-prices", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices" } }, { "label": "Base pricing", "source": "pydantic-prices", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Context ≥128K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.3125" }, "image_input": { "unit": "per_image", "price": "0.00032875" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥128K", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Context ≥128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Google's most capable multimodal model with an extremely long context window of up to 1 million tokens. It excels at complex reasoning, long-form content processing, and multimodal understanding.", "max_input_tokens": 1000000, "capabilities": { "function_calling": true, "parallel_function_calling": true, "structured_output": true, "vision": true, "pdf_input": true }, "max_output_tokens": 8192, "modalities": { "input": [ "image", "pdf" ], "output": [] }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.5 Pro" } ] }, { "slug": "google/gemini-1.5-pro-001", "model_name": "gemini-1.5-pro-001", "display_name": "Gemini 1.5 Pro 001", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.3125" }, "image_input": { "unit": "per_image", "price": "0.00032875" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Context ≥128K", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "80" } } } ], "max_output_tokens": 8192, "modalities": { "input": [ "doc", "image", "pdf" ], "output": [] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "parallel_function_calling": true, "structured_output": true, "vision": true, "pdf_input": true }, "released_at": "2024-02-15", "knowledge_cutoff": "2024-05", "max_input_tokens": 2008192, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Gemini 1.5 Pro 001 是一款可扩展的多模态 AI 解决方案，适用于复杂任务。", "zh-TW": "Gemini 1.5 Pro 001 是一款可擴展的多模態 AI 解決方案，適用於處理複雜任務。", "ja-JP": "Gemini 1.5 Pro 001 は、複雑なタスクに対応するスケーラブルなマルチモーダル AI ソリューションです。", "ru-RU": "Gemini 1.5 Pro 001 — масштабируемое мультимодальное ИИ-решение для сложных задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.5 Pro 001" } ] }, { "slug": "google/gemini-1.5-pro-001-gt-128k", "model_name": "gemini-1.5-pro-001-gt-128k", "display_name": "gemini-1.5-pro-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-pro-001-gt-128k" } ] }, { "slug": "google/gemini-1.5-pro-001-lte-128k", "model_name": "gemini-1.5-pro-001-lte-128k", "display_name": "gemini-1.5-pro-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-pro-001-lte-128k" } ] }, { "slug": "google/gemini-1.5-pro-002", "model_name": "gemini-1.5-pro-002", "display_name": "Gemini 1.5 Pro 002", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.3125" }, "image_input": { "unit": "per_image", "price": "0.00032875" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Context ≥128K", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "80" } } } ], "max_output_tokens": 8192, "modalities": { "input": [ "doc", "image", "pdf" ], "output": [] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "parallel_function_calling": true, "structured_output": true, "vision": true, "pdf_input": true }, "released_at": "2024-09-24", "knowledge_cutoff": "2024-05", "max_input_tokens": 2008192, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Gemini 1.5 Pro 002 是最新的生产级模型，在数学、长上下文和视觉任务方面输出质量更高。", "zh-TW": "Gemini 1.5 Pro 002 是最新的生產就緒模型，輸出品質更高，特別適用於數學、長上下文與視覺任務。", "ja-JP": "Gemini 1.5 Pro 002 は、特に数学、長文コンテキスト、視覚タスクにおいて高品質な出力を提供する最新の本番対応モデルです。", "ru-RU": "Gemini 1.5 Pro 002 — новейшая модель, готовая к производству, с более качественным выводом, особенно в математике, длинном контексте и визуальных задачах." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.5 Pro 002" } ] }, { "slug": "google/gemini-1.5-pro-002-batchx", "model_name": "gemini-1.5-pro-002-batchx", "display_name": "gemini-1.5-pro-002-batchx", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-pro-002-batchx" } ] }, { "slug": "google/gemini-1.5-pro-002-gt-128k", "model_name": "gemini-1.5-pro-002-gt-128k", "display_name": "gemini-1.5-pro-002-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-pro-002-gt-128k" } ] }, { "slug": "google/gemini-1.5-pro-002-lte-128k", "model_name": "gemini-1.5-pro-002-lte-128k", "display_name": "gemini-1.5-pro-002-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-pro-002-lte-128k" } ] }, { "slug": "google/gemini-1.5-pro-128k", "model_name": "gemini-1.5-pro-128k", "display_name": "Gemini 1.5 Pro", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.5 Pro" } ] }, { "slug": "google/gemini-1.5-pro-gt-128k", "model_name": "gemini-1.5-pro-gt-128k", "display_name": "gemini-1.5-pro-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-pro-gt-128k" } ] }, { "slug": "google/gemini-1.5-pro-latest-gt-128k", "model_name": "gemini-1.5-pro-latest-gt-128k", "display_name": "gemini-1.5-pro-latest-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-pro-latest-gt-128k" } ] }, { "slug": "google/gemini-1.5-pro-latest-lte-128k", "model_name": "gemini-1.5-pro-latest-lte-128k", "display_name": "gemini-1.5-pro-latest-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-pro-latest-lte-128k" } ] }, { "slug": "google/gemini-1.5-pro-lte-128k", "model_name": "gemini-1.5-pro-lte-128k", "display_name": "gemini-1.5-pro-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-pro-lte-128k" } ] }, { "slug": "google/gemini-1.5-pro-preview-0409", "model_name": "gemini-1.5-pro-preview-0409", "display_name": "gemini-1.5-pro-preview-0409", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-pro-preview-0409" } ] }, { "slug": "google/gemini-1.5-pro-preview-0514", "model_name": "gemini-1.5-pro-preview-0514", "display_name": "gemini-1.5-pro-preview-0514", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-pro-preview-0514" } ] }, { "slug": "google/gemini-1.5-vision", "model_name": "gemini-1.5-vision", "display_name": "gemini-1.5-vision", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "30" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "vision_understanding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-1.5-vision" } ] }, { "slug": "google/gemini-2-5-flash-tts", "model_name": "gemini-2-5-flash-tts", "display_name": "Gemini 2.5 Flash TTS", "vendor": "google", "pricing": [ { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" }, "provider_model_id": "gemini-2.5-flash-tts" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "northamerica-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-tts", "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Speech generation model for controllable voice, narration, and audio delivery", "released_at": "2025-09-30", "knowledge_cutoff": "2025-01", "max_input_tokens": 32768, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "family": "gemini-flash", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "prompt_caching": true, "audio_output": true }, "model_type": "speech_synthesis", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemini-2.5-flash-tts", "google/gemini-2.5-flash-tts" ], "price_history": [ { "date": "2026-08-10", "kind": "listed", "note": "Gemini 2.5 Flash TTS" } ] }, { "slug": "google/gemini-2-5-pro-tts", "model_name": "gemini-2-5-pro-tts", "display_name": "Gemini 2.5 Pro TTS", "vendor": "google", "pricing": [ { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" }, "provider_model_id": "gemini-2.5-pro-tts" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "asia-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "asia-east2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "asia-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "asia-northeast3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "asia-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "asia-southeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "australia-southeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "eu", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "europe-west2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "europe-west3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "europe-west6", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "europe-west8", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "europe-west9", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "me-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "me-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "me-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "northamerica-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "southamerica-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "us", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-pro-tts", "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Speech generation model for controllable voice, narration, and audio delivery", "released_at": "2025-09-30", "knowledge_cutoff": "2025-01", "max_input_tokens": 32768, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "family": "gemini-pro", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "prompt_caching": true, "audio_output": true }, "model_type": "speech_synthesis", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemini-2.5-pro-tts", "google/gemini-2.5-pro-tts" ], "price_history": [ { "date": "2026-08-10", "kind": "listed", "note": "Gemini 2.5 Pro TTS" } ] }, { "slug": "google/gemini-2.0-flash", "model_name": "gemini-2.0-flash", "display_name": "gemini-2.0-flash", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+pydantic-prices+truefoundry+llmdb+lobehub-modelbank+pricetoken+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "audio_input": { "unit": "per_M_tokens", "price": "0.7" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.175" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+truefoundry", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Google Vertex AI", "official": true, "source": "litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "audio_input": { "unit": "per_M_tokens", "price": "0.7" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.6" }, "message": "completion from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.6" }, "message": "completion from llmdb conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.75", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west8", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west9", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://ai.google.dev/pricing#2_0flash", "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecated": true, "model_type": "omni", "deprecation_date": "2026-06-01", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "rate_limits": { "rpm": 10000, "tpm": 10000000 }, "intro": "The newest generation of Google's Gemini models, featuring improved reasoning, instruction following, and factual accuracy, with the Flash variant optimized for cost-efficiency and performance.", "modalities": { "input": [ "audio", "image" ], "output": [ "audio" ] }, "released_at": "2024-12-11", "knowledge_cutoff": "2024-06", "family": "gemini-flash", "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemini-2.0-flash-20250609", "google/gemini-2.0-flash" ], "intro_i18n": { "zh-CN": "Gemini 2.0 Flash 提供下一代功能，包括卓越速度、原生工具使用、多模态生成以及 100 万 token 上下文窗口。", "zh-TW": "Gemini 2.0 Flash 提供次世代功能，包括極速處理、原生工具使用、多模態生成，以及 100 萬 token 的上下文視窗。", "ja-JP": "Gemini 2.0 Flash は、次世代の機能を提供するモデルで、卓越したスピード、ネイティブツールの使用、マルチモーダル生成、100万トークンのコンテキストウィンドウを備えています。", "ru-RU": "Gemini 2.0 Flash предлагает функции следующего поколения, включая исключительную скорость, нативное использование инструментов, мультимодальную генерацию и контекст до 1 миллиона токенов." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-2.0-flash-001", "model_name": "gemini-2.0-flash-001", "display_name": "gemini-2.0-flash-001", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "audio_input": { "unit": "per_M_tokens", "price": "0.7" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.175" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "google_search_grounding": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+truefoundry+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "google_search_grounding": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west8", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west9", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-001", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-06-01", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "rate_limits": { "rpm": 10000, "tpm": 10000000 }, "modalities": { "input": [ "doc", "image", "pdf" ], "output": [] }, "released_at": "2025-02-05", "knowledge_cutoff": "2024-08", "family": "gemini-flash", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "deepinfra/google/gemini-2.0-flash-001", "google/gemini-2.0-flash-001" ], "intro_i18n": { "zh-CN": "Gemini 2.0 Flash 提供下一代功能，包括卓越速度、原生工具使用、多模态生成以及 100 万 token 上下文窗口。", "zh-TW": "Gemini 2.0 Flash 提供次世代功能，包括極速處理、原生工具使用、多模態生成，以及 100 萬 token 的上下文視窗。", "ja-JP": "Gemini 2.0 Flash は、次世代の機能を提供するモデルで、卓越したスピード、ネイティブツールの使用、マルチモーダル生成、100万トークンのコンテキストウィンドウを備えています。", "ru-RU": "Gemini 2.0 Flash предлагает функции следующего поколения, включая исключительную скорость, нативное использование инструментов, мультимодальную генерацию и контекст до 1 миллиона токенов." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-2.0-flash-001-gt-128k", "model_name": "gemini-2.0-flash-001-gt-128k", "display_name": "gemini-2.0-flash-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-001-gt-128k" } ] }, { "slug": "google/gemini-2.0-flash-001-lte-128k", "model_name": "gemini-2.0-flash-001-lte-128k", "display_name": "gemini-2.0-flash-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-001-lte-128k" } ] }, { "slug": "google/gemini-2.0-flash-exp-001", "model_name": "gemini-2.0-flash-exp-001", "display_name": "gemini-2.0-flash-exp-001", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-exp-001" } ] }, { "slug": "google/gemini-2.0-flash-exp-001-gt-128k", "model_name": "gemini-2.0-flash-exp-001-gt-128k", "display_name": "gemini-2.0-flash-exp-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-exp-001-gt-128k" } ] }, { "slug": "google/gemini-2.0-flash-exp-001-lte-128k", "model_name": "gemini-2.0-flash-exp-001-lte-128k", "display_name": "gemini-2.0-flash-exp-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-exp-001-lte-128k" } ] }, { "slug": "google/gemini-2.0-flash-exp-image-generation", "model_name": "gemini-2.0-flash-exp-image-generation", "display_name": "gemini-2.0-flash-exp-image-generation", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_output": { "unit": "per_image", "price": "0.039" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_output": "litellm", "web_search": "llmdb" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://ai.google.dev/pricing", "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "image_generation", "capabilities": { "vision": true }, "rate_limits": { "rpm": 10, "tpm": 250000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] } }, { "slug": "google/gemini-2.0-flash-exp:free", "model_name": "gemini-2.0-flash-exp:free", "display_name": "Google Gemini 2.0 Flash Experimental", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "helicone-registry", "charges": { "image_output": { "unit": "per_M_tokens", "price": "120" } }, "provenance": { "base_charges": { "image_output": "helicone-registry" }, "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.0-flash-exp" }, { "provider": "google-vertex", "official": true, "source": "helicone-registry+portkey", "charges": { "image_output": { "unit": "per_M_tokens", "price": "120" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "image_output": "helicone-registry", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "helicone-registry+portkey", "charge_sources": { "image_output": "helicone-registry", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.0-flash-exp", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Experimental version of Gemini 2.0 Flash with native image generation capabilities. Features multimodal input and output support including text and images.", "knowledge_cutoff": "2024-12", "max_input_tokens": 1000000, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "parameters": { "supported": [ "max_tokens", "response_format", "seed", "stop", "temperature", "top_p" ] }, "capabilities": { "vision": true, "structured_output": true, "image_output": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemini-2.0-flash-exp", "google/gemini-2.0-flash-exp:free" ], "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Google Gemini 2.0 Flash Experimental" } ] }, { "slug": "google/gemini-2.0-flash-gt-128k", "model_name": "gemini-2.0-flash-gt-128k", "display_name": "gemini-2.0-flash-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-gt-128k" } ] }, { "slug": "google/gemini-2.0-flash-lite", "model_name": "gemini-2.0-flash-lite", "display_name": "gemini-2.0-flash-lite", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google Cloud", "official": true, "source": "litellm+pydantic-prices+truefoundry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01875" }, "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "computeprices" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "computeprices", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from computeprices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "computeprices", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "completion from computeprices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "computeprices", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.01875" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "cache_read from computeprices conflicts with litellm; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "computeprices", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.0375" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.075" }, "message": "batch prompt from computeprices conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "computeprices", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "batch completion from computeprices conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gemini-2-0-flash-lite", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "2.666667" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Google Vertex AI", "official": true, "source": "litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01875" }, "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west8", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west9", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-06-01", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "rate_limits": { "rpm": 4000, "tpm": 4000000 }, "intro": "A lighter, more cost-effective version of Gemini 2.0 Flash, designed for applications requiring high efficiency while maintaining good performance. Ideal for high-volume, cost-sensitive deployments.", "modalities": { "input": [ "doc", "image", "pdf" ], "output": [ "audio" ] }, "released_at": "2024-12-11", "knowledge_cutoff": "2024-06", "family": "gemini-flash-lite", "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemini-2-0-flash-lite", "google/gemini-2.0-flash-lite" ], "intro_i18n": { "zh-CN": "Gemini 2.0 Flash 的一个轻量变体，优化了成本效率与低延迟表现。", "zh-TW": "Gemini 2.0 Flash 的一個變體，針對成本效益與低延遲進行最佳化。", "ja-JP": "コスト効率と低遅延に最適化された Gemini 2.0 Flash のバリアントです。", "ru-RU": "Вариант Gemini 2.0 Flash, оптимизированный по стоимости и задержке." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-2.0-flash-lite-001", "model_name": "gemini-2.0-flash-lite-001", "display_name": "gemini-2.0-flash-lite-001", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01875" }, "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01875" }, "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-east2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-northeast3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-southeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "australia-southeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west6", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "europe-west8", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "europe-west9", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "me-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "me-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "me-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "northamerica-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "southamerica-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "0.075" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.0-flash-lite-001", "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash", "max_input_tokens": 1048576, "max_output_tokens": 8192, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-06-01", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "rate_limits": { "rpm": 4000, "tpm": 4000000 }, "modalities": { "input": [ "doc", "image", "pdf" ], "output": [ "audio" ] }, "released_at": "2025-02-05", "knowledge_cutoff": "2024-08", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-2.0-flash-lite-001" ], "intro_i18n": { "zh-CN": "Gemini 2.0 Flash 的一个轻量变体，优化了成本效率与低延迟表现。", "zh-TW": "Gemini 2.0 Flash 的一個變體，針對成本效益與低延遲進行最佳化。", "ja-JP": "コスト効率と低遅延に最適化された Gemini 2.0 Flash のバリアントです。", "ru-RU": "Вариант Gemini 2.0 Flash, оптимизированный по стоимости и задержке." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-2.0-flash-lite-001-gt-128k", "model_name": "gemini-2.0-flash-lite-001-gt-128k", "display_name": "gemini-2.0-flash-lite-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "0" }, "google_search_grounding": { "unit": "per_k_calls", "price": "0" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-lite-001-gt-128k" } ] }, { "slug": "google/gemini-2.0-flash-lite-001-lte-128k", "model_name": "gemini-2.0-flash-lite-001-lte-128k", "display_name": "gemini-2.0-flash-lite-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "0" }, "google_search_grounding": { "unit": "per_k_calls", "price": "0" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-lite-001-lte-128k" } ] }, { "slug": "google/gemini-2.0-flash-lite-gt-128k", "model_name": "gemini-2.0-flash-lite-gt-128k", "display_name": "gemini-2.0-flash-lite-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "0" }, "google_search_grounding": { "unit": "per_k_calls", "price": "0" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-lite-gt-128k" } ] }, { "slug": "google/gemini-2.0-flash-lite-lte-128k", "model_name": "gemini-2.0-flash-lite-lte-128k", "display_name": "gemini-2.0-flash-lite-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "0" }, "google_search_grounding": { "unit": "per_k_calls", "price": "0" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-lite-lte-128k" } ] }, { "slug": "google/gemini-2.0-flash-lite-preview-02-05", "model_name": "gemini-2.0-flash-lite-preview-02-05", "display_name": "gemini-2.0-flash-lite-preview-02-05", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-lite-preview-02-05" } ] }, { "slug": "google/gemini-2.0-flash-lte-128k", "model_name": "gemini-2.0-flash-lte-128k", "display_name": "gemini-2.0-flash-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-lte-128k" } ] }, { "slug": "google/gemini-2.0-flash-preview-image-generation", "model_name": "gemini-2.0-flash-preview-image-generation", "display_name": "gemini-2.0-flash-preview-image-generation", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.0-flash-preview-image-generation" } ] }, { "slug": "google/gemini-2.5-computer-use-preview-10-2025", "model_name": "gemini-2.5-computer-use-preview-10-2025", "display_name": "Gemini 2.5 Computer Use Preview 10-2025", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "llmdb" }, "discarded_conflicts": [ { "kind": "tier_schedule", "source": "models-dev", "threshold": 200000, "inclusive": false, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." }, { "kind": "tier_schedule", "source": "litellm", "threshold": 200000, "inclusive": false, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "threshold": 200000, "inclusive": true, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." } ], "verification_status": "conflicting" }, "warnings": [ { "code": "invalid_source_tier", "source": "models-dev", "message": "tier threshold 200000 exceeds model context window 131072." }, { "code": "invalid_source_tier", "source": "litellm", "message": "tier threshold 200000 exceeds model context window 131072." }, { "code": "invalid_source_tier", "source": "truefoundry", "message": "tier threshold 200000 exceeds model context window 131072." } ] }, { "provider": "google-vertex", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" }, "discarded_conflicts": [ { "kind": "tier_schedule", "source": "litellm", "threshold": 200000, "inclusive": false, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." }, { "kind": "tier_schedule", "source": "portkey", "threshold": 200000, "inclusive": false, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." } ], "verification_status": "conflicting" }, "warnings": [ { "code": "invalid_source_tier", "source": "litellm", "message": "tier threshold 200000 exceeds model context window 131072." }, { "code": "invalid_source_tier", "source": "portkey", "message": "tier threshold 200000 exceeds model context window 131072." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "threshold": 200000, "inclusive": true, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "threshold": 200000, "inclusive": true, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-computer-use-preview-10-2025", "region": "us-central1", "warnings": [ { "code": "invalid_source_tier", "source": "truefoundry", "message": "tier threshold 200000 exceeds model context window 131072." } ] } ], "intro": "Specialized Gemini 2.5 model for browser-control agents that automate UI tasks", "released_at": "2025-10-07", "knowledge_cutoff": "2025-01", "max_input_tokens": 131072, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gemini-pro", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "computer_use": true, "parallel_function_calling": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/computer-use", "model_type": "vision_understanding", "rate_limits": { "rpm": 2000, "tpm": 800000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "google/gemini-2.5-computer-use-preview-10-2025" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-25", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-25", "kind": "limit", "old": "128000", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-07-25", "kind": "limit", "old": "64000", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" } ] }, { "slug": "google/gemini-2.5-computer-use-preview-10-2025-gt-128k", "model_name": "gemini-2.5-computer-use-preview-10-2025-gt-128k", "display_name": "gemini-2.5-computer-use-preview-10-2025-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "vision_understanding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-computer-use-preview-10-2025-gt-128k" } ] }, { "slug": "google/gemini-2.5-computer-use-preview-10-2025-lte-128k", "model_name": "gemini-2.5-computer-use-preview-10-2025-lte-128k", "display_name": "gemini-2.5-computer-use-preview-10-2025-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "vision_understanding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-computer-use-preview-10-2025-lte-128k" } ] }, { "slug": "google/gemini-2.5-flash", "model_name": "gemini-2.5-flash", "display_name": "Gemini 2.5 Flash", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_write": { "unit": "per_M_tokens", "price": "0.3" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.1" }, "cache_storage": { "unit": "per_M_tokens_per_hour", "price": "1" }, "image_input": { "unit": "per_M_tokens", "price": "0.3" }, "video_input": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_write": "helicone-registry", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "computeprices" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+helicone-registry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_write": "helicone-registry", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.03" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.075" }, "message": "cache_read from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.03" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.075" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gemini-2-5-flash", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+helicone-registry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "cache_write": { "unit": "per_M_tokens", "price": "0.383" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.1" }, "cache_storage": { "unit": "per_M_tokens_per_hour", "price": "1" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "image_output": { "unit": "per_M_tokens", "price": "30" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+helicone-registry+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0.383" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "cache_write from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "0.666667" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "5" } } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-northeast3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-southeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "australia-southeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west8", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west9", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "northamerica-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "southamerica-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "released_at": "2025-06-17", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash", "reasoning_config": { "mandatory": false, "budget_min": 0 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "model_type": "image_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 100000, "tpm": 8000000 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "deprecated": true, "aliases": [ "coding/gemini-2.5-flash", "deepinfra/google/gemini-2.5-flash", "gemini-2-5-flash", "gemini/gemini-2.5-flash", "google/gemini-2.5-flash", "vertex/gemini-2.5-flash" ], "intro_i18n": { "zh-CN": "Gemini 2.5 Flash 是 Google 功能最全、性价比最高的模型。", "zh-TW": "Gemini 2.5 Flash 是 Google 功能最完整、性價比最高的模型。", "ja-JP": "Gemini 2.5 Flash は、Google によるフル機能を備えた最もコスト効率の高いモデルです。", "ru-RU": "Gemini 2.5 Flash — самая выгодная модель от Google с полным набором возможностей." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "google/gemini-2.5-flash-gt-128k", "model_name": "gemini-2.5-flash-gt-128k", "display_name": "gemini-2.5-flash-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-gt-128k" } ] }, { "slug": "google/gemini-2.5-flash-image", "model_name": "gemini-2.5-flash-image", "display_name": "Nano Banana", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "image_output": { "unit": "per_image", "price": "0.039" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "image_input": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "image_output": "litellm", "cache_write_1h": "truefoundry", "image_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "image_output": "litellm", "cache_write_1h": "truefoundry", "image_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.039" }, "discarded_charge": { "unit": "per_M_tokens", "price": "30" }, "message": "image_output from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.039" }, "message": "completion from ai-model-directory conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.041667" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "image_output": { "unit": "per_image", "price": "0.039" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "image_output": "litellm", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "image_output": "litellm", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.039" }, "discarded_charge": { "unit": "per_M_tokens", "price": "30" }, "message": "image_output from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.041667", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.041667" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "5" } } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "europe-west8", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "global", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-image", "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Nano Banana image model for fast generation, edits, and character-consistent assets", "released_at": "2025-08-26", "knowledge_cutoff": "2024-06", "max_input_tokens": 32768, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "family": "gemini-flash", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "parallel_function_calling": true, "web_search": true, "stream": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image", "model_type": "image_generation", "rate_limits": { "rpm": 100000, "tpm": 8000000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "deprecation_date": "2026-10-02", "parameters": { "supported": [ "max_tokens", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_p" ] }, "aliases": [ "google/gemini-2.5-flash-image", "vertex/gemini-2.5-flash-image" ], "intro_i18n": { "zh-CN": "Nano Banana 是 Google 最新、最快、最高效的原生多模态模型，支持对话式图像生成与编辑。", "zh-TW": "Nano Banana 是 Google 最新、最快且最有效率的原生多模態模型，支援對話式圖像生成與編輯。", "ja-JP": "Nano Banana は、Google による最新かつ最速、最も効率的なネイティブマルチモーダルモデルで、会話形式での画像生成と編集が可能です。", "ru-RU": "Nano Banana — новейшая, самая быстрая и эффективная нативная мультимодальная модель от Google, поддерживающая генерацию и редактирование изображений в диалоговом режиме." }, "price_history": [ { "date": "2026-07-12", "kind": "price", "provider": "google-vertex", "charge": "completion", "old": "2.5", "new": "30" }, { "date": "2026-07-09", "kind": "capability", "note": "audio_input: true→false" }, { "date": "2026-07-09", "kind": "capability", "note": "video_input: true→false" }, { "date": "2026-07-04", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-04", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-2.5-flash-image-gt-128k", "model_name": "gemini-2.5-flash-image-gt-128k", "display_name": "gemini-2.5-flash-image-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "image_output": { "unit": "per_M_tokens", "price": "30" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-image-gt-128k" } ] }, { "slug": "google/gemini-2.5-flash-image-lte-128k", "model_name": "gemini-2.5-flash-image-lte-128k", "display_name": "gemini-2.5-flash-image-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "image_output": { "unit": "per_M_tokens", "price": "30" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-image-lte-128k" } ] }, { "slug": "google/gemini-2.5-flash-image-preview", "model_name": "gemini-2.5-flash-image-preview", "display_name": "Nano Banana Preview (Gemini 2.5 Flash Image Preview)", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "image_output": { "unit": "per_M_tokens", "price": "30" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "maps": { "unit": "per_request", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "image_output": "0.5", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "image_output": "0.5", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "capabilities": { "reasoning": true, "prompt_caching": true, "image_output": true }, "released_at": "2025-03-20", "knowledge_cutoff": "2025-01", "max_input_tokens": 32768, "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text", "image" ] }, "family": "gemini-flash", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-2.5-flash-image-preview" ], "model_type": "image_generation", "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Nano Banana Preview (Gemini 2.5 Flash Image Preview)" } ] }, { "slug": "google/gemini-2.5-flash-image-preview-gt-128k", "model_name": "gemini-2.5-flash-image-preview-gt-128k", "display_name": "gemini-2.5-flash-image-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "image_output_1024px": { "unit": "per_image", "price": "0.039" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "image_output_1024px": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "image_output_1024px": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-image-preview-gt-128k" } ] }, { "slug": "google/gemini-2.5-flash-image-preview-lte-128k", "model_name": "gemini-2.5-flash-image-preview-lte-128k", "display_name": "gemini-2.5-flash-image-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_M_tokens", "price": "30" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.039" } }, "provenance": { "base_charges": { "web_search": "portkey", "image_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-image-preview-lte-128k" } ] }, { "slug": "google/gemini-2.5-flash-image:image", "model_name": "gemini-2.5-flash-image:image", "display_name": "Nano Banana", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "image_output": { "unit": "per_M_tokens", "price": "30" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank", "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-08-26", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Nano Banana 是 Google 最新、最快、最高效的原生多模态模型，支持对话式图像生成与编辑。", "zh-TW": "Nano Banana 是 Google 最新、最快且最有效率的原生多模態模型，支援對話式圖像生成與編輯。", "ja-JP": "Nano Banana は、Google による最新かつ最速、最も効率的なネイティブマルチモーダルモデルで、会話形式での画像生成と編集が可能です。", "ru-RU": "Nano Banana — новейшая, самая быстрая и эффективная нативная мультимодальная модель от Google, поддерживающая генерацию и редактирование изображений в диалоговом режиме." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Nano Banana" } ] }, { "slug": "google/gemini-2.5-flash-lite", "model_name": "gemini-2.5-flash-lite", "display_name": "Gemini 2.5 Flash-Lite", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.4" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.1" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.02499999" }, "cache_storage": { "unit": "per_M_tokens_per_hour", "price": "1" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_write": "helicone-registry", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "google_search_grounding": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+helicone-registry+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_write": "helicone-registry", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "google_search_grounding": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.01" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.025" }, "message": "cache_read from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.01" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.025" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+helicone-registry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.4" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write": { "unit": "per_M_tokens", "price": "0.1" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.02499999" }, "cache_storage": { "unit": "per_M_tokens_per_hour", "price": "1" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write": "helicone-registry", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+helicone-registry+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write": "helicone-registry", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.01" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.025" }, "message": "cache_read from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.01" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.025" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "1.5" } } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "europe-west8", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "europe-west9", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite", "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents", "released_at": "2025-06-17", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash-lite", "reasoning_config": { "mandatory": false, "budget_min": 512 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 15, "tpm": 250000 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "deprecated": true, "aliases": [ "gemini-2-5-flash-lite", "gemini/gemini-2.5-flash-lite", "google/gemini-2.5-flash-lite", "vertex/gemini-2.5-flash-lite" ], "intro_i18n": { "zh-CN": "Gemini 2.5 Flash-Lite 是 Google 最小、性价比最高的模型，适用于大规模使用场景。", "zh-TW": "Gemini 2.5 Flash-Lite 是 Google 體積最小、性價比最高的模型，專為大規模應用而設計。", "ja-JP": "Gemini 2.5 Flash-Lite は、Google による最小かつ最もコストパフォーマンスに優れたモデルで、大規模利用に適しています。", "ru-RU": "Gemini 2.5 Flash-Lite — самая компактная и экономичная модель от Google, предназначенная для масштабного использования." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "google/gemini-2.5-flash-lite-gt-128k", "model_name": "gemini-2.5-flash-lite-gt-128k", "display_name": "gemini-2.5-flash-lite-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "cache_write": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-lite-gt-128k" } ] }, { "slug": "google/gemini-2.5-flash-lite-lte-128k", "model_name": "gemini-2.5-flash-lite-lte-128k", "display_name": "gemini-2.5-flash-lite-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "cache_write": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-lite-lte-128k" } ] }, { "slug": "google/gemini-2.5-flash-lite-preview-06-17", "model_name": "gemini-2.5-flash-lite-preview-06-17", "display_name": "gemini-2.5-flash-lite-preview-06-17", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.4" }, "audio_input": { "unit": "per_M_tokens", "price": "0.5" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "provider_name": "Google Vertex AI", "official": true, "source": "litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.4" }, "audio_input": { "unit": "per_M_tokens", "price": "0.5" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "maps": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.025" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.01" }, "message": "cache_read from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "0.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2025-11-18", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 15, "tpm": 250000 }, "released_at": "2025-06-17", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash-lite", "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "aliases": [ "google/gemini-2.5-flash-lite-preview-06-17" ], "intro_i18n": { "zh-CN": "Gemini 2.5 Flash-Lite Preview 是 Google 最小、性价比最高的模型，适用于大规模使用场景。", "zh-TW": "Gemini 2.5 Flash-Lite Preview 是 Google 體積最小、性價比最高的模型，專為大規模應用而設計。", "ja-JP": "Gemini 2.5 Flash-Lite Preview は、Google による最小かつ最もコストパフォーマンスに優れたモデルで、大規模利用に適しています。", "ru-RU": "Gemini 2.5 Flash-Lite Preview — самая компактная и экономичная модель от Google, предназначенная для масштабного использования." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-2.5-flash-lite-preview-06-17-gt-128k", "model_name": "gemini-2.5-flash-lite-preview-06-17-gt-128k", "display_name": "gemini-2.5-flash-lite-preview-06-17-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-lite-preview-06-17-gt-128k" } ] }, { "slug": "google/gemini-2.5-flash-lite-preview-06-17-lte-128k", "model_name": "gemini-2.5-flash-lite-preview-06-17-lte-128k", "display_name": "gemini-2.5-flash-lite-preview-06-17-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-lite-preview-06-17-lte-128k" } ] }, { "slug": "google/gemini-2.5-flash-lite-preview-09-2025", "model_name": "gemini-2.5-flash-lite-preview-09-2025", "display_name": "gemini-2.5-flash-lite-preview-09-2025", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.4" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+truefoundry", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Google Vertex AI", "official": true, "source": "litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.4" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.01" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.025" }, "message": "cache_read from llmdb conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.03" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-lite-preview-09-2025", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "max_input_tokens": 1048576, "max_output_tokens": 65535, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true, "image_output": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "deprecated": true, "deprecation_date": "2026-03-31", "rate_limits": { "rpm": 15, "tpm": 250000 }, "modalities": { "input": [ "audio", "doc", "image", "pdf" ], "output": [] }, "released_at": "2025-09-25", "knowledge_cutoff": "2025-01", "family": "gemini-flash-lite", "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "aliases": [ "gemini-2-5-flash-lite-preview-09-2025", "google/gemini-2.5-flash-lite-preview-09-2025" ], "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-09", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "google/gemini-2.5-flash-lite-preview-09-2025-gt-128k", "model_name": "gemini-2.5-flash-lite-preview-09-2025-gt-128k", "display_name": "gemini-2.5-flash-lite-preview-09-2025-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "cache_write": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-lite-preview-09-2025-gt-128k" } ] }, { "slug": "google/gemini-2.5-flash-lite-preview-09-2025-lte-128k", "model_name": "gemini-2.5-flash-lite-preview-09-2025-lte-128k", "display_name": "gemini-2.5-flash-lite-preview-09-2025-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "cache_write": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-lite-preview-09-2025-lte-128k" } ] }, { "slug": "google/gemini-2.5-flash-lite-preview-tts", "model_name": "gemini-2.5-flash-lite-preview-tts", "display_name": "gemini-2.5-flash-lite-preview-tts", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "speech_synthesis", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-lite-preview-tts" } ] }, { "slug": "google/gemini-2.5-flash-lte-128k", "model_name": "gemini-2.5-flash-lte-128k", "display_name": "gemini-2.5-flash-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-lte-128k" } ] }, { "slug": "google/gemini-2.5-flash-native-audio-latest", "model_name": "gemini-2.5-flash-native-audio-latest", "display_name": "gemini-2.5-flash-native-audio-latest", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "12" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "audio_output": "truefoundry", "web_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "audio_input from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://ai.google.dev/pricing", "max_input_tokens": 1048576, "max_output_tokens": 8192, "model_type": "realtime_omni", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true }, "rate_limits": { "rpm": 10, "tpm": 250000 }, "modalities": { "input": [ "text", "audio", "video" ], "output": [ "text", "audio" ] }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" } ] }, { "slug": "google/gemini-2.5-flash-native-audio-preview-09-2025", "model_name": "gemini-2.5-flash-native-audio-preview-09-2025", "display_name": "gemini-2.5-flash-native-audio-preview-09-2025", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "12" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "audio_output": "truefoundry", "web_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "audio_input from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://ai.google.dev/pricing", "max_input_tokens": 1048576, "max_output_tokens": 8192, "model_type": "realtime_omni", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true }, "rate_limits": { "rpm": 10, "tpm": 250000 }, "modalities": { "input": [ "text", "audio", "video", "image" ], "output": [ "text", "audio" ] }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" } ] }, { "slug": "google/gemini-2.5-flash-native-audio-preview-12-2025", "model_name": "gemini-2.5-flash-native-audio-preview-12-2025", "display_name": "gemini-2.5-flash-native-audio-preview-12-2025", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "12" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "audio_output": "truefoundry", "web_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "audio_input from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "prompt from ai-model-directory conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "completion from ai-model-directory conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://ai.google.dev/pricing", "max_input_tokens": 1048576, "max_output_tokens": 8192, "model_type": "realtime_omni", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "pdf_input": true }, "rate_limits": { "rpm": 10, "tpm": 250000 }, "modalities": { "input": [ "text", "audio", "video" ], "output": [ "text", "audio" ] }, "released_at": "2025-09-01", "knowledge_cutoff": "2025-01", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-08-01", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-01", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "google/gemini-2.5-flash-preview-04-17-gt-128k", "model_name": "gemini-2.5-flash-preview-04-17-gt-128k", "display_name": "gemini-2.5-flash-preview-04-17-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-preview-04-17-gt-128k" } ] }, { "slug": "google/gemini-2.5-flash-preview-04-17-lte-128k", "model_name": "gemini-2.5-flash-preview-04-17-lte-128k", "display_name": "gemini-2.5-flash-preview-04-17-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-preview-04-17-lte-128k" } ] }, { "slug": "google/gemini-2.5-flash-preview-04-17:thinking", "model_name": "gemini-2.5-flash-preview-04-17:thinking", "display_name": "Gemini 2.5 Flash Preview 04-17", "vendor": "google", "pricing": [ { "provider": "google-vertex", "provider_name": "Google Vertex AI", "official": true, "source": "portkey+llmdb", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "portkey", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.03" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0375" }, "message": "cache_read from llmdb conflicts with portkey; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gemini-2.5-flash-preview-04-17", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "3.6", "completion": "7.5", "cache_read": "1.666667" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1", "completion": "2.083333" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "stream": true, "pdf_input": true, "audio_input": true, "video_input": true }, "released_at": "2025-04-17", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "model_type": "deep_thinking", "family": "gemini-flash", "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemini-2.5-flash-preview-04-17" ], "intro_i18n": { "zh-CN": "Gemini 2.5 Flash Preview 是 Google 功能最全、性价比最高的模型。", "zh-TW": "Gemini 2.5 Flash Preview 是 Google 功能最完整、性價比最高的模型。", "ja-JP": "Gemini 2.5 Flash Preview は、Google によるフル機能を備えた最もコスト効率の高いモデルです。", "ru-RU": "Gemini 2.5 Flash Preview — самая выгодная модель от Google с полным набором возможностей." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 2.5 Flash Preview 04-17" } ] }, { "slug": "google/gemini-2.5-flash-preview-05-20-gt-128k", "model_name": "gemini-2.5-flash-preview-05-20-gt-128k", "display_name": "gemini-2.5-flash-preview-05-20-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-preview-05-20-gt-128k" } ] }, { "slug": "google/gemini-2.5-flash-preview-05-20-lte-128k", "model_name": "gemini-2.5-flash-preview-05-20-lte-128k", "display_name": "gemini-2.5-flash-preview-05-20-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-preview-05-20-lte-128k" } ] }, { "slug": "google/gemini-2.5-flash-preview-05-20:thinking", "model_name": "gemini-2.5-flash-preview-05-20:thinking", "display_name": "Gemini 2.5 Flash Preview 05-20", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "llmdb", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0375" } }, "provenance": { "base_charges": { "web_search": "llmdb", "prompt": "llmdb", "completion": "llmdb", "cache_read": "llmdb" }, "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-preview-05-20" }, { "provider": "google-vertex", "provider_name": "Google Vertex AI", "official": true, "source": "portkey+llmdb", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "portkey", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.03" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0375" }, "message": "cache_read from llmdb conflicts with portkey; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gemini-2.5-flash-preview-05-20", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "3.6", "completion": "7.5", "cache_read": "1.666667" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1", "completion": "2.083333" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "stream": true, "structured_output": true, "pdf_input": true, "audio_input": true, "video_input": true }, "released_at": "2025-05-20", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "model_type": "deep_thinking", "family": "gemini-flash", "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemini-2.5-flash-preview-05-20" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 2.5 Flash Preview 05-20" } ] }, { "slug": "google/gemini-2.5-flash-preview-09-2025", "model_name": "gemini-2.5-flash-preview-09-2025", "display_name": "gemini-2.5-flash-preview-09-2025", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm+truefoundry+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+truefoundry", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from llm-prices-www conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Google Vertex AI", "official": true, "source": "litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "image_output": { "unit": "per_M_tokens", "price": "30" }, "maps": { "unit": "per_request", "price": "0.025" }, "cache_write": { "unit": "per_M_tokens", "price": "0.383" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "cache_write": "llmdb" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "cache_write": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "0.666667" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-2.5-flash-preview-09-2025", "region": "global" } ], "docs_url": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "max_input_tokens": 1048576, "max_output_tokens": 65535, "model_type": "image_generation", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true, "image_output": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "deprecated": true, "deprecation_date": "2026-02-17", "rate_limits": { "rpm": 15, "tpm": 250000 }, "modalities": { "input": [ "doc", "image", "pdf" ], "output": [] }, "released_at": "2025-09-25", "knowledge_cutoff": "2025-01", "family": "gemini-flash", "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "aliases": [ "gemini-2-5-flash-preview-09-2025", "google/gemini-2.5-flash-preview-09-2025" ], "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "google/gemini-2.5-flash-preview-09-2025-gt-128k", "model_name": "gemini-2.5-flash-preview-09-2025-gt-128k", "display_name": "gemini-2.5-flash-preview-09-2025-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-preview-09-2025-gt-128k" } ] }, { "slug": "google/gemini-2.5-flash-preview-09-2025-lte-128k", "model_name": "gemini-2.5-flash-preview-09-2025-lte-128k", "display_name": "gemini-2.5-flash-preview-09-2025-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-preview-09-2025-lte-128k" } ] }, { "slug": "google/gemini-2.5-flash-preview-tts", "model_name": "gemini-2.5-flash-preview-tts", "display_name": "Gemini 2.5 Flash Preview TTS", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "audio_output": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+truefoundry", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "audio_output": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Speech generation model for controllable voice, narration, and audio delivery", "released_at": "2025-05-01", "knowledge_cutoff": "2025-01", "max_input_tokens": 8192, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "family": "gemini-flash", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_output": true, "structured_output": true }, "model_type": "speech_synthesis", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-2.5-flash-preview-tts" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" } ] }, { "slug": "google/gemini-2.5-flash-preview-tts-gt-128k", "model_name": "gemini-2.5-flash-preview-tts-gt-128k", "display_name": "gemini-2.5-flash-preview-tts-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "speech_synthesis", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-preview-tts-gt-128k" } ] }, { "slug": "google/gemini-2.5-flash-preview-tts-lte-128k", "model_name": "gemini-2.5-flash-preview-tts-lte-128k", "display_name": "gemini-2.5-flash-preview-tts-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "speech_synthesis", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-preview-tts-lte-128k" } ] }, { "slug": "google/gemini-2.5-flash-preview:thinking", "model_name": "gemini-2.5-flash-preview:thinking", "display_name": "gemini-2.5-flash-preview:thinking", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" }, "provider_model_id": "gemini-2.5-flash-preview" } ], "intro": "Gemini 2.5 Flash May 20th Checkpoint is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in \"thinking\" capabilities, enabling it to provide responses with greater accuracy and nuanced context handling.", "deprecated": true, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemini-2.5-flash-preview", "google/gemini-2.5-flash-preview", "google/gemini-2.5-flash-preview:thinking" ], "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-flash-preview:thinking" } ] }, { "slug": "google/gemini-2.5-pro", "model_name": "gemini-2.5-pro", "display_name": "Gemini 2.5 Pro", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_write": { "unit": "per_M_tokens", "price": "1.25" }, "cache_storage": { "unit": "per_M_tokens_per_hour", "price": "4.5" }, "image_input": { "unit": "per_M_tokens", "price": "1.25" }, "video_input": { "unit": "per_M_tokens", "price": "1.25" }, "audio_input": { "unit": "per_M_tokens", "price": "1.25" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_write": "helicone-registry", "cache_storage": "helicone-registry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank", "audio_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "computeprices" } }, { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank", "audio_input": "lobehub-modelbank" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+helicone-registry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_write": "helicone-registry", "cache_storage": "helicone-registry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank", "audio_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3125" }, "message": "cache_read from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "computeprices", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from computeprices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.31" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "pydantic-prices", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "pydantic-prices introduced a ≥200000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "helicone-registry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "helicone-registry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "threshold": 200000, "inclusive": false, "selected_charge": { "unit": "per_M_tokens", "price": "0.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.625" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gemini-2-5-pro", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.4" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "image_input": "2", "video_input": "2", "audio_input": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+helicone-registry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write": { "unit": "per_M_tokens", "price": "1.25" }, "cache_storage": { "unit": "per_M_tokens_per_hour", "price": "4.5" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "maps": { "unit": "per_request", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "cache_write": "helicone-registry", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch AND Context >200K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } }, { "label": "Priority AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "litellm", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+helicone-registry+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "cache_write": "helicone-registry", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3125" }, "message": "cache_read from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.31" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "helicone-registry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "helicone-registry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch AND Context >200K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "3.6", "completion": "2.7", "cache_read": "3.6" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.84" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "0.2", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "25" } } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "asia-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "europe-west8", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "europe-west9", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "northamerica-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "google/gemini-2.5-pro", "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "intro": "Google's proven reasoning model for coding, math, and multimodal analysis", "released_at": "2025-06-17", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "family": "gemini-pro", "reasoning_config": { "mandatory": true, "budget_min": 128 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "stream": true }, "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 2000, "tpm": 800000 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "deprecated": true, "benchmarks": { "intelligence_index": 25.9, "coding_index": 33.3, "agentic_index": 7.2 }, "aliases": [ "coding/gemini-2.5-pro", "deepinfra/google/gemini-2.5-pro", "gemini-2-5-pro", "gemini/gemini-2.5-pro", "google/gemini-2.5-pro", "vertex/gemini-2.5-pro" ], "intro_i18n": { "zh-CN": "Gemini 2.5 Pro 是 Google 的旗舰推理模型，支持长上下文，适用于复杂任务。", "zh-TW": "Gemini 2.5 Pro 是 Google 的旗艦推理模型，支援長上下文，適用於處理複雜任務。", "ja-JP": "Gemini 2.5 Pro は、Google による最も高度な推論モデルで、コード、数学、STEM 問題に対する推論や、大規模なデータセット、コードベース、文書の分析に対応します。", "ru-RU": "Gemini 2.5 Pro — флагманская модель рассуждения от Google с поддержкой длинного контекста для сложных задач." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "google/gemini-2.5-pro-gt-128k", "model_name": "gemini-2.5-pro-gt-128k", "display_name": "gemini-2.5-pro-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-pro-gt-128k" } ] }, { "slug": "google/gemini-2.5-pro-lte-128k", "model_name": "gemini-2.5-pro-lte-128k", "display_name": "gemini-2.5-pro-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-pro-lte-128k" } ] }, { "slug": "google/gemini-2.5-pro-preview-03-25", "model_name": "gemini-2.5-pro-preview-03-25", "display_name": "Gemini 2.5 Pro Preview", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "maps": { "unit": "per_request", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.13" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >200K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } }, { "label": "Priority AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch AND Context >200K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "3.6", "completion": "2.7", "cache_read": "3.461538" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.769231" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "2", "completion": "1.5", "cache_read": "1.923077" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-03-25", "max_input_tokens": 1048756, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "family": "gemini", "knowledge_cutoff": "2025-01", "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-2.5-pro-preview-03-25" ], "intro_i18n": { "zh-CN": "Gemini 2.5 Pro Preview 是 Google 最先进的推理模型，能够处理代码、数学、STEM 问题，并分析大规模数据集、代码库和长文档。", "zh-TW": "Gemini 2.5 Pro Preview 是 Google 最先進的推理模型，能處理程式碼、數學與 STEM 問題，並分析大型資料集、程式碼庫與長篇文件。", "ja-JP": "Gemini 2.5 Pro Preview は、Google による最も高度な推論モデルで、コード、数学、STEM 問題に対する推論や、大規模なデータセット、コードベース、文書の分析に対応します。", "ru-RU": "Gemini 2.5 Pro Preview — самая продвинутая модель рассуждения от Google, способная анализировать код, математику и задачи STEM, а также обрабатывать большие наборы данных, кодовые базы и документы с длинным контекстом." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 2.5 Pro Preview" } ] }, { "slug": "google/gemini-2.5-pro-preview-03-25-gt-128k", "model_name": "gemini-2.5-pro-preview-03-25-gt-128k", "display_name": "gemini-2.5-pro-preview-03-25-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "15" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-pro-preview-03-25-gt-128k" } ] }, { "slug": "google/gemini-2.5-pro-preview-03-25-lte-128k", "model_name": "gemini-2.5-pro-preview-03-25-lte-128k", "display_name": "gemini-2.5-pro-preview-03-25-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-pro-preview-03-25-lte-128k" } ] }, { "slug": "google/gemini-2.5-pro-preview-05-06", "model_name": "gemini-2.5-pro-preview-05-06", "display_name": "Gemini 2.5 Pro Preview 05-06", "vendor": "google", "pricing": [ { "provider": "google-vertex", "provider_name": "Google Vertex AI", "official": true, "source": "portkey+llmdb", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "enterprise_web_search": { "unit": "per_request", "price": "0.045" }, "maps": { "unit": "per_request", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.13" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >200K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } }, { "label": "Priority AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "portkey", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.13" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.31" }, "message": "cache_read from llmdb conflicts with portkey; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch AND Context >200K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "3.6", "completion": "2.7", "cache_read": "3.461538" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.769231" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "2", "completion": "1.5", "cache_read": "1.923077" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "stream": true, "structured_output": true, "pdf_input": true, "audio_input": true, "video_input": true }, "released_at": "2025-05-06", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "model_type": "deep_thinking", "family": "gemini-pro", "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "reasoning_config": { "mandatory": true, "budget_min": 128 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-2.5-pro-preview-05-06" ], "intro_i18n": { "zh-CN": "Gemini 2.5 Pro Preview 是 Google 最先进的推理模型，能够处理代码、数学、STEM 问题，并分析大规模数据集、代码库和长文档。", "zh-TW": "Gemini 2.5 Pro Preview 是 Google 最先進的推理模型，能處理程式碼、數學與 STEM 問題，並分析大型資料集、程式碼庫與長篇文件。", "ja-JP": "Gemini 2.5 Pro Preview は、Google による最も高度な推論モデルで、コード、数学、STEM 問題に対する推論や、大規模なデータセット、コードベース、文書の分析に対応します。", "ru-RU": "Gemini 2.5 Pro Preview — самая продвинутая модель рассуждения от Google, способная анализировать код, математику и задачи STEM, а также обрабатывать большие наборы данных, кодовые базы и документы с длинным контекстом." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 2.5 Pro Preview 05-06" } ] }, { "slug": "google/gemini-2.5-pro-preview-05-06-gt-128k", "model_name": "gemini-2.5-pro-preview-05-06-gt-128k", "display_name": "gemini-2.5-pro-preview-05-06-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "15" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-pro-preview-05-06-gt-128k" } ] }, { "slug": "google/gemini-2.5-pro-preview-05-06-lte-128k", "model_name": "gemini-2.5-pro-preview-05-06-lte-128k", "display_name": "gemini-2.5-pro-preview-05-06-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-pro-preview-05-06-lte-128k" } ] }, { "slug": "google/gemini-2.5-pro-preview-06-05", "model_name": "gemini-2.5-pro-preview-06-05", "display_name": "Gemini 2.5 Pro Preview 06-05", "vendor": "google", "pricing": [ { "provider": "google-vertex", "provider_name": "Google Vertex AI", "official": true, "source": "llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.31" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb", "cache_read": "llmdb" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-06-05", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "model_type": "deep_thinking", "family": "gemini-pro", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "stream": true, "structured_output": true, "pdf_input": true, "audio_input": true, "video_input": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-2.5-pro-preview-06-05" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 2.5 Pro Preview 06-05" } ] }, { "slug": "google/gemini-2.5-pro-preview-tts", "model_name": "gemini-2.5-pro-preview-tts", "display_name": "Gemini 2.5 Pro Preview TTS", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "20" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "audio_input": { "unit": "per_M_tokens", "price": "0.7" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm", "audio_output": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.25" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "20" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "litellm", "threshold": 200000, "inclusive": false, "message": "tier threshold 200000 exceeds model context window 8192; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "invalid_source_tier", "source": "litellm", "message": "tier threshold 200000 exceeds model context window 8192." } ] }, { "provider": "google-vertex", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "audio_input": { "unit": "per_M_tokens", "price": "0.7" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "audio_input": "litellm", "web_search": "litellm" }, "discarded_conflicts": [ { "kind": "tier_schedule", "source": "litellm", "threshold": 200000, "inclusive": false, "message": "tier threshold 200000 exceeds model context window 8192; it was discarded." } ], "verification_status": "conflicting" }, "warnings": [ { "code": "invalid_source_tier", "source": "litellm", "message": "tier threshold 200000 exceeds model context window 8192." } ] } ], "intro": "Speech generation model for controllable voice, narration, and audio delivery", "released_at": "2025-05-01", "knowledge_cutoff": "2025-01", "max_input_tokens": 8192, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "family": "gemini-flash", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_output": true, "structured_output": true, "web_search": true, "parallel_function_calling": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-pro-preview", "model_type": "speech_synthesis", "rate_limits": { "rpm": 10000, "tpm": 10000000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-2.5-pro-preview-tts" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "reasoning: false→true" } ] }, { "slug": "google/gemini-2.5-pro-preview-tts-gt-128k", "model_name": "gemini-2.5-pro-preview-tts-gt-128k", "display_name": "gemini-2.5-pro-preview-tts-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "speech_synthesis", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-pro-preview-tts-gt-128k" } ] }, { "slug": "google/gemini-2.5-pro-preview-tts-lte-128k", "model_name": "gemini-2.5-pro-preview-tts-lte-128k", "display_name": "gemini-2.5-pro-preview-tts-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "speech_synthesis", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-2.5-pro-preview-tts-lte-128k" } ] }, { "slug": "google/gemini-3-1-flash-tts", "model_name": "gemini-3-1-flash-tts", "display_name": "Gemini 3.1 Flash TTS", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" }, "provider_model_id": "gemini-3.1-flash-tts" } ], "capabilities": { "prompt_caching": true, "audio_output": true }, "released_at": "2026-04-13", "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemini-3.1-flash-tts" ], "model_type": "speech_synthesis", "price_history": [ { "date": "2026-08-10", "kind": "listed", "note": "Gemini 3.1 Flash TTS" } ] }, { "slug": "google/gemini-3-1-pro", "model_name": "gemini-3-1-pro", "display_name": "Gemini 3.1 Pro", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google Cloud", "official": true, "source": "computeprices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "computeprices", "completion": "computeprices", "cache_read": "computeprices" }, "tracks": [ { "label": "Batch", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } }, { "label": "Base pricing", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices", "cache_read": "computeprices" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "family": "Gemini", "capabilities": { "vision": true, "audio_input": true, "video_input": true, "function_calling": true, "reasoning": true, "structured_output": true, "pdf_input": true, "prompt_caching": true, "stream": true }, "intro": "Reasoning-first Gemini preview for agentic coding and complex problem solving", "released_at": "2026-02-19", "knowledge_cutoff": "2025-01", "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "anthropic/pioneer/gemini-3.1-pro", "gemini-3.1-pro", "google/gemini-3.1-pro" ], "intro_i18n": { "zh-CN": "Google 的 Gemini 3.1 Pro —— 高端多模态模型，具备 100 万上下文窗口。", "zh-TW": "Google Gemini 3.1 Pro —— 旗艦多模態模型，具備 100 萬上下文。", "ja-JP": "Gemini 3.1 Pro by Google — 1Mコンテキストウィンドウを備えたプレミアムマルチモーダルモデル。", "ru-RU": "Gemini 3.1 Pro от Google — премиальная мультимодальная модель с контекстом 1M." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 3.1 Pro" } ] }, { "slug": "google/gemini-3-flash", "model_name": "gemini-3-flash", "display_name": "Gemini 3 Flash", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google Cloud", "official": true, "source": "computeprices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" } }, "provenance": { "base_charges": { "prompt": "computeprices", "completion": "computeprices", "cache_read": "computeprices" }, "tracks": [ { "label": "Batch", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } }, { "label": "Base pricing", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices", "cache_read": "computeprices" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "knowledge_cutoff": "2025-06", "max_input_tokens": 1000000, "family": "Gemini", "capabilities": { "vision": true, "audio_input": true, "video_input": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "intro": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs", "released_at": "2025-12-17", "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "anthropic/pioneer/gemini-3-flash", "google/gemini-3-flash" ], "intro_i18n": { "zh-CN": "Google 的 Gemini 3 Flash —— 超高速模型，支持多模态输入。", "zh-TW": "Google Gemini 3 Flash —— 超高速模型，支援多模態輸入。", "ja-JP": "Gemini 3 Flash by Google — 超高速モデルでマルチモーダル入力をサポートします。", "ru-RU": "Gemini 3 Flash от Google — ультрабыстрая модель с поддержкой мультимодальных входов." }, "price_history": [ { "date": "2026-07-25", "kind": "limit", "old": "65535", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "65000", "new": "65535", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Gemini 3 Flash" } ] }, { "slug": "google/gemini-3-flash-preview", "model_name": "gemini-3-flash-preview", "display_name": "Gemini 3 Flash Preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "3" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.1" }, "image_input": { "unit": "per_M_tokens", "price": "0.5" }, "video_input": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "audio_cache_read": "helicone-registry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+helicone-registry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "audio_cache_read": "helicone-registry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "14" }, "discarded_charge": { "unit": "per_k_calls", "price": "35" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+helicone-registry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "3" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.1" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" }, "cache_write": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "web_search": "litellm", "internal_reasoning": "litellm", "audio_cache_read": "helicone-registry", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+helicone-registry+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "web_search": "litellm", "internal_reasoning": "litellm", "audio_cache_read": "helicone-registry", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3-flash-preview", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs", "released_at": "2025-12-17", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 2000, "tpm": 800000 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "reasoning_config": { "mandatory": false }, "aliases": [ "gemini/gemini-3-flash-preview", "google/gemini-3-flash-preview", "pa/gemini-3-flash-preview", "vertex/gemini-3-flash-preview" ], "intro_i18n": { "zh-CN": "Gemini 3 Flash 是一款以速度为核心的智能模型，融合前沿智能与卓越的搜索能力。", "zh-TW": "Gemini 3 Flash 是一款以速度為核心的智慧模型，結合尖端智能與卓越的搜尋基礎能力。", "ja-JP": "Gemini 3 Flash は、最先端の知能と優れた検索基盤を融合し、スピードに特化した最もスマートなモデルです。", "ru-RU": "Gemini 3 Flash — самая быстрая и интеллектуальная модель, сочетающая передовые ИИ-возможности с точной привязкой к поисковым данным." }, "price_history": [ { "date": "2026-07-15", "kind": "capability", "note": "open_weights: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-3-flash-preview-gt-128k", "model_name": "gemini-3-flash-preview-gt-128k", "display_name": "gemini-3-flash-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "cache_write": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3-flash-preview-gt-128k" } ] }, { "slug": "google/gemini-3-flash-preview-lte-128k", "model_name": "gemini-3-flash-preview-lte-128k", "display_name": "gemini-3-flash-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "cache_write": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3-flash-preview-lte-128k" } ] }, { "slug": "google/gemini-3-pro", "model_name": "gemini-3-pro", "display_name": "Gemini 3 Pro", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google Cloud", "official": true, "source": "computeprices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "computeprices", "completion": "computeprices", "cache_read": "computeprices" }, "tracks": [ { "label": "Batch", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices" } }, { "label": "Base pricing", "source": "computeprices", "charge_sources": { "prompt": "computeprices", "completion": "computeprices", "cache_read": "computeprices" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "knowledge_cutoff": "2025-06", "max_input_tokens": 1000000, "family": "Gemini", "capabilities": { "vision": true, "audio_input": true, "video_input": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "stream": true }, "intro": "Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts", "released_at": "2025-11-18", "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "deprecated": true, "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-3-pro" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 3 Pro" } ] }, { "slug": "google/gemini-3-pro-image", "model_name": "gemini-3-pro-image", "display_name": "Nano Banana Pro", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "120" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_image", "price": "0.134" }, "image_input": { "unit": "per_image", "price": "0.0011" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "120" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "120" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "120" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from ai-model-directory conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.05" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "120" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_image", "price": "0.134" }, "image_input": { "unit": "per_image", "price": "0.0011" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm", "google_search_grounding": "portkey", "maps": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm", "google_search_grounding": "portkey", "maps": "portkey", "cache_read": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "120" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "120" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.134" }, "discarded_charge": { "unit": "per_M_tokens", "price": "120" }, "message": "image_output from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "120" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.05", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.05" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "5" } } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00112" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3-pro-image", "region": "global" } ], "intro": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits", "released_at": "2026-05-28", "knowledge_cutoff": "2025-01", "max_input_tokens": 65536, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "family": "gemini-pro", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image", "model_type": "image_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 1000, "tpm": 4000000 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "reasoning_config": { "mandatory": true }, "aliases": [ "google/gemini-3-pro-image", "vertex/gemini-3-pro-image" ], "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "65536", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "131072", "new": "65536", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "131072", "new": "65536", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "65536", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "131072", "new": "65536", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "65536", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "131072", "new": "65536", "note": "max_input_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "65536", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-07-25", "kind": "limit", "old": "65536", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-07-25", "kind": "price", "provider": "google", "charge": "completion", "old": "12", "new": "120" }, { "date": "2026-07-12", "kind": "price", "provider": "google-vertex", "charge": "completion", "old": "12", "new": "120" }, { "date": "2026-07-04", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" } ] }, { "slug": "google/gemini-3-pro-image-gt-128k", "model_name": "gemini-3-pro-image-gt-128k", "display_name": "gemini-3-pro-image-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_M_tokens", "price": "120" }, "image_input": { "unit": "per_image", "price": "0.000011" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "web_search": "portkey", "image_output": "portkey", "image_input": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "image_input": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3-pro-image-gt-128k" } ] }, { "slug": "google/gemini-3-pro-image-lte-128k", "model_name": "gemini-3-pro-image-lte-128k", "display_name": "gemini-3-pro-image-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_M_tokens", "price": "120" }, "image_input": { "unit": "per_image", "price": "0.000011" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "web_search": "portkey", "image_output": "portkey", "image_input": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "image_input": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3-pro-image-lte-128k" } ] }, { "slug": "google/gemini-3-pro-image-preview", "model_name": "gemini-3-pro-image-preview", "display_name": "Nano Banana Pro", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "120" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_image", "price": "0.134" }, "image_input": { "unit": "per_image", "price": "0.0011" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "120" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "120" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "120" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from helicone-registry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.0011" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "image_input from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.134" }, "discarded_charge": { "unit": "per_M_tokens", "price": "120" }, "message": "image_output from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "14" }, "discarded_charge": { "unit": "per_k_calls", "price": "35" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "120" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.134" }, "discarded_charge": { "unit": "per_M_tokens", "price": "120" }, "message": "image_output from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.0011" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "image_input from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "120" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "helicone-registry", "threshold": 200000, "inclusive": true, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.05" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "invalid_source_tier", "source": "helicone-registry", "message": "tier threshold 200000 exceeds model context window 131072." } ] }, { "provider": "google-vertex", "official": true, "source": "litellm+helicone-registry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_image", "price": "0.134" }, "image_input": { "unit": "per_image", "price": "0.0011" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm", "google_search_grounding": "portkey", "maps": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm", "google_search_grounding": "portkey", "maps": "portkey", "cache_read": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.0011" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "image_input from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.134" }, "discarded_charge": { "unit": "per_M_tokens", "price": "120" }, "message": "image_output from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.134" }, "discarded_charge": { "unit": "per_M_tokens", "price": "120" }, "message": "image_output from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "helicone-registry", "threshold": 200000, "inclusive": true, "message": "tier threshold 200000 exceeds model context window 131072; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "invalid_source_tier", "source": "helicone-registry", "message": "tier threshold 200000 exceeds model context window 131072." } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "5" } } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.00112" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3-pro-image-preview", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Nano Banana Pro for higher-fidelity image generation and design-heavy edits", "released_at": "2025-11-20", "knowledge_cutoff": "2025-01", "max_input_tokens": 131072, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "family": "gemini-pro", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing", "deprecated": true, "model_type": "image_generation", "deprecation_date": "2026-06-25", "rate_limits": { "rpm": 1000, "tpm": 4000000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "parameters": { "supported": [ "max_tokens", "response_format", "seed", "stop", "temperature", "top_p" ] }, "reasoning_config": { "mandatory": true }, "aliases": [ "google/gemini-3-pro-image-preview" ], "intro_i18n": { "zh-CN": "Gemini 3 Pro Image（Nano Banana Pro）是 Google 的图像生成模型，同时支持多模态对话。", "zh-TW": "Gemini 3 Pro Image (Nano Banana Pro) 是 Google 的影像生成模型，亦支持多模態對話。", "ja-JP": "Gemini 3 Pro Image（Nano Banana Pro）は、Googleの画像生成モデルで、マルチモーダル対話もサポートします。", "ru-RU": "Gemini 3 Pro Image (Nano Banana Pro) — это модель генерации изображений от Google, которая также поддерживает мультимодальный диалог." }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-07", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" } ] }, { "slug": "google/gemini-3-pro-image-preview-gt-128k", "model_name": "gemini-3-pro-image-preview-gt-128k", "display_name": "gemini-3-pro-image-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_M_tokens", "price": "120" }, "image_input": { "unit": "per_image", "price": "0.000011" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "web_search": "portkey", "image_output": "portkey", "image_input": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "image_input": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3-pro-image-preview-gt-128k" } ] }, { "slug": "google/gemini-3-pro-image-preview-lte-128k", "model_name": "gemini-3-pro-image-preview-lte-128k", "display_name": "gemini-3-pro-image-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_M_tokens", "price": "120" }, "image_input": { "unit": "per_image", "price": "0.000011" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "web_search": "portkey", "image_output": "portkey", "image_input": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "image_output": "portkey", "image_input": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3-pro-image-preview-lte-128k" } ] }, { "slug": "google/gemini-3-pro-image-preview:image", "model_name": "gemini-3-pro-image-preview:image", "display_name": "Nano Banana Pro", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_M_tokens", "price": "120" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-11-18", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Gemini 3 Pro Image（Nano Banana Pro）是 Google 的图像生成模型，同时支持多模态聊天。", "zh-TW": "Gemini 3 Pro Image（Nano Banana Pro）是 Google 的圖像生成模型，並支持多模態聊天。", "ja-JP": "Gemini 3 Pro Image（Nano Banana Pro）は、Googleの画像生成モデルで、マルチモーダルチャットもサポートしています。", "ru-RU": "Gemini 3 Pro Image (Nano Banana Pro) — модель генерации изображений от Google, также поддерживающая мультимодальный чат." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Nano Banana Pro" } ] }, { "slug": "google/gemini-3-pro-preview", "model_name": "gemini-3-pro-preview", "display_name": "gemini-3-pro-preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+pydantic-prices+truefoundry+helicone-registry+llmdb+pricetoken+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "cache_storage": { "unit": "per_M_tokens_per_hour", "price": "4.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_storage": "helicone-registry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >200K", "source": "litellm", "charge_sources": { "cache_read": "litellm", "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm+truefoundry+helicone-registry", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_storage": "helicone-registry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "14" }, "discarded_charge": { "unit": "per_k_calls", "price": "35" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "pydantic-prices", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "pydantic-prices introduced a ≥200000 tier outside the litellm schedule; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the litellm schedule; it was discarded." }, { "kind": "tier_schedule", "source": "helicone-registry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "helicone-registry introduced a ≥200000 tier outside the litellm schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "provider_name": "Google Vertex AI", "official": true, "source": "litellm+helicone-registry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "cache_storage": { "unit": "per_M_tokens_per_hour", "price": "4.5" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "enterprise_web_search": { "unit": "per_request", "price": "0.014" }, "image_output": { "unit": "per_M_tokens", "price": "120" }, "maps": { "unit": "per_request", "price": "0.014" }, "cache_write": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "litellm", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >200K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey" } }, { "label": "Priority AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >200K", "source": "litellm", "charge_sources": { "cache_read": "litellm", "cache_write": "litellm", "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey" } }, { "label": "Base pricing", "source": "litellm+helicone-registry+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "litellm", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "image_output": "portkey", "maps": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "helicone-registry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "helicone-registry introduced a ≥200000 tier outside the litellm schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch AND Context >200K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "0.5", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "0.5", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "1", "maps": "1", "prompt": "3.6", "completion": "2.7", "cache_read": "3.6" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "0.5", "maps": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "0.5", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "cache_read": "2", "cache_write": "1.25", "prompt": "2", "completion": "1.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "image_output": "1", "maps": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-east2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-northeast3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "asia-southeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "australia-southeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west6", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west8", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "europe-west9", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "me-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "me-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "me-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "northamerica-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "southamerica-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "max_input_tokens": 1048576, "max_output_tokens": 65535, "deprecated": true, "model_type": "image_generation", "deprecation_date": "2026-03-26", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true, "image_output": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 2000, "tpm": 800000 }, "intro": "The best model in the world for multimodal understanding, and our most powerful agentic and vibe-coding model yet.", "modalities": { "input": [ "audio", "doc", "image", "pdf" ], "output": [] }, "knowledge_cutoff": "2025-11", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "released_at": "2025-11-18", "family": "gemini-pro", "status": "deprecated", "aliases": [ "google/gemini-3-pro-preview", "pa/gemini-3-pro-preview", "vertex/gemini-3-pro-preview" ], "intro_i18n": { "zh-CN": "Gemini 3 Pro 是 Google 最强大的智能体与编程模型，在最先进推理基础上提供更丰富的视觉效果与更深入的交互体验。", "zh-TW": "Gemini 3 Pro 是 Google 最強大的智能代理與情境編碼模型，具備頂尖推理能力、豐富視覺表現與深度互動。", "ja-JP": "Gemini 3 Pro は、Google による最も強力なエージェントおよびバイブコーディングモデルで、最先端の推論に加え、より豊かなビジュアルと深い対話を実現します。", "ru-RU": "Gemini 3 Pro — самая мощная агентная модель от Google с поддержкой визуализации и глубокой интерактивности, основанная на передовых возможностях рассуждения." }, "price_history": [ { "date": "2026-08-10", "kind": "limit", "old": "65536", "new": "65535", "note": "max_output_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-3-pro-preview-02-05", "model_name": "gemini-3-pro-preview-02-05", "display_name": "gemini-3-pro-preview-02-05", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "4.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >200K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Priority AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch AND Context >200K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "3.6", "completion": "2.7", "cache_read": "0.16" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "0.08" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "2", "completion": "1.5", "cache_read": "0.088889" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3-pro-preview-02-05" } ] }, { "slug": "google/gemini-3-pro-preview-02-05-gt-128k", "model_name": "gemini-3-pro-preview-02-05-gt-128k", "display_name": "gemini-3-pro-preview-02-05-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "18" }, "cache_read": { "unit": "per_M_tokens", "price": "4.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3-pro-preview-02-05-gt-128k" } ] }, { "slug": "google/gemini-3-pro-preview-02-05-lte-128k", "model_name": "gemini-3-pro-preview-02-05-lte-128k", "display_name": "gemini-3-pro-preview-02-05-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "4.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3-pro-preview-02-05-lte-128k" } ] }, { "slug": "google/gemini-3-pro-preview-gt-128k", "model_name": "gemini-3-pro-preview-gt-128k", "display_name": "gemini-3-pro-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "18" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3-pro-preview-gt-128k" } ] }, { "slug": "google/gemini-3-pro-preview-lte-128k", "model_name": "gemini-3-pro-preview-lte-128k", "display_name": "gemini-3-pro-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "cache_write": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3-pro-preview-lte-128k" } ] }, { "slug": "google/gemini-3.1-flash-image", "model_name": "gemini-3.1-flash-image", "display_name": "Nano Banana 2", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry+computeprices+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "60" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_image", "price": "0.045" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "image_input": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "cache_read": "computeprices", "image_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "computeprices" } }, { "label": "Base pricing", "source": "models-dev+litellm+computeprices+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "cache_read": "computeprices", "image_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.25" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "computeprices", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from computeprices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.045" }, "discarded_charge": { "unit": "per_M_tokens", "price": "60" }, "message": "image_output from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from ai-model-directory conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gemini-3-1-flash-image", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.025", "cache_read": "0.125" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "60" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_image", "price": "0.0672" }, "image_input": { "unit": "per_image", "price": "0.00056" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm", "google_search_grounding": "portkey", "maps": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.0672" }, "discarded_charge": { "unit": "per_M_tokens", "price": "60" }, "message": "image_output from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.025", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.025" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.1-flash-image", "region": "global", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2026-05-28", "knowledge_cutoff": "2025-01", "max_input_tokens": 131072, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text", "image" ] }, "family": "gemini-flash", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true }, "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "model_type": "image_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 1000, "tpm": 4000000 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "structured_outputs", "temperature", "top_p" ] }, "reasoning_config": { "mandatory": false }, "aliases": [ "gemini-3-1-flash-image", "google/gemini-3.1-flash-image", "vertex/gemini-3.1-flash-image" ], "intro_i18n": { "zh-CN": "Gemini 3.1 Flash Image（Nano Banana 2）是 Google 最快的原生图像生成模型，支持思考、对话式图像生成和编辑。", "zh-TW": "Gemini 3.1 Flash Image（Nano Banana 2）是 Google 最快的原生圖像生成模型，支持思維能力、對話式圖像生成和編輯。", "ja-JP": "Gemini 3.1 Flash Image（Nano Banana 2）は、思考サポート、会話型画像生成および編集機能を備えたGoogleの最速ネイティブ画像生成モデルです。", "ru-RU": "Gemini 3.1 Flash Image (Nano Banana 2) — самая быстрая модель Google для генерации изображений с поддержкой мышления, создания и редактирования изображений в диалоговом режиме." }, "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "131072", "new": "65536", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "32768", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "65536", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "65536", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "65536", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "65536", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "131072", "new": "65536", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "32768", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "65536", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "65536", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "131072", "new": "65536", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "32768", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "65536", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "65536", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "131072", "new": "65536", "note": "max_input_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "32768", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-07-25", "kind": "limit", "old": "131072", "new": "65536", "note": "max_input_tokens" }, { "date": "2026-07-25", "kind": "limit", "old": "32768", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-07-25", "kind": "price", "provider": "google", "charge": "completion", "old": "1.5", "new": "60" }, { "date": "2026-07-25", "kind": "price", "provider": "google", "charge": "prompt", "old": "0.25", "new": "0.5" } ] }, { "slug": "google/gemini-3.1-flash-image-gt-128k", "model_name": "gemini-3.1-flash-image-gt-128k", "display_name": "gemini-3.1-flash-image-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_M_tokens", "price": "60" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-flash-image-gt-128k" } ] }, { "slug": "google/gemini-3.1-flash-image-lte-128k", "model_name": "gemini-3.1-flash-image-lte-128k", "display_name": "gemini-3.1-flash-image-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_M_tokens", "price": "60" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-flash-image-lte-128k" } ] }, { "slug": "google/gemini-3.1-flash-image-preview", "model_name": "gemini-3.1-flash-image-preview", "display_name": "Nano Banana 2", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "60" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_image", "price": "0.045" }, "image_input": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "image_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "image_output": "litellm", "image_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.25" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.045" }, "discarded_charge": { "unit": "per_image", "price": "0.067" }, "message": "image_output from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "14" }, "discarded_charge": { "unit": "per_k_calls", "price": "35" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.25" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.045" }, "discarded_charge": { "unit": "per_M_tokens", "price": "60" }, "message": "image_output from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.025" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_image", "price": "0.0672" }, "image_input": { "unit": "per_image", "price": "0.00056" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "web_search": "litellm", "image_output": "litellm", "image_input": "litellm", "google_search_grounding": "portkey", "maps": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.0672" }, "discarded_charge": { "unit": "per_M_tokens", "price": "60" }, "message": "image_output from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.1-flash-image-preview", "region": "global", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2026-02-26", "knowledge_cutoff": "2025-01", "max_input_tokens": 65536, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text", "image" ] }, "family": "gemini-flash", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "stream": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image-preview", "deprecated": true, "model_type": "image_generation", "deprecation_date": "2026-06-25", "rate_limits": { "rpm": 1000, "tpm": 4000000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "structured_outputs", "temperature", "top_p" ] }, "reasoning_config": { "mandatory": false }, "aliases": [ "google/gemini-3.1-flash-image-preview" ], "intro_i18n": { "zh-CN": "Gemini 3.1 Flash Image（Nano Banana 2）是 Google 最快的原生图像生成模型，支持思考、对话式图像生成和编辑。", "zh-TW": "Gemini 3.1 Flash Image (Nano Banana 2) 是 Google 最快的原生影像生成模型，支持思考、對話式影像生成與編輯。", "ja-JP": "Gemini 3.1 Flash Image（Nano Banana 2）は、Googleの最速のネイティブ画像生成モデルで、思考サポート、対話型画像生成および編集を提供します。", "ru-RU": "Gemini 3.1 Flash Image (Nano Banana 2) — это самая быстрая нативная модель генерации изображений от Google с поддержкой мышления, генерации и редактирования изображений в диалоговом режиме." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "google/gemini-3.1-flash-image-preview-gt-128k", "model_name": "gemini-3.1-flash-image-preview-gt-128k", "display_name": "gemini-3.1-flash-image-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_M_tokens", "price": "60" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-flash-image-preview-gt-128k" } ] }, { "slug": "google/gemini-3.1-flash-image-preview-lte-128k", "model_name": "gemini-3.1-flash-image-preview-lte-128k", "display_name": "gemini-3.1-flash-image-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_M_tokens", "price": "60" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "image_output": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-flash-image-preview-lte-128k" } ] }, { "slug": "google/gemini-3.1-flash-image-preview:image", "model_name": "gemini-3.1-flash-image-preview:image", "display_name": "Nano Banana 2", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_M_tokens", "price": "60" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-02-26", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Gemini 3.1 Flash Image（Nano Banana 2）是 Google 最快速的原生图像生成模型，支持思维能力、对话式图像生成和编辑功能。", "zh-TW": "Gemini 3.1 Flash Image（Nano Banana 2）是 Google 最快速的原生圖像生成模型，支持思維能力、對話式圖像生成和編輯。", "ja-JP": "Gemini 3.1 Flash Image（Nano Banana 2）は、Googleの最速のネイティブ画像生成モデルで、思考サポート、会話型画像生成、編集を可能にします。", "ru-RU": "Gemini 3.1 Flash Image (Nano Banana 2) — самая быстрая модель генерации изображений от Google с поддержкой размышлений, генерации и редактирования изображений в рамках диалога." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Nano Banana 2" } ] }, { "slug": "google/gemini-3.1-flash-image:image", "model_name": "gemini-3.1-flash-image:image", "display_name": "Nano Banana 2", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_M_tokens", "price": "60" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "image_input": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank", "prompt": "lobehub-modelbank", "image_input": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-05-28", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Gemini 3.1 Flash Image（Nano Banana 2）是 Google 最快速的原生图像生成模型，支持思维能力、对话式图像生成和编辑功能。", "zh-TW": "Gemini 3.1 Flash Image（Nano Banana 2）是 Google 最快的原生圖像生成模型，支持思維能力、對話式圖像生成和編輯。", "ja-JP": "Gemini 3.1 Flash Image（Nano Banana 2）は、思考サポート、会話型画像生成および編集機能を備えたGoogleの最速ネイティブ画像生成モデルです。", "ru-RU": "Gemini 3.1 Flash Image (Nano Banana 2) — самая быстрая модель Google для генерации изображений с поддержкой мышления, создания и редактирования изображений в диалоговом режиме." }, "price_history": [ { "date": "2026-08-05", "kind": "listed", "note": "Nano Banana 2" } ] }, { "slug": "google/gemini-3.1-flash-lite", "model_name": "gemini-3.1-flash-lite", "display_name": "Gemini 3.1 Flash Lite", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "audio_input": { "unit": "per_M_tokens", "price": "0.5" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.05" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "image_input": { "unit": "per_M_tokens", "price": "0.25" }, "video_input": { "unit": "per_M_tokens", "price": "0.25" }, "cache_write": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "audio_cache_read": "lobehub-modelbank", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank", "cache_write": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "computeprices" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "audio_cache_read": "lobehub-modelbank", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank", "cache_write": "lobehub-modelbank" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gemini-3-1-flash-lite", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "audio_input": { "unit": "per_M_tokens", "price": "0.5" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" }, "cache_write": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1", "cache_read": "0.55" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1.98", "completion": "1.98", "cache_read": "1.98" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.55", "completion": "0.55", "cache_read": "0.55" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.055" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0275" }, "audio_input": { "unit": "per_M_tokens", "price": "0.55" }, "prompt": { "unit": "per_M_tokens", "price": "0.275" }, "completion": { "unit": "per_M_tokens", "price": "1.65" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.1-flash-lite", "region": "eu", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.05" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "audio_input": { "unit": "per_M_tokens", "price": "0.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "google/gemini-3.1-flash-lite", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.055" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0275" }, "audio_input": { "unit": "per_M_tokens", "price": "0.55" }, "prompt": { "unit": "per_M_tokens", "price": "0.275" }, "completion": { "unit": "per_M_tokens", "price": "1.65" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.1-flash-lite", "region": "us", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Low-latency Gemini model for high-volume multimodal and agent workloads", "released_at": "2026-05-07", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash-lite", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "deprecation_date": "2027-05-07", "rate_limits": { "rpm": 15, "tpm": 250000 }, "parameters": { "unsupported": [ "temperature" ] }, "reasoning_config": { "mandatory": false }, "aliases": [ "gemini-3-1-flash-lite", "google/gemini-3.1-flash-lite", "vertex/gemini-3.1-flash-lite" ], "intro_i18n": { "zh-CN": "Gemini 3.1 Flash-Lite 是谷歌最具成本效益的多模态模型，优化用于高容量代理任务、翻译和数据处理。", "zh-TW": "Gemini 3.1 Flash-Lite 是 Google 最具成本效益的多模態模型，專為高容量代理任務、翻譯和數據處理而優化。", "ja-JP": "Gemini 3.1 Flash-LiteはGoogleの最もコスト効率の高いマルチモーダルモデルで、大量のエージェントタスク、翻訳、データ処理に最適化されています。", "ru-RU": "Gemini 3.1 Flash-Lite — самая экономичная мультимодальная модель от Google, оптимизированная для задач с высоким объемом, перевода и обработки данных." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.02", "new": "0.01" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.75", "new": "1.18" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.14", "new": "0.2" }, { "date": "2026-08-11", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.01", "new": "0.02" }, { "date": "2026-08-11", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.95", "new": "0.75" }, { "date": "2026-08-11", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.16", "new": "0.14" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.02", "new": "0.01" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.75", "new": "0.95" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.14", "new": "0.16" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "cache_read", "old": "0.022", "new": "0.025" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "completion", "old": "1.464", "new": "1.631" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "prompt", "old": "0.244", "new": "0.272" }, { "date": "2026-08-03", "kind": "price", "provider": "kilo", "charge": "cache_write", "old": "0.08333", "new": "0.083333" }, { "date": "2026-08-01", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.9", "new": "0.75" }, { "date": "2026-08-01", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.15", "new": "0.14" }, { "date": "2026-07-31", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "1.1", "new": "0.9" }, { "date": "2026-07-31", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.2", "new": "0.15" }, { "date": "2026-07-30", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.02", "new": "0.01" }, { "date": "2026-07-30", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.75", "new": "1.1" }, { "date": "2026-07-30", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.14", "new": "0.2" } ] }, { "slug": "google/gemini-3.1-flash-lite-gt-128k", "model_name": "gemini-3.1-flash-lite-gt-128k", "display_name": "gemini-3.1-flash-lite-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-flash-lite-gt-128k" } ] }, { "slug": "google/gemini-3.1-flash-lite-image", "model_name": "gemini-3.1-flash-lite-image", "display_name": "Nano Banana 2 Lite", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+truefoundry+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "image_output": { "unit": "per_M_tokens", "price": "30" }, "image_input": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "image_output": "lobehub-modelbank", "image_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "image_output": "lobehub-modelbank", "image_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from ai-model-directory conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.025" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_M_tokens", "price": "30" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "image_output": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "0.5", "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.1-flash-lite-image", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing", "released_at": "2026-06-30", "knowledge_cutoff": "2025-01", "max_input_tokens": 65536, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "family": "gemini-flash-lite", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true }, "model_type": "image_generation", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "temperature", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-3.1-flash-lite-image" ], "intro_i18n": { "zh-CN": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 是 Google 最快且最具成本效益的图像生成模型，专为高容量生成和编辑而设计。", "zh-TW": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 是 Google 最快且最具成本效益的圖像生成模型，專為高容量生成和編輯而設計。", "ja-JP": "Gemini 3.1 Flash Lite Image（Nano Banana 2 Lite）は、Googleが開発した最速かつ最もコスト効率の高い画像生成モデルで、大量生成と編集に特化しています。", "ru-RU": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) — это самая быстрая и экономичная модель генерации изображений от Google, созданная для массовой генерации и редактирования." }, "price_history": [ { "date": "2026-07-25", "kind": "limit", "old": "4096", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-07-25", "kind": "price", "provider": "google", "charge": "completion", "old": "1.5", "new": "30" }, { "date": "2026-07-09", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Nano Banana 2 Lite" } ] }, { "slug": "google/gemini-3.1-flash-lite-image-gt-128k", "model_name": "gemini-3.1-flash-lite-image-gt-128k", "display_name": "gemini-3.1-flash-lite-image-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_M_tokens", "price": "30" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-flash-lite-image-gt-128k" } ] }, { "slug": "google/gemini-3.1-flash-lite-image-lte-128k", "model_name": "gemini-3.1-flash-lite-image-lte-128k", "display_name": "gemini-3.1-flash-lite-image-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_M_tokens", "price": "30" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-flash-lite-image-lte-128k" } ] }, { "slug": "google/gemini-3.1-flash-lite-image:image", "model_name": "gemini-3.1-flash-lite-image:image", "display_name": "Nano Banana 2 Lite", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_M_tokens", "price": "30" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "image_input": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank", "prompt": "lobehub-modelbank", "image_input": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-06-30", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 是 Google 最快且最具成本效益的图像生成模型，专为高容量生成和编辑而设计。", "zh-TW": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) 是 Google 最快且最具成本效益的圖像生成模型，專為高容量生成和編輯而設計。", "ja-JP": "Gemini 3.1 Flash Lite Image（Nano Banana 2 Lite）は、Googleが開発した最速かつ最もコスト効率の高い画像生成モデルで、大量生成と編集に特化しています。", "ru-RU": "Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) — это самая быстрая и экономичная модель генерации изображений от Google, созданная для массовой генерации и редактирования." }, "price_history": [ { "date": "2026-07-10", "kind": "listed", "note": "Nano Banana 2 Lite" } ] }, { "slug": "google/gemini-3.1-flash-lite-lte-128k", "model_name": "gemini-3.1-flash-lite-lte-128k", "display_name": "gemini-3.1-flash-lite-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-flash-lite-lte-128k" } ] }, { "slug": "google/gemini-3.1-flash-lite-preview", "model_name": "gemini-3.1-flash-lite-preview", "display_name": "Gemini 3.1 Flash Lite Preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry+helicone-registry+llmdb+lobehub-modelbank+pricetoken+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "audio_input": { "unit": "per_M_tokens", "price": "0.5" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.05" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "cache_storage": { "unit": "per_M_tokens_per_hour", "price": "1" }, "image_input": { "unit": "per_M_tokens", "price": "0.25" }, "video_input": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+helicone-registry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "14" }, "discarded_charge": { "unit": "per_k_calls", "price": "35" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.025" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.05" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+helicone-registry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "audio_input": { "unit": "per_M_tokens", "price": "0.5" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "cache_storage": { "unit": "per_M_tokens_per_hour", "price": "1" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" }, "cache_write": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+helicone-registry+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "audio_cache_read": "helicone-registry", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1", "cache_read": "0.55" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1.98", "completion": "1.98", "cache_read": "1.98" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.55", "completion": "0.55", "cache_read": "0.55" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.05" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "audio_input": { "unit": "per_M_tokens", "price": "0.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "google/gemini-3.1-flash-lite-preview", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Low-latency Gemini model for high-volume multimodal and agent workloads", "released_at": "2026-03-03", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "deprecated": true, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash-lite", "status": "deprecated", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/models", "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "deprecation_date": "2026-05-25", "rate_limits": { "rpm": 15, "tpm": 250000 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "benchmarks": { "intelligence_index": 25.6, "coding_index": 34.7, "agentic_index": 6.5 }, "reasoning_config": { "mandatory": false }, "aliases": [ "google/gemini-3.1-flash-lite-preview", "pa/gemini-3.1-flash-lite-preview" ], "intro_i18n": { "zh-CN": "Gemini 3.1 Flash-Lite Preview是谷歌最具成本效益的多模态模型，专为高容量代理任务、翻译和数据处理优化。", "zh-TW": "Gemini 3.1 Flash-Lite Preview 是 Google 最具成本效益的多模態模型，專為高容量代理任務、翻譯和數據處理而優化。", "ja-JP": "Gemini 3.1 Flash-Lite PreviewはGoogleの最もコスト効率の高いマルチモーダルモデルで、大量のエージェントタスク、翻訳、データ処理に最適化されています。", "ru-RU": "Gemini 3.1 Flash-Lite Preview — самая экономичная мультимодальная модель от Google, оптимизированная для задач с высоким объемом, перевода и обработки данных." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-3.1-flash-lite-preview-gt-128k", "model_name": "gemini-3.1-flash-lite-preview-gt-128k", "display_name": "gemini-3.1-flash-lite-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-flash-lite-preview-gt-128k" } ] }, { "slug": "google/gemini-3.1-flash-lite-preview-lte-128k", "model_name": "gemini-3.1-flash-lite-preview-lte-128k", "display_name": "gemini-3.1-flash-lite-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-flash-lite-preview-lte-128k" } ] }, { "slug": "google/gemini-3.1-flash-live-preview", "model_name": "gemini-3.1-flash-live-preview", "display_name": "Gemini 3.1 Flash Live Preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.75" }, "completion": { "unit": "per_M_tokens", "price": "4.5" }, "audio_input": { "unit": "per_M_tokens", "price": "3" }, "audio_output": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev", "audio_output": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications", "released_at": "2026-03-26", "knowledge_cutoff": "2025-01", "max_input_tokens": 131072, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text", "audio" ] }, "family": "gemini-flash", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing", "model_type": "realtime_omni", "rate_limits": { "rpm": 10, "tpm": 250000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-08-01", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-01", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "google/gemini-3.1-flash-tts-preview", "model_name": "gemini-3.1-flash-tts-preview", "display_name": "Gemini 3.1 Flash TTS Preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "20" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+truefoundry", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "audio_output": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "audio_output": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "audio_output": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "audio_output": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.1-flash-tts-preview", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Low-latency speech generation with steerable prompts and expressive audio tags", "released_at": "2026-04-15", "knowledge_cutoff": "2025-01", "max_input_tokens": 8192, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "family": "gemini-flash", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_output": true, "structured_output": true }, "model_type": "speech_synthesis", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-3.1-flash-tts-preview" ], "price_history": [ { "date": "2026-07-25", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-20", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-20", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-20", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Gemini 3.1 Flash TTS Preview" } ] }, { "slug": "google/gemini-3.1-pro-preview", "model_name": "gemini-3.1-pro-preview", "display_name": "Gemini 3.1 Pro Preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" }, "image_input": { "unit": "per_M_tokens", "price": "2" }, "video_input": { "unit": "per_M_tokens", "price": "2" }, "audio_input": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "cache_write_1h": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank", "audio_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank", "audio_input": "lobehub-modelbank" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "cache_write_1h": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank", "audio_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "14" }, "discarded_charge": { "unit": "per_k_calls", "price": "35" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "pydantic-prices", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "pydantic-prices introduced a ≥200000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "provider_model_id": "gemini-3-1-pro-preview", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "image_input": "2", "video_input": "2", "audio_input": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+helicone-registry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_image", "price": "0.00012" }, "cache_storage": { "unit": "per_M_tokens_per_hour", "price": "4.5" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" }, "cache_write": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "image_output": "litellm", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >200K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "image_output": "portkey", "maps": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "image_output": "portkey", "maps": "portkey" } }, { "label": "Priority AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "image_output": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "litellm", "web_search": "portkey", "google_search_grounding": "portkey", "image_output": "portkey", "maps": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+helicone-registry+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "image_output": "litellm", "cache_storage": "helicone-registry", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.00012" }, "discarded_charge": { "unit": "per_M_tokens", "price": "120" }, "message": "image_output from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "helicone-registry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "helicone-registry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch AND Context >200K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "3.6", "completion": "2.7", "cache_read": "3.6" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >200K", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "1.25", "web_search": "1", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "cache_write_1h": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.1-pro-preview", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "intro": "Reasoning-first Gemini preview for agentic coding and complex problem solving", "released_at": "2026-02-19", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "family": "gemini-pro", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "model_type": "image_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 2000, "tpm": 800000 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "reasoning_config": { "mandatory": true, "budget_min": 256 }, "benchmarks": { "intelligence_index": 47.7, "coding_index": 68.8, "agentic_index": 23 }, "aliases": [ "gemini-3-1-pro-preview", "gemini/gemini-3.1-pro-preview", "google/gemini-3.1-pro-preview", "pa/gemini-3.1-pro-preview", "vertex/gemini-3.1-pro-preview" ], "intro_i18n": { "zh-CN": "Gemini 3.1 Pro Preview在Gemini 3 Pro的基础上增强了推理能力，并增加了中等思维水平支持。", "zh-TW": "Gemini 3.1 Pro Preview 在 Gemini 3 Pro 的基礎上增強了推理能力，並新增了中等思考層級支持。", "ja-JP": "Gemini 3.1 Pro Previewは、Gemini 3 Proの推論能力を強化し、中程度の思考レベルサポートを追加しています。", "ru-RU": "Gemini 3.1 Pro Preview улучшает Gemini 3 Pro с расширенными возможностями рассуждений и добавляет поддержку среднего уровня мышления." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-3.1-pro-preview-customtools", "model_name": "gemini-3.1-pro-preview-customtools", "display_name": "Gemini 3.1 Pro Preview Custom Tools", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "cache_write_1h": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "cache_write_1h": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "14" }, "discarded_charge": { "unit": "per_k_calls", "price": "35" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "image_output": { "unit": "per_image", "price": "0.00012" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "maps": { "unit": "per_request", "price": "0.025" }, "cache_write": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "image_output": "litellm", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >200K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Priority AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >200K", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "litellm", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "image_output": "litellm", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "14" }, "discarded_charge": { "unit": "per_k_calls", "price": "35" }, "message": "web_search from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4.5" }, "message": "cache_read from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch AND Context >200K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "web_search": "2.5", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "2.5", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority AND Context >200K", "factor": "1", "charge_factors": { "web_search": "2.5", "google_search_grounding": "1", "maps": "1", "prompt": "3.6", "completion": "2.7", "cache_read": "3.6" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "2.5", "google_search_grounding": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >200K", "factor": "1", "charge_factors": { "web_search": "2.5", "google_search_grounding": "1", "maps": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "2.5", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "1.25", "web_search": "2.5", "google_search_grounding": "1", "maps": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis", "released_at": "2026-02-19", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "family": "gemini-pro", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "model_type": "image_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 2000, "tpm": 800000 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "reasoning_config": { "mandatory": true }, "aliases": [ "google/gemini-3.1-pro-preview-customtools" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-3.1-pro-preview-customtools-gt-128k", "model_name": "gemini-3.1-pro-preview-customtools-gt-128k", "display_name": "gemini-3.1-pro-preview-customtools-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "18" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-pro-preview-customtools-gt-128k" } ] }, { "slug": "google/gemini-3.1-pro-preview-customtools-gt-200k", "model_name": "gemini-3.1-pro-preview-customtools-gt-200k", "display_name": "gemini-3.1-pro-preview-customtools-gt-200k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "18" }, "cache_read": { "unit": "per_M_tokens", "price": "4.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-pro-preview-customtools-gt-200k" } ] }, { "slug": "google/gemini-3.1-pro-preview-customtools-lte-128k", "model_name": "gemini-3.1-pro-preview-customtools-lte-128k", "display_name": "gemini-3.1-pro-preview-customtools-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-pro-preview-customtools-lte-128k" } ] }, { "slug": "google/gemini-3.1-pro-preview-customtools-lte-200k", "model_name": "gemini-3.1-pro-preview-customtools-lte-200k", "display_name": "gemini-3.1-pro-preview-customtools-lte-200k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "4.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-pro-preview-customtools-lte-200k" } ] }, { "slug": "google/gemini-3.1-pro-preview-gt-128k", "model_name": "gemini-3.1-pro-preview-gt-128k", "display_name": "gemini-3.1-pro-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "18" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-pro-preview-gt-128k" } ] }, { "slug": "google/gemini-3.1-pro-preview-gt-200k", "model_name": "gemini-3.1-pro-preview-gt-200k", "display_name": "gemini-3.1-pro-preview-gt-200k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "18" }, "cache_read": { "unit": "per_M_tokens", "price": "4.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-pro-preview-gt-200k" } ] }, { "slug": "google/gemini-3.1-pro-preview-lte-128k", "model_name": "gemini-3.1-pro-preview-lte-128k", "display_name": "gemini-3.1-pro-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-pro-preview-lte-128k" } ] }, { "slug": "google/gemini-3.1-pro-preview-lte-200k", "model_name": "gemini-3.1-pro-preview-lte-200k", "display_name": "gemini-3.1-pro-preview-lte-200k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "google_search_grounding": { "unit": "per_k_calls", "price": "35" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "4.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.1-pro-preview-lte-200k" } ] }, { "slug": "google/gemini-3.5-flash", "model_name": "gemini-3.5-flash", "display_name": "Gemini 3.5 Flash", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "audio_input": { "unit": "per_M_tokens", "price": "1.5" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "9" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "image_input": { "unit": "per_M_tokens", "price": "1.5" }, "video_input": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "computeprices" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "audio_input from litellm conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gemini-3-5-flash", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "audio_input": { "unit": "per_M_tokens", "price": "1.5" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "9" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "enterprise_web_search": { "unit": "per_request", "price": "0.014" }, "maps": { "unit": "per_request", "price": "0.014" }, "cache_write": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "audio_input from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "audio_input from litellm conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "cache_read": "0.55" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1.98", "completion": "1.98", "cache_read": "1.98" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.55", "completion": "0.55", "cache_read": "0.55" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.165" }, "prompt": { "unit": "per_M_tokens", "price": "1.65" }, "completion": { "unit": "per_M_tokens", "price": "9.9" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.5-flash", "region": "asia-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.165" }, "prompt": { "unit": "per_M_tokens", "price": "1.65" }, "completion": { "unit": "per_M_tokens", "price": "9.9" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.5-flash", "region": "asia-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.165" }, "prompt": { "unit": "per_M_tokens", "price": "1.65" }, "completion": { "unit": "per_M_tokens", "price": "9.9" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.5-flash", "region": "asia-southeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.165" }, "prompt": { "unit": "per_M_tokens", "price": "1.65" }, "completion": { "unit": "per_M_tokens", "price": "9.9" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.5-flash", "region": "eu", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.165" }, "prompt": { "unit": "per_M_tokens", "price": "1.65" }, "completion": { "unit": "per_M_tokens", "price": "9.9" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.5-flash", "region": "europe-west2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "enterprise_web_search": { "unit": "per_request", "price": "0.014" }, "maps": { "unit": "per_request", "price": "0.014" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "google/gemini-3.5-flash", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.533333" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.165" }, "prompt": { "unit": "per_M_tokens", "price": "1.65" }, "completion": { "unit": "per_M_tokens", "price": "9.9" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.5-flash", "region": "us", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "released_at": "2026-05-19", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true }, "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 2000, "tpm": 800000 }, "parameters": { "unsupported": [ "temperature" ] }, "reasoning_config": { "mandatory": true, "budget_min": 256 }, "benchmarks": { "intelligence_index": 52, "coding_index": 70.1, "agentic_index": 39.7 }, "aliases": [ "gemini-3-5-flash", "gemini/gemini-3.5-flash", "google/gemini-3.5-flash", "vertex/gemini-3.5-flash" ], "intro_i18n": { "zh-CN": "Gemini 的最智能模型，专为速度而设计，结合前沿智能与卓越的搜索和基础能力。", "zh-TW": "Gemini 最智能的模型，專為速度而設計，結合前沿智能與卓越的搜索和基礎能力。", "ja-JP": "最先端の知能と優れた検索・基盤技術を組み合わせた、スピード重視のGeminiの最も知的なモデル。", "ru-RU": "Самая интеллектуальная модель Gemini, созданная для скорости, объединяющая передовой интеллект с превосходным поиском и обоснованием." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "google/gemini-3.5-flash-gt-128k", "model_name": "gemini-3.5-flash-gt-128k", "display_name": "gemini-3.5-flash-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.5-flash-gt-128k" } ] }, { "slug": "google/gemini-3.5-flash-lite", "model_name": "gemini-3.5-flash-lite", "display_name": "Gemini 3.5 Flash Lite", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "image_input": { "unit": "per_M_tokens", "price": "0.3" }, "video_input": { "unit": "per_M_tokens", "price": "0.3" }, "audio_input": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank", "audio_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank", "audio_input": "lobehub-modelbank" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" }, "cache_write": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "maps": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1", "cache_read": "0.55" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1.98", "completion": "1.98", "cache_read": "1.98" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.55", "completion": "0.55", "cache_read": "0.55" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.033" }, "prompt": { "unit": "per_M_tokens", "price": "0.33" }, "completion": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.5-flash-lite", "region": "eu", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "maps": { "unit": "per_request", "price": "0.014" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "google/gemini-3.5-flash-lite", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "maps": "1", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "maps": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.033" }, "prompt": { "unit": "per_M_tokens", "price": "0.33" }, "completion": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-3.5-flash-lite", "region": "us", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "released_at": "2026-07-21", "knowledge_cutoff": "2026-03", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash-lite", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing", "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 15, "tpm": 250000 }, "benchmarks": { "intelligence_index": 37.4, "coding_index": 49.3, "agentic_index": 27.2 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "reasoning_config": { "mandatory": true }, "aliases": [ "gemini-3-5-flash-lite", "gemini/gemini-3.5-flash-lite", "google/gemini-3.5-flash-lite", "vertex/gemini-3.5-flash-lite" ], "intro_i18n": { "zh-CN": "Gemini 3.5 Flash-Lite 是 Google 最快、最具成本效益的 3.5 模型，适用于高吞吐量的代理任务、文档解析和简单数据提取。", "zh-TW": "Gemini 3.5 Flash-Lite 是 Google 最快速、最具成本效益的 3.5 模型，適用於高吞吐量的代理任務、文件解析和簡單的數據提取。", "ja-JP": "Gemini 3.5 Flash-Liteは、エージェントタスク、高スループットのドキュメント解析、シンプルなデータ抽出において、Googleの最速かつ最もコスト効率の良い3.5モデルです。", "ru-RU": "Gemini 3.5 Flash-Lite — самая быстрая и экономичная модель 3.5 от Google для высокопроизводительных агентных задач, анализа документов и простого извлечения данных." }, "price_history": [ { "date": "2026-07-25", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-22", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-21", "kind": "listed", "note": "Gemini 3.5 Flash Lite" } ] }, { "slug": "google/gemini-3.5-flash-lite-gt-128k", "model_name": "gemini-3.5-flash-lite-gt-128k", "display_name": "gemini-3.5-flash-lite-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-25", "kind": "listed", "note": "gemini-3.5-flash-lite-gt-128k" } ] }, { "slug": "google/gemini-3.5-flash-lite-lte-128k", "model_name": "gemini-3.5-flash-lite-lte-128k", "display_name": "gemini-3.5-flash-lite-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-25", "kind": "listed", "note": "gemini-3.5-flash-lite-lte-128k" } ] }, { "slug": "google/gemini-3.5-flash-lte-128k", "model_name": "gemini-3.5-flash-lte-128k", "display_name": "gemini-3.5-flash-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-3.5-flash-lte-128k" } ] }, { "slug": "google/gemini-3.5-live-translate-preview", "model_name": "gemini-3.5-live-translate-preview", "display_name": "Gemini 3.5 Live Translate Preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3.5" }, "completion": { "unit": "per_M_tokens", "price": "21" }, "audio_input": { "unit": "per_M_tokens", "price": "3.5" }, "audio_output": { "unit": "per_M_tokens", "price": "21" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev", "audio_output": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Low-latency audio-to-audio model for real-time speech translation across 70+ languages", "released_at": "2026-06-09", "knowledge_cutoff": "2025-01", "max_input_tokens": 16384, "max_output_tokens": 32768, "modalities": { "input": [ "audio" ], "output": [ "audio", "text" ] }, "family": "gemini-pro", "capabilities": { "audio_input": true, "audio_output": true, "pdf_input": true }, "model_type": "realtime_speech_translation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-25", "kind": "limit", "old": "131072", "new": "16384", "note": "max_input_tokens" }, { "date": "2026-07-25", "kind": "limit", "old": "65536", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Gemini 3.5 Live Translate Preview" } ] }, { "slug": "google/gemini-3.6-flash", "model_name": "gemini-3.6-flash", "display_name": "Gemini 3.6 Flash", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "audio_input": { "unit": "per_M_tokens", "price": "1.5" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "7.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "image_input": { "unit": "per_M_tokens", "price": "0.75" }, "video_input": { "unit": "per_M_tokens", "price": "0.75" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.075" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.75" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.75" }, "message": "audio_input from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "7.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.75" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "truefoundry", "charge": "cache_write_1h", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "cache_write_1h from lobehub-modelbank conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.75" }, "message": "prompt from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "7.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.75" }, "message": "completion from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.075" }, "message": "cache_read from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.75" }, "message": "prompt from ai-model-directory conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "7.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.75" }, "message": "completion from ai-model-directory conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.075" }, "message": "cache_read from ai-model-directory conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "audio_input": { "unit": "per_M_tokens", "price": "1.5" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "7.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "enterprise_web_search": { "unit": "per_request", "price": "0.014" }, "maps": { "unit": "per_request", "price": "0.014" }, "cache_write": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "enterprise_web_search": { "unit": "per_request", "price": "0.014" }, "maps": { "unit": "per_request", "price": "0.014" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "google/gemini-3.6-flash", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "released_at": "2026-07-21", "knowledge_cutoff": "2026-03", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true }, "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 2000, "tpm": 800000 }, "parameters": { "unsupported": [ "temperature" ] }, "reasoning_config": { "mandatory": true, "budget_min": 256 }, "benchmarks": { "intelligence_index": 51.6, "coding_index": 69.2, "agentic_index": 40.5 }, "aliases": [ "gemini-3-6-flash", "gemini/gemini-3.6-flash", "google/gemini-3.6-flash", "vertex/gemini-3.6-flash" ], "intro_i18n": { "zh-CN": "Gemini 3.6 Flash 在代理和多模态任务中平衡了速度与智能，输出成本低于 3.5 Flash。", "zh-TW": "Gemini 3.6 Flash 在代理和多模態任務中平衡了速度與智能，輸出成本低於 3.5 Flash。", "ja-JP": "Gemini 3.6 Flashは、エージェントタスクやマルチモーダルタスクにおいて、スピードと知能をバランスさせ、3.5 Flashよりも低コストで出力を提供します。", "ru-RU": "Gemini 3.6 Flash сочетает скорость с интеллектом для агентных и мультимодальных задач, обеспечивая более низкую стоимость вывода, чем 3.5 Flash." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "google", "charge": "image_input", "old": "1.5", "new": "0.75" }, { "date": "2026-08-14", "kind": "price", "provider": "google", "charge": "video_input", "old": "1.5", "new": "0.75" } ] }, { "slug": "google/gemini-3.6-flash-gt-128k", "model_name": "gemini-3.6-flash-gt-128k", "display_name": "gemini-3.6-flash-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-25", "kind": "listed", "note": "gemini-3.6-flash-gt-128k" } ] }, { "slug": "google/gemini-3.6-flash-lte-128k", "model_name": "gemini-3.6-flash-lte-128k", "display_name": "gemini-3.6-flash-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-25", "kind": "listed", "note": "gemini-3.6-flash-lte-128k" } ] }, { "slug": "google/gemini-3.7-flash", "model_name": "gemini-3.7-flash", "display_name": "Gemini 3.7 Flash", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.75" }, "completion": { "unit": "per_M_tokens", "price": "3.75" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "audio_input": { "unit": "per_M_tokens", "price": "0.75" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "3.75" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "image_input": { "unit": "per_M_tokens", "price": "0.75" }, "video_input": { "unit": "per_M_tokens", "price": "0.75" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank", "cache_write_1h": "lobehub-modelbank" }, "verification_status": "cross_checked" } }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.75" }, "completion": { "unit": "per_M_tokens", "price": "3.75" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "audio_input": { "unit": "per_M_tokens", "price": "0.75" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "3.75" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "enterprise_web_search": { "unit": "per_request", "price": "0.014" }, "maps": { "unit": "per_request", "price": "0.014" }, "cache_write": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.75" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "prompt from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3.75" }, "discarded_charge": { "unit": "per_M_tokens", "price": "7.5" }, "message": "completion from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "cache_read from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "1", "completion": "1", "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "3.6", "completion": "3.6", "cache_read": "3.6" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1", "completion": "1", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "enterprise_web_search": { "unit": "per_request", "price": "0.014" }, "maps": { "unit": "per_request", "price": "0.014" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "enterprise_web_search": "portkey", "maps": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "google_search_grounding": "1", "enterprise_web_search": "1", "maps": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning", "released_at": "2026-08-13", "knowledge_cutoff": "2026-03", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true }, "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "rate_limits": { "rpm": 2000, "tpm": 800000 }, "benchmarks": { "intelligence_index": 56, "coding_index": 76.1, "agentic_index": 45.1 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "reasoning_config": { "mandatory": true }, "aliases": [ "gemini-3-7-flash", "google/gemini-3.7-flash", "vertex/gemini-3.7-flash" ], "price_history": [ { "date": "2026-08-13", "kind": "listed", "note": "Gemini 3.7 Flash" } ] }, { "slug": "google/gemini-3.7-flash-gt-128k", "model_name": "gemini-3.7-flash-gt-128k", "display_name": "gemini-3.7-flash-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-08-13", "kind": "listed", "note": "gemini-3.7-flash-gt-128k" } ] }, { "slug": "google/gemini-3.7-flash-lte-128k", "model_name": "gemini-3.7-flash-lte-128k", "display_name": "gemini-3.7-flash-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-08-13", "kind": "listed", "note": "gemini-3.7-flash-lte-128k" } ] }, { "slug": "google/gemini-embedding-001", "model_name": "gemini-embedding-001", "display_name": "Gemini Embedding 001", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "service_tier_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.12" }, "message": "batch prompt from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "asia-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "asia-east2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "asia-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "asia-northeast3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "asia-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "asia-southeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "australia-southeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "eu", "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "europe-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "europe-north1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "europe-southwest1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "europe-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "europe-west2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "europe-west3", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "europe-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "europe-west6", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "europe-west8", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "europe-west9", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "me-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "me-central2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "me-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "northamerica-northeast1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "southamerica-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "us-east1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "us-east4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "us-east5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "us-south1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "us-west1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-001", "region": "us-west4", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2025-05-20", "knowledge_cutoff": "2025-05", "max_input_tokens": 2048, "max_output_tokens": 1, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gemini", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "stream": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", "model_type": "text_embedding", "deprecation_date": "2028-05-14", "rate_limits": { "rpm": 10000, "tpm": 10000000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-embedding-001" ], "intro_i18n": { "zh-CN": "一款先进的嵌入模型，在英文、多语言和代码任务中表现出色。", "zh-TW": "一款最先進的嵌入模型，在英文、多語言與程式任務中表現優異。", "ja-JP": "英語、多言語、コードタスクにおいて高性能を発揮する最先端の埋め込みモデルです。", "ru-RU": "Современная модель встраивания с высокой производительностью для задач на английском языке, в многоязычной среде и в программировании." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-embedding-001-gt-128k", "model_name": "gemini-embedding-001-gt-128k", "display_name": "gemini-embedding-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_embedding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-embedding-001-gt-128k" } ] }, { "slug": "google/gemini-embedding-001-lte-128k", "model_name": "gemini-embedding-001-lte-128k", "display_name": "gemini-embedding-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_embedding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-embedding-001-lte-128k" } ] }, { "slug": "google/gemini-embedding-2", "model_name": "gemini-embedding-2", "display_name": "Gemini Embedding 2", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "audio_input": { "unit": "per_M_tokens", "price": "6.5" }, "image_input": { "unit": "per_image", "price": "0.00012" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev", "image_input": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev", "image_input": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_input": { "unit": "per_image", "price": "0.00012" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm" }, "verification_status": "cross_checked" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "6.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-2", "region": "eu", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "6.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-2", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "6.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-2", "region": "us", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space", "released_at": "2026-04-22", "knowledge_cutoff": "2025-11", "max_input_tokens": 8192, "max_output_tokens": 1, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "family": "gemini", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing", "model_type": "multimodal_embedding", "rate_limits": { "rpm": 10000, "tpm": 10000000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-embedding-2" ], "price_history": [ { "date": "2026-07-25", "kind": "limit", "old": "0", "new": "1", "note": "max_output_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "google/gemini-embedding-2-preview", "model_name": "gemini-embedding-2-preview", "display_name": "gemini-embedding-2-preview", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_input": { "unit": "per_image", "price": "0.00012" }, "audio_input": { "unit": "per_M_tokens", "price": "6.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm", "audio_input": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+truefoundry", "charge_sources": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm", "audio_input": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_input": { "unit": "per_image", "price": "0.00012" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm" }, "verification_status": "cross_checked" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "6.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-2-preview", "region": "eu", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "6.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-2-preview", "region": "global", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "6.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-2-preview", "region": "us", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "6.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "audio_input": "truefoundry", "prompt": "truefoundry" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-embedding-2-preview", "region": "us-central1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "max_input_tokens": 8192, "model_type": "multimodal_embedding", "capabilities": { "vision": true, "prompt_caching": true, "audio_input": true, "video_input": true, "pdf_input": true, "stream": true }, "deprecated": true, "deprecation_date": "2026-08-10", "rate_limits": { "rpm": 10000, "tpm": 10000000 }, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "embedding" ] }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-embedding-2-preview" ], "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-embedding-2-preview-gt-128k", "model_name": "gemini-embedding-2-preview-gt-128k", "display_name": "gemini-embedding-2-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_embedding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-embedding-2-preview-gt-128k" } ] }, { "slug": "google/gemini-embedding-2-preview-lte-128k", "model_name": "gemini-embedding-2-preview-lte-128k", "display_name": "gemini-embedding-2-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_embedding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-embedding-2-preview-lte-128k" } ] }, { "slug": "google/gemini-exp-1114", "model_name": "gemini-exp-1114", "display_name": "gemini-exp-1114", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://ai.google.dev/pricing", "max_input_tokens": 1048576, "max_output_tokens": 8192, "model_type": "vision_understanding", "rate_limits": { "rpm": 1000, "tpm": 4000000 }, "capabilities": { "vision": true, "function_calling": true, "structured_output": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-exp-1114" ] }, { "slug": "google/gemini-exp-1206", "model_name": "gemini-exp-1206", "display_name": "gemini-exp-1206", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from litellm conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://ai.google.dev/pricing", "max_input_tokens": 2097152, "max_output_tokens": 8192, "model_type": "vision_understanding", "rate_limits": { "rpm": 1000, "tpm": 4000000 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2024-12-06", "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "family": "gemini", "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "audio_input: false→true" } ] }, { "slug": "google/gemini-flash-1.5", "model_name": "gemini-flash-1.5", "display_name": "gemini-flash-1.5", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01875" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "tracks": [ { "label": "Context ≥128K", "source": "pydantic-prices", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" } }, { "label": "Base pricing", "source": "pydantic-prices", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Context ≥128K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Gemini 1.5 Flash is a foundation model that performs well at a variety of multimodal tasks such as visual understanding, classification, summarization, and creating content from image, audio and video. It's adept at processing visual and text inputs such as photographs, documents, infographics, and screenshots.", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-flash-1.5" ], "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemini 1.5 Flash" } ] }, { "slug": "google/gemini-flash-1.5-8b", "model_name": "gemini-flash-1.5-8b", "display_name": "gemini-flash-1.5-8b", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.0375" }, "completion": { "unit": "per_M_tokens", "price": "0.15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "tracks": [ { "label": "Context ≥128K", "source": "pydantic-prices", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" } }, { "label": "Base pricing", "source": "pydantic-prices", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Context ≥128K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "A faster, more cost-effective variant of Gemini 1.5 that maintains strong capabilities while optimizing for performance and cost efficiency. Suitable for production deployments requiring high throughput.", "max_input_tokens": 1000000, "capabilities": { "function_calling": true, "vision": true }, "max_output_tokens": 8192, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-flash-1.5-8b" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-flash-1.5-8b" } ] }, { "slug": "google/gemini-flash-experimental", "model_name": "gemini-flash-experimental", "display_name": "gemini-flash-experimental", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "max_input_tokens": 1000000, "max_output_tokens": 8192, "model_type": "vision_understanding", "capabilities": {}, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-flash-experimental" } ] }, { "slug": "google/gemini-flash-latest", "model_name": "gemini-flash-latest", "display_name": "Gemini Flash Latest", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "audio_input": { "unit": "per_M_tokens", "price": "1.5" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.1" }, "image_input": { "unit": "per_M_tokens", "price": "1.5" }, "video_input": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "9" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.075" }, "message": "cache_read from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "audio_input from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "9" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "audio_input from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.05" }, "message": "cache_read from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "audio_input from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "prompt from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "9" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "9" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.075" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "9" }, "discarded_charge": { "unit": "per_M_tokens", "price": "7.5" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.166667", "completion": "0.166667" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "audio_input": { "unit": "per_M_tokens", "price": "1.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0.383" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "cache_write": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "9" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.075" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Fast Gemini model balancing multimodal reasoning, tool use, and cost", "released_at": "2026-05-19", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "model_type": "vision_understanding", "rate_limits": { "rpm": 15, "tpm": 250000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "google/gemini-flash-latest", "~google/gemini-flash-latest" ], "intro_i18n": { "zh-CN": "指向 gemini-3.6-flash", "zh-TW": "指向 gemini-3-flash-preview", "ja-JP": "gemini-3-flash-previewを指します。", "ru-RU": "Указывает на gemini-3-flash-preview" }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "nano-gpt", "charge": "cache_read", "old": "0.15", "new": "0.075" }, { "date": "2026-08-14", "kind": "price", "provider": "nano-gpt", "charge": "completion", "old": "7.5", "new": "3.75" }, { "date": "2026-08-14", "kind": "price", "provider": "nano-gpt", "charge": "prompt", "old": "1.5", "new": "0.75" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "audio_input", "old": "1.5", "new": "0.375" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "cache_read", "old": "0.15", "new": "0.0375" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "cache_write", "old": "0.083333", "new": "0.020833" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "completion", "old": "7.5", "new": "1.875" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "internal_reasoning", "old": "7.5", "new": "1.875" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "1.5", "new": "0.375" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.15", "new": "0.0375" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "cache_write", "old": "0.083333", "new": "0.041667" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "cache_write", "old": "0.041667", "new": "0.020833" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "7.5", "new": "1.875" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "internal_reasoning", "old": "7.5", "new": "1.875" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "1.5", "new": "0.375" }, { "date": "2026-08-03", "kind": "price", "provider": "kilo", "charge": "cache_write", "old": "0.08333333333333334", "new": "0.083333" }, { "date": "2026-08-03", "kind": "price", "provider": "kilo", "charge": "completion", "old": "9", "new": "7.5" }, { "date": "2026-08-03", "kind": "price", "provider": "nano-gpt", "charge": "completion", "old": "9", "new": "7.5" }, { "date": "2026-07-22", "kind": "price", "provider": "kilo", "charge": "internal_reasoning", "old": "9", "new": "7.5" }, { "date": "2026-07-22", "kind": "price", "provider": "openrouter", "charge": "audio_input", "old": "3", "new": "1.5" } ] }, { "slug": "google/gemini-flash-latest-gt-128k", "model_name": "gemini-flash-latest-gt-128k", "display_name": "gemini-flash-latest-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-flash-latest-gt-128k" } ] }, { "slug": "google/gemini-flash-latest-lte-128k", "model_name": "gemini-flash-latest-lte-128k", "display_name": "gemini-flash-latest-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-flash-latest-lte-128k" } ] }, { "slug": "google/gemini-flash-lite-latest", "model_name": "gemini-flash-lite-latest", "display_name": "Gemini Flash-Lite Latest", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "audio_input": { "unit": "per_M_tokens", "price": "0.5" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "0.4" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.05" }, "image_input": { "unit": "per_M_tokens", "price": "0.3" }, "video_input": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm+truefoundry+lobehub-modelbank", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry", "cache_read_input_audio": "truefoundry", "image_input": "lobehub-modelbank", "video_input": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "audio_input from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.025" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.01" }, "message": "cache_read from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "audio_input from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.025" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "audio_input from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "provider_name": "Vertex", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "audio_input": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Low-latency Gemini model for high-volume multimodal and agent workloads", "released_at": "2026-05-07", "knowledge_cutoff": "2025-01", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio", "pdf" ], "output": [ "text" ] }, "family": "gemini-flash-lite", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://developers.googleblog.com/en/continuing-to-bring-you-our-latest-models-with-an-improved-gemini-2-5-flash-and-flash-lite-release/", "model_type": "vision_understanding", "rate_limits": { "rpm": 15, "tpm": 250000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "google/gemini-flash-lite-latest" ], "intro_i18n": { "zh-CN": "指向 gemini-3.5-flash-lite", "zh-TW": "指向 gemini-3.1-flash-lite", "ja-JP": "gemini-3.1-flash-liteを指します。", "ru-RU": "Указывает на gemini-3.1-flash-lite" }, "price_history": [ { "date": "2026-07-15", "kind": "price", "provider": "google", "charge": "audio_input", "old": "0.3", "new": "0.5" }, { "date": "2026-07-15", "kind": "price", "provider": "google", "charge": "completion", "old": "0.4", "new": "1.5" }, { "date": "2026-07-15", "kind": "price", "provider": "google", "charge": "prompt", "old": "0.1", "new": "0.25" }, { "date": "2026-07-15", "kind": "price", "provider": "google-vertex", "charge": "completion", "old": "0.4", "new": "1.5" }, { "date": "2026-07-15", "kind": "price", "provider": "google-vertex", "charge": "prompt", "old": "0.1", "new": "0.25" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "google/gemini-flash-lite-latest-gt-128k", "model_name": "gemini-flash-lite-latest-gt-128k", "display_name": "gemini-flash-lite-latest-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "cache_write": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-flash-lite-latest-gt-128k" } ] }, { "slug": "google/gemini-flash-lite-latest-lte-128k", "model_name": "gemini-flash-lite-latest-lte-128k", "display_name": "gemini-flash-lite-latest-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "cache_write": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-flash-lite-latest-lte-128k" } ] }, { "slug": "google/gemini-gemma-2-27b-it", "model_name": "gemini-gemma-2-27b-it", "display_name": "gemini-gemma-2-27b-it", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.35" }, "completion": { "unit": "per_M_tokens", "price": "1.05" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "max_input_tokens": 8192, "max_output_tokens": 8192, "model_type": "vision_understanding", "rate_limits": { "rpm": 10, "tpm": 250000 }, "capabilities": { "vision": true, "function_calling": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] } }, { "slug": "google/gemini-gemma-2-9b-it", "model_name": "gemini-gemma-2-9b-it", "display_name": "gemini-gemma-2-9b-it", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.35" }, "completion": { "unit": "per_M_tokens", "price": "1.05" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#foundation_models", "max_input_tokens": 8192, "max_output_tokens": 8192, "model_type": "vision_understanding", "rate_limits": { "rpm": 10, "tpm": 250000 }, "capabilities": { "vision": true, "function_calling": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] } }, { "slug": "google/gemini-live-2.5-flash", "model_name": "gemini-live-2.5-flash", "display_name": "gemini-live-2.5-flash", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "audio_input": { "unit": "per_M_tokens", "price": "3" }, "audio_output": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "audio_input": "pydantic-prices", "audio_output": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Google's Live API model for low-latency bidirectional voice and video interactions, GA on Vertex AI (model id `gemini-live-2.5-flash`, served from the `global` location). The prefix match also covers the AI Studio preview ids (`gemini-live-2.5-flash-preview*`).", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "realtime_omni", "price_history": [ { "date": "2026-07-25", "kind": "listed", "note": "gemini-live-2.5-flash" } ] }, { "slug": "google/gemini-live-2.5-flash-native-audio", "model_name": "gemini-live-2.5-flash-native-audio", "display_name": "gemini-live-2.5-flash-native-audio", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_M_tokens", "price": "3" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "audio_output": { "unit": "per_M_tokens", "price": "12" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-live-2.5-flash-native-audio" } ], "max_input_tokens": 128000, "max_output_tokens": 64000, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text", "audio" ] }, "model_type": "realtime_omni", "capabilities": { "function_calling": true, "vision": true, "audio_input": true, "video_input": true, "audio_output": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-live-2.5-flash-native-audio" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-live-2.5-flash-native-audio" } ] }, { "slug": "google/gemini-omni-flash-preview", "model_name": "gemini-omni-flash-preview", "display_name": "Gemini Omni Flash Preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "17.5" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "9" }, "audio_input": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "litellm", "audio_input": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "17.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "9" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "17.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "9" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "17.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "9" }, "message": "completion from ai-model-directory conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } }, { "provider": "google-vertex", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "9" }, "audio_input": { "unit": "per_M_tokens", "price": "1.5" }, "output_video_token": { "unit": "per_M_tokens", "price": "17.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "output_video_token": "portkey" }, "verification_status": "cross_checked" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/gemini-omni-flash-preview", "region": "global" } ], "intro": "Video generation and editing model for fast, conversational text- and image-to-video workflows", "released_at": "2026-06-30", "max_input_tokens": 131072, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "family": "gemini", "capabilities": { "vision": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "pdf_input": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing", "model_type": "omni", "rate_limits": { "rpm": 2000, "tpm": 800000 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "parameters": { "unsupported": [ "temperature" ] }, "aliases": [ "google/gemini-omni-flash-preview" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-14", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-08", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-08", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-08", "kind": "limit", "new": "57920", "note": "max_output_tokens" }, { "date": "2026-07-08", "kind": "limit", "old": "1048576", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-07-08", "kind": "limit", "old": "57920", "new": "65536", "note": "max_output_tokens" }, { "date": "2026-07-08", "kind": "price", "provider": "google", "charge": "completion", "old": "9", "new": "17.5" }, { "date": "2026-07-03", "kind": "listed", "note": "Gemini Omni Flash Preview" } ] }, { "slug": "google/gemini-omni-flash-preview-gt-128k", "model_name": "gemini-omni-flash-preview-gt-128k", "display_name": "gemini-omni-flash-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "output_video_token": { "unit": "per_M_tokens", "price": "17.5" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" } }, "provenance": { "base_charges": { "output_video_token": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "omni", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-omni-flash-preview-gt-128k" } ] }, { "slug": "google/gemini-omni-flash-preview-lte-128k", "model_name": "gemini-omni-flash-preview-lte-128k", "display_name": "gemini-omni-flash-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "output_video_token": { "unit": "per_M_tokens", "price": "17.5" }, "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "9" } }, "provenance": { "base_charges": { "output_video_token": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "omni", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-omni-flash-preview-lte-128k" } ] }, { "slug": "google/gemini-pro", "model_name": "gemini-pro", "display_name": "gemini-pro", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.125" }, "completion": { "unit": "per_M_tokens", "price": "0.375" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "pydantic-prices", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.25" }, "message": "prompt from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.375" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "completion from portkey conflicts with pydantic-prices; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.666667" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.125" }, "image_input": { "unit": "per_image", "price": "0.0025" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "intro": "Google's first-generation advanced multimodal model that can understand text, code, and images. It provides strong reasoning capabilities and follows instructions effectively.", "max_input_tokens": 32768, "capabilities": { "function_calling": true, "parallel_function_calling": true }, "max_output_tokens": 8192, "model_type": "text_generation", "released_at": "2026-08-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-pro" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-pro" } ] }, { "slug": "google/gemini-pro-1.5", "model_name": "gemini-pro-1.5", "display_name": "gemini-pro-1.5", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3125" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "tracks": [ { "label": "Context ≥128K", "source": "pydantic-prices", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" } }, { "label": "Base pricing", "source": "pydantic-prices", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Context ≥128K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Google's latest multimodal model, supports image and video[0] in text or chat prompts.", "max_input_tokens": 2000000, "capabilities": { "function_calling": true, "vision": true }, "max_output_tokens": 8192, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-pro-1.5" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-pro-1.5" } ] }, { "slug": "google/gemini-pro-latest", "model_name": "gemini-pro-latest", "display_name": "gemini-pro-latest", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "4.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >200K", "source": "litellm", "charge_sources": { "cache_read": "litellm", "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm+truefoundry", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.31" }, "message": "cache_read from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the litellm schedule; it was discarded." }, { "kind": "tier_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "cache_read", "threshold": 200000, "inclusive": false, "selected_charge": { "unit": "per_M_tokens", "price": "0.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.625" }, "message": "cache_read from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8", "completion": "0.6" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >200K", "factor": "1", "charge_factors": { "cache_read": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "max_input_tokens": 1048576, "max_output_tokens": 65535, "model_type": "vision_understanding", "rate_limits": { "rpm": 2000, "tpm": 800000 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "modalities": { "input": [ "audio", "image", "pdf" ], "output": [] }, "knowledge_cutoff": "2025-01", "intro": "Advanced Gemini model for complex reasoning, coding, and multimodal analysis", "released_at": "2026-03-29", "family": "gemini-pro", "aliases": [ "google/gemini-pro-latest", "~google/gemini-pro-latest" ], "intro_i18n": { "zh-CN": "指向 gemini-3.1-pro-preview", "zh-TW": "指向 gemini-3.1-pro-preview", "ja-JP": "gemini-3.1-pro-previewを指します。", "ru-RU": "Указывает на gemini-3.1-pro-preview" } }, { "slug": "google/gemini-pro-latest-gt-128k", "model_name": "gemini-pro-latest-gt-128k", "display_name": "gemini-pro-latest-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "18" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-pro-latest-gt-128k" } ] }, { "slug": "google/gemini-pro-latest-lte-128k", "model_name": "gemini-pro-latest-lte-128k", "display_name": "gemini-pro-latest-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "14" }, "google_search_grounding": { "unit": "per_k_calls", "price": "14" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "google_search_grounding": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-pro-latest-lte-128k" } ] }, { "slug": "google/gemini-pro-vision", "model_name": "gemini-pro-vision", "display_name": "gemini-pro-vision", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.0025" }, "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 2048, "modalities": { "input": [ "image" ], "output": [] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "parallel_function_calling": true, "vision": true }, "deprecated": true, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemini-pro-vision" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-pro-vision" } ] }, { "slug": "google/gemini-robotics-er-1.5-preview", "model_name": "gemini-robotics-er-1.5-preview", "display_name": "gemini-robotics-er-1.5-preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "1" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm" }, "verification_status": "cross_checked" } }, { "provider": "google-vertex", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://ai.google.dev/gemini-api/docs/models#gemini-robotics-er-1-5-preview", "max_input_tokens": 1048576, "max_output_tokens": 65535, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "deprecated": true, "deprecation_date": "2026-04-30", "rate_limits": { "rpm": 10, "tpm": 250000 }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "released_at": "2026-08-14", "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "google/gemini-robotics-er-1.5-preview-gt-128k", "model_name": "gemini-robotics-er-1.5-preview-gt-128k", "display_name": "gemini-robotics-er-1.5-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-robotics-er-1.5-preview-gt-128k" } ] }, { "slug": "google/gemini-robotics-er-1.5-preview-lte-128k", "model_name": "gemini-robotics-er-1.5-preview-lte-128k", "display_name": "gemini-robotics-er-1.5-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemini-robotics-er-1.5-preview-lte-128k" } ] }, { "slug": "google/gemini-robotics-er-1.6-preview", "model_name": "gemini-robotics-er-1.6-preview", "display_name": "Gemini Robotics-ER 1.6 Preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "5" }, "audio_input": { "unit": "per_M_tokens", "price": "2" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "5" }, "web_search": { "unit": "per_k_calls", "price": "14" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+litellm", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "models-dev", "internal_reasoning": "litellm", "web_search": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics", "released_at": "2026-04-14", "knowledge_cutoff": "2025-01", "max_input_tokens": 131072, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "family": "gemini", "reasoning_config": { "budget_min": 0 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er", "model_type": "deep_thinking", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "google/gemini-robotics-er-1.6-preview" ], "price_history": [ { "date": "2026-08-04", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-08-04", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Gemini Robotics-ER 1.6 Preview" } ] }, { "slug": "google/gemini-robotics-er-2-preview", "model_name": "gemini-robotics-er-2-preview", "display_name": "gemini-robotics-er-2-preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "10" }, "audio_input": { "unit": "per_M_tokens", "price": "2" }, "web_search": { "unit": "per_k_calls", "price": "14" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+truefoundry", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "internal_reasoning": "litellm", "audio_input": "litellm", "web_search": "litellm", "cache_write_1h": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-robotics-er-2", "max_input_tokens": 131072, "max_output_tokens": 65536, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "openai-compatible" ] }, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "released_at": "2026-07-01", "knowledge_cutoff": "2025-01", "aliases": [ "google/gemini-robotics-er-2-preview" ], "price_history": [ { "date": "2026-08-04", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-08-04", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-08-01", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-08-01", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-08-01", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-31", "kind": "listed", "note": "Gemini Robotics-ER 2 Preview" } ] }, { "slug": "google/gemini-robotics-er-2-streaming-preview", "model_name": "gemini-robotics-er-2-streaming-preview", "display_name": "gemini-robotics-er-2-streaming-preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "audio_input": { "unit": "per_M_tokens", "price": "2" }, "web_search": { "unit": "per_k_calls", "price": "14" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "web_search": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://ai.google.dev/gemini-api/docs/pricing", "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "audio_input": true, "video_input": true, "pdf_input": true, "web_search": true }, "max_input_tokens": 131072, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "released_at": "2026-07-01", "knowledge_cutoff": "2025-01", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-08-12", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-08-01", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-08-01", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-31", "kind": "listed", "note": "Gemini Robotics-ER 2 Streaming Preview" } ] }, { "slug": "google/gemma-2-27b-it", "model_name": "gemma-2-27b-it", "display_name": "Gemma 2 27B", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.65" }, "completion": { "unit": "per_M_tokens", "price": "0.65" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Gemma 2 27B by Google is an open model built from the same research and technology used to create the Gemini models. Gemma models are well-suited for a variety of text generation and instruction-following tasks.", "capabilities": { "function_calling": true, "structured_output": true, "open_weights": true }, "released_at": "2024-07-13", "knowledge_cutoff": "2024-06", "max_input_tokens": 8192, "max_output_tokens": 2048, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gemma", "deprecated": true, "model_type": "text_generation", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_p" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemma-2-27b-it" ], "intro_i18n": { "zh-CN": "Gemma 2 27B 是一款通用大型语言模型，在多种场景下表现优异。", "zh-TW": "Gemma 2 27B 是一款通用大型語言模型，在多種場景中表現出色。", "ja-JP": "Gemma 2 27Bは、さまざまなシナリオで高性能を発揮する汎用LLMです。", "ru-RU": "Gemma 2 27B — универсальная языковая модель с высокой производительностью в различных сценариях." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Google: Gemma 2 27B" } ] }, { "slug": "google/gemma-3-12b-it", "model_name": "gemma-3-12b-it", "display_name": "Gemma 3 12B", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "open_weights": true, "pdf_input": true, "prompt_caching": true, "structured_output": true, "reasoning": true }, "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments", "released_at": "2025-03-12", "family": "gemma", "knowledge_cutoff": "2024-08", "deprecated": true, "benchmarks": { "intelligence_index": 5.5, "coding_index": 5.8, "agentic_index": 0.3 }, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "@cf/google/gemma-3-12b-it", "accounts/fireworks/models/gemma-3-12b-it", "deepinfra/google/gemma-3-12b-it", "gemma-3-12b-it:free", "google.gemma-3-12b-it", "google/gemma-3-12b-it", "google/gemma-3-12b-it:free", "unsloth/gemma-3-12b-it", "workers-ai/@cf/google/gemma-3-12b-it" ], "intro_i18n": { "zh-CN": "Gemma 3 12B 是 Google 推出的开源语言模型，在效率和性能方面树立了新标杆。", "zh-TW": "Gemma 3 12B 是 Google 推出的開源語言模型，在效率與效能上樹立新標竿。", "ja-JP": "Gemma 3 12Bは、効率と性能の新たな基準を打ち立てるGoogleのオープンソース言語モデルです。", "ru-RU": "Gemma 3 12B — языковая модель с открытым исходным кодом от Google, устанавливающая новый стандарт эффективности и производительности." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemma 3 12B" } ] }, { "slug": "google/gemma-3-1b-it", "model_name": "gemma-3-1b-it", "display_name": "Gemma 3 1B", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "truefoundry+llmdb", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "0" }, "cache_read": { "unit": "per_M_tokens", "price": "0" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "capabilities": { "prompt_caching": true, "open_weights": true }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "accounts/fireworks/models/gemma-3-1b-it" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemma 3 1B" } ] }, { "slug": "google/gemma-3-27b-it", "model_name": "gemma-3-27b-it", "display_name": "gemma-3-27b-it", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_input": { "unit": "per_image", "price": "0" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "cache_write_1h": { "unit": "per_M_tokens", "price": "0" }, "cache_read": { "unit": "per_M_tokens", "price": "0" }, "speech_input": { "unit": "per_M_characters", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm", "cache_write": "truefoundry", "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "speech_input": "truefoundry", "web_search": "llmdb" }, "verification_status": "cross_checked" } } ], "docs_url": "https://aistudio.google.com", "max_input_tokens": 131072, "max_output_tokens": 8192, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "open_weights": true, "stream": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "Gemma 3 is a family of lightweight, multimodal models from Google, supporting text and image inputs, multilingual capabilities, and a 131K context window.", "released_at": "2025-03-12", "parameters": { "unsupported": [ "temperature" ] }, "family": "gemma", "knowledge_cutoff": "2024-08", "deprecated": true, "benchmarks": { "intelligence_index": 7.4, "coding_index": 10.1, "agentic_index": 0.3 }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "TEE/gemma-3-27b-it", "accounts/fireworks/models/gemma-3-27b-it", "deepinfra/google/gemma-3-27b-it", "gemma-3-27b-it:free", "google.gemma-3-27b-it", "google/gemma-3-27b-it", "google/gemma-3-27b-it:free", "nebius/google/gemma-3-27b-it", "unsloth/gemma-3-27b-it" ], "intro_i18n": { "zh-CN": "Gemma 3 27B 是 Google 推出的开源语言模型，在效率和性能方面树立了新标杆。", "zh-TW": "Gemma 3 27B 是 Google 推出的開源語言模型，在效率與效能上樹立新標竿。", "ja-JP": "Gemma 3 27Bは、効率と性能の新たな基準を打ち立てるGoogleのオープンソース言語モデルです。", "ru-RU": "Gemma 3 27B — языковая модель с открытым исходным кодом от Google, устанавливающая новый стандарт эффективности и производительности." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "google/gemma-3-4b-it", "model_name": "gemma-3-4b-it", "display_name": "Gemma 3 4B", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "vision": true, "open_weights": true, "pdf_input": true, "prompt_caching": true, "structured_output": true, "stream": true, "reasoning": true }, "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments", "released_at": "2025-03-12", "family": "gemma", "knowledge_cutoff": "2024-08", "deprecated": true, "benchmarks": { "intelligence_index": null, "coding_index": 2.7, "agentic_index": null }, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "accounts/fireworks/models/gemma-3-4b-it", "deepinfra/google/gemma-3-4b-it", "gemma-3-4b-it:free", "google.gemma-3-4b-it", "google/gemma-3-4b-it", "google/gemma-3-4b-it:free", "unsloth/gemma-3-4b-it" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemma 3 4B" } ] }, { "slug": "google/gemma-3n-e2b-it", "model_name": "gemma-3n-e2b-it", "display_name": "Gemma 3n E2B", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "truefoundry+llmdb", "charges": { "cache_write_1h": { "unit": "per_M_tokens", "price": "0" }, "cache_read": { "unit": "per_M_tokens", "price": "0" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "cache_write_1h": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32000, "max_output_tokens": 2048, "modalities": { "input": [ "text", "audio", "image", "video" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "vision": true, "audio_input": true, "video_input": true, "function_calling": true, "structured_output": true, "open_weights": true, "pdf_input": true, "prompt_caching": true }, "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments", "released_at": "2025-06-12", "knowledge_cutoff": "2024-06", "deprecated": true, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemma-3n-e2b-it:free", "google/gemma-3n-e2b-it", "google/gemma-3n-e2b-it:free" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Gemma 3n E2B" } ] }, { "slug": "google/gemma-3n-E4B-it", "model_name": "gemma-3n-E4B-it", "display_name": "Gemma 3n E4B", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb" }, "verification_status": "aggregator_only" }, "provider_model_id": "gemma-3n-e4b-it" } ], "max_input_tokens": 32000, "max_output_tokens": 32000, "modalities": { "input": [ "text", "audio", "image", "video" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "vision": true, "audio_input": true, "video_input": true, "function_calling": true, "structured_output": true, "open_weights": true, "pdf_input": true, "prompt_caching": true }, "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments", "released_at": "2025-06-03", "knowledge_cutoff": "2024-06", "family": "gemma", "deprecated": true, "benchmarks": { "intelligence_index": null, "coding_index": 3.2, "agentic_index": null }, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "stop", "structured_outputs", "temperature", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "gemma-3n-e4b-it", "gemma-3n-e4b-it:free", "google/gemma-3n-E4B-it", "google/gemma-3n-e4b-it", "google/gemma-3n-e4b-it:free" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Gemma 3n E4B" } ] }, { "slug": "google/gemma-4-26b-a4b-it", "model_name": "gemma-4-26b-a4b-it", "display_name": "Gemma 4 26B A4B IT", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+pydantic-prices+truefoundry+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.33" }, "cache_read": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "pydantic-prices", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.06" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "prompt from truefoundry conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.33" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from truefoundry conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "pydantic-prices", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.06" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "prompt from lobehub-modelbank conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.33" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from lobehub-modelbank conflicts with pydantic-prices; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments", "released_at": "2026-04-02", "max_input_tokens": 262144, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gemma", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "web_search": true }, "model_type": "deep_thinking", "knowledge_cutoff": "2025-01", "status": "beta", "benchmarks": { "intelligence_index": 26.1, "coding_index": 39.3, "agentic_index": 11 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95, "top_k": 64 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "@cf/google/gemma-4-26b-a4b-it", "accounts/fireworks/models/gemma-4-26b-a4b-it", "deepinfra/google/gemma-4-26B-A4B-it", "gemma-4-26B-A4B-it", "google/gemma-4-26B-A4B-it", "google/gemma-4-26b-a4b-it", "google/gemma-4-26b-a4b-it:free", "google/gemma-4-26b-a4b-it:thinking", "novita/google/gemma-4-26b-a4b-it", "parasail/google/gemma-4-26B-A4B-it", "workers-ai/@cf/google/gemma-4-26b-a4b-it" ], "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "hyper", "charge": "cache_write", "old": "0.063", "new": "0.062" }, { "date": "2026-08-14", "kind": "price", "provider": "hyper", "charge": "prompt", "old": "0.126", "new": "0.124" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.063", "new": "0.062" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.126", "new": "0.124" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.518819525", "new": "0.518985635" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.518819525", "new": "0.518985635" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "cache_write", "old": "0.058", "new": "0.063" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "completion", "old": "0.408", "new": "0.42" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "prompt", "old": "0.116", "new": "0.126" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.058", "new": "0.063" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "0.408", "new": "0.42" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.116", "new": "0.126" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "0.518900655", "new": "0.518819525" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.518900655", "new": "0.518819525" }, { "date": "2026-08-12", "kind": "price", "provider": "hyper", "charge": "cache_write", "old": "0.059", "new": "0.058" }, { "date": "2026-08-12", "kind": "price", "provider": "hyper", "charge": "completion", "old": "0.428", "new": "0.408" }, { "date": "2026-08-12", "kind": "price", "provider": "hyper", "charge": "prompt", "old": "0.118", "new": "0.116" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.059", "new": "0.058" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "completion", "old": "0.428", "new": "0.408" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.118", "new": "0.116" } ] }, { "slug": "google/gemma-4-26b-a4b-it-maas", "model_name": "gemma-4-26b-a4b-it-maas", "display_name": "gemma-4-26b-a4b-it-maas", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.015" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.015" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/gemma-4-26b-a4b-it-maas", "region": "global" } ], "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true, "pdf_input": true }, "max_input_tokens": 262144, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemma-4-26b-a4b-it-maas" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gemma-4-26b-a4b-it-maas" } ] }, { "slug": "google/gemma-4-31b-it", "model_name": "gemma-4-31b-it", "display_name": "Gemma 4 31B IT", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+pydantic-prices+truefoundry+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.12" }, "completion": { "unit": "per_M_tokens", "price": "0.36" }, "cache_read": { "unit": "per_M_tokens", "price": "0.09" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "pydantic-prices", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.12" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "prompt from truefoundry conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.36" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from truefoundry conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "pydantic-prices", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.09" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "cache_read from lobehub-modelbank conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "pydantic-prices", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.12" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "prompt from lobehub-modelbank conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.36" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from lobehub-modelbank conflicts with pydantic-prices; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Largest Gemma 4 instruction model for open, self-hosted chat and reasoning", "released_at": "2026-04-02", "max_input_tokens": 262144, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gemma", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "web_search": true }, "model_type": "deep_thinking", "knowledge_cutoff": "2025-01", "docs_url": "https://cloud.sambanova.ai/plans/pricing", "benchmarks": { "intelligence_index": 29.7, "coding_index": 43.4, "agentic_index": 14.4 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95, "top_k": 64 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "TEE/gemma-4-31b-it", "accounts/fireworks/models/gemma-4-31b-it", "deepinfra/google/gemma-4-31B-it", "gemma-4-31B-it", "gemma-4-31b-it:free", "google/gemma-4-31B-it", "google/gemma-4-31b-it", "google/gemma-4-31b-it:free", "google/gemma-4-31b-it:thinking", "pearl-ai/gemma-4-31b-it" ], "price_history": [ { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "cache_read", "old": "0.01", "new": "0.05" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "cache_read", "old": "0.05", "new": "0.01" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "completion", "old": "0.35", "new": "0.34" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "completion", "old": "0.34", "new": "0.35" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "0.08", "new": "0.09" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "0.09", "new": "0.08" }, { "date": "2026-08-08", "kind": "price", "provider": "kilo", "charge": "cache_read", "old": "0.05", "new": "0.01" }, { "date": "2026-08-08", "kind": "price", "provider": "kilo", "charge": "completion", "old": "0.34", "new": "0.35" }, { "date": "2026-08-08", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "0.09", "new": "0.08" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "completion", "old": "0.35", "new": "0.39" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "prompt", "old": "0.2", "new": "0.223" }, { "date": "2026-08-03", "kind": "price", "provider": "kilo", "charge": "completion", "old": "0.4", "new": "0.34" }, { "date": "2026-08-03", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "0.14", "new": "0.09" }, { "date": "2026-08-03", "kind": "price", "provider": "nano-gpt", "charge": "completion", "old": "0.306", "new": "0.35" }, { "date": "2026-08-03", "kind": "price", "provider": "nano-gpt", "charge": "prompt", "old": "0.306", "new": "0.1" }, { "date": "2026-07-30", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.09", "new": "0.1" }, { "date": "2026-07-30", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "0.4", "new": "0.34" }, { "date": "2026-07-30", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.14", "new": "0.1" }, { "date": "2026-07-27", "kind": "price", "provider": "llmgateway", "charge": "completion", "old": "0.38", "new": "0.297" }, { "date": "2026-07-27", "kind": "price", "provider": "llmgateway", "charge": "prompt", "old": "0.13", "new": "0.102" } ] }, { "slug": "google/gemma4", "model_name": "gemma4", "display_name": "gemma4", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.015" }, "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/gemma4" } ], "intro": "Open Gemma instruction model for efficient chat and self-hosted deployments", "released_at": "2026-04-02", "max_input_tokens": 262144, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gemma", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/gemma4" ], "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.57681632", "new": "0.576166795" }, { "date": "2026-08-14", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.28840816", "new": "0.2880833975" }, { "date": "2026-08-13", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.57728041", "new": "0.57681632" }, { "date": "2026-08-13", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.288640205", "new": "0.28840816" }, { "date": "2026-08-12", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.577674015", "new": "0.57728041" }, { "date": "2026-08-12", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.2888370075", "new": "0.288640205" }, { "date": "2026-08-11", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.57801792", "new": "0.577674015" }, { "date": "2026-08-11", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.28900896", "new": "0.2888370075" }, { "date": "2026-08-10", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.577930585", "new": "0.57801792" }, { "date": "2026-08-10", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.2889652925", "new": "0.28900896" }, { "date": "2026-08-09", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.576162225", "new": "0.577930585" }, { "date": "2026-08-09", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.2880811125", "new": "0.2889652925" }, { "date": "2026-08-08", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.57764259", "new": "0.576162225" }, { "date": "2026-08-08", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.288821295", "new": "0.2880811125" }, { "date": "2026-08-07", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.5768647", "new": "0.57764259" }, { "date": "2026-08-07", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.28843235", "new": "0.288821295" }, { "date": "2026-08-06", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.575504175", "new": "0.5768647" }, { "date": "2026-08-06", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.2877520875", "new": "0.28843235" }, { "date": "2026-08-05", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.576461085", "new": "0.575504175" }, { "date": "2026-08-05", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.2882305425", "new": "0.2877520875" } ] }, { "slug": "google/imagen-3.0-capability-001", "model_name": "imagen-3.0-capability-001", "display_name": "imagen-3.0-capability-001", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "australia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-north1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-southwest1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west6" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west8" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west9" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "global" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "northamerica-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "southamerica-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east5" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west4" } ], "capabilities": { "vision": true, "image_output": true }, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "model_type": "image_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-3.0-capability-001" } ] }, { "slug": "google/imagen-3.0-capability-002", "model_name": "imagen-3.0-capability-002", "display_name": "imagen-3.0-capability-002", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-3.0-capability-002" } ] }, { "slug": "google/imagen-3.0-fast-generate-001", "model_name": "imagen-3.0-fast-generate-001", "display_name": "imagen-3.0-fast-generate-001", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "litellm" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "australia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-north1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-southwest1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west6" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west8" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west9" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "global" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "northamerica-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "southamerica-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east5" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west4" } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_type": "image_generation", "capabilities": { "image_output": true }, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "google/imagen-3.0-generate-001", "model_name": "imagen-3.0-generate-001", "display_name": "imagen-3.0-generate-001", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "litellm" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "australia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-north1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-southwest1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west6" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west8" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west9" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "global" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "northamerica-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "southamerica-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east5" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west4" } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_type": "image_generation", "capabilities": { "image_output": true }, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "google/imagen-3.0-generate-002", "model_name": "imagen-3.0-generate-002", "display_name": "imagen-3.0-generate-002", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "litellm" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "australia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-north1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-southwest1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west6" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west8" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west9" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "global" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "northamerica-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "southamerica-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east5" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west4" } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "deprecated": true, "model_type": "image_generation", "deprecation_date": "2025-11-10", "capabilities": { "image_output": true }, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "google/imagen-4.0-fast-generate-001", "model_name": "imagen-4.0-fast-generate-001", "display_name": "imagen-4.0-fast-generate-001", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+llmdb+lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.02" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "image_output": "litellm", "web_search": "llmdb" }, "verification_status": "cross_checked" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "australia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "eu" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-north1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-southwest1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west6" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west8" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west9" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "global" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "northamerica-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "southamerica-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east5" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west4" } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_type": "image_generation", "deprecation_date": "2026-08-17", "capabilities": { "vision": true, "image_output": true }, "max_output_tokens": 8192, "deprecated": true, "modalities": { "input": [ "image" ], "output": [] }, "max_input_tokens": 480, "released_at": "2025-08-15", "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "imagen", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/imagen-4.0-fast-generate-001" ], "intro_i18n": { "zh-CN": "Imagen 第四代文本生成图像模型系列 Fast 版本", "zh-TW": "Imagen 第四代文字轉圖像模型系列的快速版本", "ja-JP": "Imagen第4世代テキスト→画像モデルシリーズの高速版です。", "ru-RU": "Серия моделей генерации изображений Imagen 4-го поколения, версия Fast." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "limit", "old": "0", "new": "8192", "note": "max_output_tokens" } ] }, { "slug": "google/imagen-4.0-fast-generate-001-gt-128k", "model_name": "imagen-4.0-fast-generate-001-gt-128k", "display_name": "imagen-4.0-fast-generate-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.02" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-4.0-fast-generate-001-gt-128k" } ] }, { "slug": "google/imagen-4.0-fast-generate-001-lte-128k", "model_name": "imagen-4.0-fast-generate-001-lte-128k", "display_name": "imagen-4.0-fast-generate-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.02" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-4.0-fast-generate-001-lte-128k" } ] }, { "slug": "google/imagen-4.0-fast-generate-preview-06-06", "model_name": "imagen-4.0-fast-generate-preview-06-06", "display_name": "imagen-4.0-fast-generate-preview-06-06", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.02" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-4.0-fast-generate-preview-06-06" } ] }, { "slug": "google/imagen-4.0-generate-001", "model_name": "imagen-4.0-generate-001", "display_name": "imagen-4.0-generate-001", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+llmdb+lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.04" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "image_output": "litellm", "web_search": "llmdb" }, "verification_status": "cross_checked" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "australia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-north1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-southwest1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west6" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west8" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west9" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "global" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "northamerica-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "southamerica-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east5" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west4" } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_type": "image_generation", "deprecation_date": "2026-08-17", "capabilities": { "image_output": true }, "max_input_tokens": 480, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "image" ] }, "max_output_tokens": 8192, "released_at": "2025-08-15", "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "imagen", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/imagen-4.0-generate-001" ], "intro_i18n": { "zh-CN": "Imagen 第四代文本生成图像模型系列", "zh-TW": "Imagen 第四代文字轉圖像模型系列", "ja-JP": "Imagen第4世代テキスト→画像モデルシリーズです。", "ru-RU": "Серия моделей генерации изображений Imagen 4-го поколения." }, "price_history": [ { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "limit", "old": "0", "new": "8192", "note": "max_output_tokens" } ] }, { "slug": "google/imagen-4.0-generate-001-gt-128k", "model_name": "imagen-4.0-generate-001-gt-128k", "display_name": "imagen-4.0-generate-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.04" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-4.0-generate-001-gt-128k" } ] }, { "slug": "google/imagen-4.0-generate-001-lte-128k", "model_name": "imagen-4.0-generate-001-lte-128k", "display_name": "imagen-4.0-generate-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.04" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-4.0-generate-001-lte-128k" } ] }, { "slug": "google/imagen-4.0-generate-preview-05-20", "model_name": "imagen-4.0-generate-preview-05-20", "display_name": "imagen-4.0-generate-preview-05-20", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-4.0-generate-preview-05-20" } ] }, { "slug": "google/imagen-4.0-generate-preview-06-06", "model_name": "imagen-4.0-generate-preview-06-06", "display_name": "imagen-4.0-generate-preview-06-06", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.04" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-4.0-generate-preview-06-06" } ] }, { "slug": "google/imagen-4.0-ultra-generate-001", "model_name": "imagen-4.0-ultra-generate-001", "display_name": "imagen-4.0-ultra-generate-001", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "litellm+truefoundry+llmdb+lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.06" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "image_output": "litellm", "web_search": "llmdb" }, "verification_status": "cross_checked" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "australia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-north1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-southwest1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west6" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west8" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west9" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "global" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "northamerica-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "southamerica-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east5" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west4" } ], "docs_url": "https://cloud.google.com/vertex-ai/generative-ai/pricing", "model_type": "image_generation", "deprecation_date": "2026-08-17", "capabilities": { "vision": true, "image_output": true }, "max_output_tokens": 8192, "deprecated": true, "modalities": { "input": [ "image" ], "output": [] }, "max_input_tokens": 480, "released_at": "2025-08-15", "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "family": "imagen", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/imagen-4.0-ultra-generate-001" ], "intro_i18n": { "zh-CN": "Imagen 第四代文本生成图像模型系列 Ultra 版本", "zh-TW": "Imagen 第四代文字轉圖像模型系列的超高版本", "ja-JP": "Imagen第4世代テキスト→画像モデルシリーズのUltraバージョンです。", "ru-RU": "Серия моделей генерации изображений Imagen 4-го поколения, версия Ultra." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "limit", "old": "0", "new": "8192", "note": "max_output_tokens" } ] }, { "slug": "google/imagen-4.0-ultra-generate-001-gt-128k", "model_name": "imagen-4.0-ultra-generate-001-gt-128k", "display_name": "imagen-4.0-ultra-generate-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.06" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-4.0-ultra-generate-001-gt-128k" } ] }, { "slug": "google/imagen-4.0-ultra-generate-001-lte-128k", "model_name": "imagen-4.0-ultra-generate-001-lte-128k", "display_name": "imagen-4.0-ultra-generate-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.06" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "image_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-4.0-ultra-generate-001-lte-128k" } ] }, { "slug": "google/imagen-4.0-ultra-generate-preview-05-20", "model_name": "imagen-4.0-ultra-generate-preview-05-20", "display_name": "imagen-4.0-ultra-generate-preview-05-20", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-4.0-ultra-generate-preview-05-20" } ] }, { "slug": "google/imagen-4.0-ultra-generate-preview-06-06", "model_name": "imagen-4.0-ultra-generate-preview-06-06", "display_name": "imagen-4.0-ultra-generate-preview-06-06", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.06" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-4.0-ultra-generate-preview-06-06" } ] }, { "slug": "google/imagen-product-recontext-preview-06-30", "model_name": "imagen-product-recontext-preview-06-30", "display_name": "imagen-product-recontext-preview-06-30", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_output": { "unit": "per_image", "price": "0.12" } }, "provenance": { "base_charges": { "image_output": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "imagen-product-recontext-preview-06-30" } ] }, { "slug": "google/language-v1-analyze-entity-sentiment", "model_name": "language-v1-analyze-entity-sentiment", "display_name": "language-v1-analyze-entity-sentiment", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "2" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/language-v1-analyze-entity-sentiment" } ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_understanding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/language-v1-analyze-entity-sentiment" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "language-v1-analyze-entity-sentiment" } ] }, { "slug": "google/language-v1-analyze-syntax", "model_name": "language-v1-analyze-syntax", "display_name": "language-v1-analyze-syntax", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.5" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/language-v1-analyze-syntax" } ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_understanding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/language-v1-analyze-syntax" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "language-v1-analyze-syntax" } ] }, { "slug": "google/learnlm-1.5-pro-experimental", "model_name": "learnlm-1.5-pro-experimental", "display_name": "learnlm-1.5-pro-experimental", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_input": { "unit": "per_image", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm" }, "discarded_conflicts": [ { "kind": "tier_schedule", "source": "litellm", "threshold": 128000, "inclusive": false, "message": "tier threshold 128000 exceeds model context window 32767; it was discarded." } ], "verification_status": "conflicting" }, "warnings": [ { "code": "invalid_source_tier", "source": "litellm", "message": "tier threshold 128000 exceeds model context window 32767." } ] } ], "docs_url": "https://aistudio.google.com", "max_input_tokens": 32767, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2024-01-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gemini", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "google/lyria-3-clip-preview", "model_name": "lyria-3-clip-preview", "display_name": "Lyria 3 Clip Preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_output": { "unit": "per_image", "price": "0.04" }, "request": { "unit": "per_request", "price": "0.04" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "image_output": "litellm", "request": "truefoundry" }, "verification_status": "cross_checked" } } ], "intro": "Music generation model for short 30-second clips, loops, and previews from text or image prompts", "released_at": "2026-03-25", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image" ], "output": [ "text", "audio" ] }, "family": "lyria", "capabilities": { "vision": true, "audio_output": true, "pdf_input": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing", "model_type": "music_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/lyria-3-clip-preview" ], "price_history": [ { "date": "2026-07-25", "kind": "limit", "old": "131072", "new": "1048576", "note": "max_input_tokens" }, { "date": "2026-07-25", "kind": "limit", "old": "8192", "new": "65536", "note": "max_output_tokens" } ] }, { "slug": "google/lyria-3-pro-preview", "model_name": "lyria-3-pro-preview", "display_name": "Lyria 3 Pro Preview", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "request": { "unit": "per_request", "price": "0.08" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "request": "truefoundry" }, "verification_status": "cross_checked" } } ], "intro": "Music generation model for full-length songs from text or images with vocals and structure", "released_at": "2026-03-25", "max_input_tokens": 1048576, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image" ], "output": [ "text", "audio" ] }, "family": "lyria", "capabilities": { "vision": true, "audio_output": true, "pdf_input": true }, "docs_url": "https://ai.google.dev/gemini-api/docs/pricing", "model_type": "music_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/lyria-3-pro-preview" ], "price_history": [ { "date": "2026-07-25", "kind": "limit", "old": "131072", "new": "1048576", "note": "max_input_tokens" }, { "date": "2026-07-25", "kind": "limit", "old": "8192", "new": "65536", "note": "max_output_tokens" } ] }, { "slug": "google/multimodalembedding", "model_name": "multimodalembedding", "display_name": "multimodalembedding", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "image_input": { "unit": "per_image", "price": "0.0001" }, "input_video_plus": { "unit": "per_request", "price": "0.002" }, "input_video_standard": { "unit": "per_request", "price": "0.001" }, "input_video_essential": { "unit": "per_request", "price": "0.0005" }, "prompt": { "unit": "per_M_tokens", "price": "0.025" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "image_input": "portkey", "input_video_plus": "portkey", "input_video_standard": "portkey", "input_video_essential": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.2" }, "image_input": { "unit": "per_image", "price": "0.0001" }, "audio_input": { "unit": "per_second", "price": "0.0005" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "audio_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/multimodalembedding", "region": "asia-northeast3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.2" }, "image_input": { "unit": "per_image", "price": "0.0001" }, "audio_input": { "unit": "per_second", "price": "0.0005" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "audio_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/multimodalembedding", "region": "europe-west2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.2" }, "image_input": { "unit": "per_image", "price": "0.0001" }, "audio_input": { "unit": "per_second", "price": "0.0005" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "image_input": "truefoundry", "audio_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/multimodalembedding", "region": "us-central1" } ], "capabilities": { "vision": true, "video_input": true }, "modalities": { "input": [ "text", "image", "video" ], "output": [ "embedding" ] }, "model_type": "multimodal_embedding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/multimodalembedding" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "multimodalembedding" } ] }, { "slug": "google/nano-banana-pro-preview", "model_name": "nano-banana-pro-preview", "display_name": "Nano Banana Pro", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "truefoundry+llmdb", "charges": { "image_input": { "unit": "per_image", "price": "0.0011" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry+llmdb", "charge_sources": { "image_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 65536, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "model_type": "image_generation", "capabilities": { "structured_output": true, "reasoning": true, "vision": true, "image_output": true, "prompt_caching": true }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Nano Banana Pro" } ] }, { "slug": "google/object-detector", "model_name": "object-detector", "display_name": "object-detector", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0016667" } }, "provenance": { "base_charges": { "audio_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/object-detector" } ], "modalities": { "input": [ "video" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "video_input": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/object-detector" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "object-detector" } ] }, { "slug": "google/people-blur", "model_name": "people-blur", "display_name": "people-blur", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0016666666666666668" } }, "provenance": { "base_charges": { "audio_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/people-blur" } ], "deprecated": true, "modalities": { "input": [ "video" ], "output": [ "video" ] }, "model_type": "vision_understanding", "capabilities": { "video_input": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/people-blur" ], "price_history": [ { "date": "2026-08-01", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-03", "kind": "listed", "note": "people-blur" } ] }, { "slug": "google/ppe-detector", "model_name": "ppe-detector", "display_name": "ppe-detector", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.00166667" } }, "provenance": { "base_charges": { "audio_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/ppe-detector" } ], "deprecated": true, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "video_input": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/ppe-detector" ], "price_history": [ { "date": "2026-08-01", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-03", "kind": "listed", "note": "ppe-detector" } ] }, { "slug": "google/product-recognizer", "model_name": "product-recognizer", "display_name": "product-recognizer", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.000025" } }, "provenance": { "base_charges": { "image_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/product-recognizer" } ], "deprecated": true, "modalities": { "input": [ "image" ], "output": [ "text" ] }, "model_type": "image_generation", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/product-recognizer" ], "price_history": [ { "date": "2026-08-01", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-03", "kind": "listed", "note": "product-recognizer" } ] }, { "slug": "google/tag-recognizer", "model_name": "tag-recognizer", "display_name": "tag-recognizer", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.000025" } }, "provenance": { "base_charges": { "image_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/tag-recognizer" } ], "deprecated": true, "modalities": { "input": [ "image" ], "output": [ "text" ] }, "model_type": "image_generation", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/tag-recognizer" ], "price_history": [ { "date": "2026-08-01", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-03", "kind": "listed", "note": "tag-recognizer" } ] }, { "slug": "google/text-bison", "model_name": "text-bison", "display_name": "text-bison", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 2048, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "text-bison" } ] }, { "slug": "google/text-bison@001", "model_name": "text-bison@001", "display_name": "text-bison@001", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 1024, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "text-bison@001" } ] }, { "slug": "google/text-bison@002", "model_name": "text-bison@002", "display_name": "text-bison@002", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.25" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 1024, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "text-bison@002" } ] }, { "slug": "google/text-detector", "model_name": "text-detector", "display_name": "text-detector", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.0015" } }, "provenance": { "base_charges": { "image_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-detector" } ], "modalities": { "input": [ "image", "pdf" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "vision": true, "pdf_input": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/text-detector" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "text-detector" } ] }, { "slug": "google/text-embedding-005", "model_name": "text-embedding-005", "display_name": "Text Embedding 005", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.025" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "global" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-central1" } ], "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true }, "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2024-08-01", "max_input_tokens": 8192, "max_output_tokens": 1536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "text-embedding", "model_type": "text_embedding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/text-embedding-005" ], "intro_i18n": { "zh-CN": "一款专注于英文任务的文本嵌入模型，针对代码和英文任务进行了优化。", "zh-TW": "一款專注於英文的文字嵌入模型，針對程式與英文任務進行最佳化。", "ja-JP": "コードおよび英語タスクに最適化された英語中心のテキスト埋め込みモデルです。", "ru-RU": "Модель встраивания текста, ориентированная на английский язык, оптимизирована для задач на английском и программировании." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Text Embedding 005" } ] }, { "slug": "google/text-multilingual-embedding-002", "model_name": "text-multilingual-embedding-002", "display_name": "Text Multilingual Embedding 002", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.025" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "asia-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "asia-east2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "asia-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "asia-northeast3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "asia-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "asia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "australia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "eu" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "europe-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "europe-north1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "europe-southwest1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "europe-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "europe-west2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "europe-west3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "europe-west4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "europe-west6" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "europe-west8" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "europe-west9" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "global" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "me-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "me-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "me-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "northamerica-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "southamerica-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "us" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "us-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "us-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "us-east4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "us-east5" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "us-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "us-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-multilingual-embedding-002", "region": "us-west4" } ], "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true }, "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2024-03-01", "max_input_tokens": 8192, "max_output_tokens": 1536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "text-embedding", "model_type": "text_embedding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/text-multilingual-embedding-002" ], "intro_i18n": { "zh-CN": "一款多语言文本嵌入模型，针对跨语言任务进行了优化，支持多种语言。", "zh-TW": "一款多語言文字嵌入模型，針對跨語言任務進行最佳化，支援多種語言。", "ja-JP": "多言語間タスクに最適化された多言語テキスト埋め込みモデルです。", "ru-RU": "Многоязычная модель встраивания текста, оптимизированная для кросс-языковых задач на множестве языков." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Text Multilingual Embedding 002" } ] }, { "slug": "google/text-translation", "model_name": "text-translation", "display_name": "text-translation", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "20" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/text-translation" } ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_understanding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/text-translation" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "text-translation" } ] }, { "slug": "google/textembedding-gecko", "model_name": "textembedding-gecko", "display_name": "textembedding-gecko", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.025" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.2" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "model_type": "text_embedding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "textembedding-gecko" } ] }, { "slug": "google/textembedding-gecko-multilingual", "model_name": "textembedding-gecko-multilingual", "display_name": "textembedding-gecko-multilingual", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "model_type": "text_embedding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "textembedding-gecko-multilingual" } ] }, { "slug": "google/textembedding-gecko-multilingual@001", "model_name": "textembedding-gecko-multilingual@001", "display_name": "textembedding-gecko-multilingual@001", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "model_type": "text_embedding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "textembedding-gecko-multilingual@001" } ] }, { "slug": "google/textembedding-gecko@001", "model_name": "textembedding-gecko@001", "display_name": "textembedding-gecko@001", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "model_type": "text_embedding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "textembedding-gecko@001" } ] }, { "slug": "google/textembedding-gecko@003", "model_name": "textembedding-gecko@003", "display_name": "textembedding-gecko@003", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry+portkey", "charges": { "speech_input": { "unit": "per_M_characters", "price": "0.025" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "speech_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.025" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.2" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "model_type": "text_embedding", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "textembedding-gecko@003" } ] }, { "slug": "google/translate-llm", "model_name": "translate-llm", "display_name": "translate-llm", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "10" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/translate-llm" } ], "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/translate-llm" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "translate-llm" } ] }, { "slug": "google/veo-2.0-generate-001", "model_name": "veo-2.0-generate-001", "display_name": "Veo 2", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "truefoundry+llmdb", "charges": { "audio_output": { "unit": "per_second", "price": "0.35" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "audio_output": "truefoundry", "web_search": "llmdb" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "video_output": { "unit": "per_second", "price": "0.5" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "australia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-north1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-southwest1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west6" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west8" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west9" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "global" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "northamerica-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "southamerica-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east5" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west4" } ], "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "model_type": "video_generation", "capabilities": { "vision": true }, "max_input_tokens": 480, "max_output_tokens": 8192, "deprecated": true, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "price_history": [ { "date": "2026-07-07", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-03", "kind": "listed", "note": "Veo 2" } ] }, { "slug": "google/veo-2.0-generate-001-gt-128k", "model_name": "veo-2.0-generate-001-gt-128k", "display_name": "veo-2.0-generate-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output": { "unit": "per_second", "price": "0.35" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "veo-2.0-generate-001-gt-128k" } ] }, { "slug": "google/veo-2.0-generate-001-lte-128k", "model_name": "veo-2.0-generate-001-lte-128k", "display_name": "veo-2.0-generate-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output": { "unit": "per_second", "price": "0.35" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "veo-2.0-generate-001-lte-128k" } ] }, { "slug": "google/veo-3.0-fast-generate-001", "model_name": "veo-3.0-fast-generate-001", "display_name": "Veo 3 fast", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "truefoundry+llmdb", "charges": { "audio_output": { "unit": "per_second", "price": "0.15" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "audio_output": "truefoundry", "web_search": "llmdb" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "video_output": { "unit": "per_second", "price": "0.1" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.15" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/veo-3.0-fast-generate-001", "region": "global" } ], "modalities": { "input": [ "text", "image" ], "output": [ "video", "audio" ] }, "model_type": "video_generation", "capabilities": { "vision": true, "audio_output": true }, "max_input_tokens": 480, "max_output_tokens": 8192, "intro": "Video model for prompt-guided generation, editing, and motion workflows", "released_at": "2025-07-31", "family": "veo", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/veo-3.0-fast-generate-001" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Veo 3 fast" } ] }, { "slug": "google/veo-3.0-fast-generate-001-gt-128k", "model_name": "veo-3.0-fast-generate-001-gt-128k", "display_name": "veo-3.0-fast-generate-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output": { "unit": "per_second", "price": "0.15" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "veo-3.0-fast-generate-001-gt-128k" } ] }, { "slug": "google/veo-3.0-fast-generate-001-lte-128k", "model_name": "veo-3.0-fast-generate-001-lte-128k", "display_name": "veo-3.0-fast-generate-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output": { "unit": "per_second", "price": "0.15" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "veo-3.0-fast-generate-001-lte-128k" } ] }, { "slug": "google/veo-3.0-generate-001", "model_name": "veo-3.0-generate-001", "display_name": "Veo 3", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "truefoundry+llmdb", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" }, "web_search": { "unit": "per_k_calls", "price": "35" } }, "provenance": { "base_charges": { "audio_output": "truefoundry", "web_search": "llmdb" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "video_output": { "unit": "per_second", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-east2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-northeast3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "asia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "australia-southeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-north1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-southwest1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west3" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west6" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west8" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "europe-west9" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "global" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-central2" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "me-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "northamerica-northeast1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "southamerica-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-central1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east4" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-east5" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-south1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west1" }, { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.4" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "region": "us-west4" } ], "modalities": { "input": [ "text", "image" ], "output": [ "video", "audio" ] }, "model_type": "video_generation", "capabilities": { "vision": true, "audio_output": true }, "max_input_tokens": 480, "max_output_tokens": 8192, "intro": "Video model for prompt-guided generation, editing, and motion workflows", "released_at": "2025-05-20", "family": "veo", "deprecated": true, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/veo-3.0-generate-001" ], "price_history": [ { "date": "2026-07-07", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-03", "kind": "listed", "note": "Veo 3" } ] }, { "slug": "google/veo-3.0-generate-001-gt-128k", "model_name": "veo-3.0-generate-001-gt-128k", "display_name": "veo-3.0-generate-001-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output": { "unit": "per_second", "price": "0.4" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "veo-3.0-generate-001-gt-128k" } ] }, { "slug": "google/veo-3.0-generate-001-lte-128k", "model_name": "veo-3.0-generate-001-lte-128k", "display_name": "veo-3.0-generate-001-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output": { "unit": "per_second", "price": "0.4" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "veo-3.0-generate-001-lte-128k" } ] }, { "slug": "google/veo-3.1-fast-generate-001", "model_name": "veo-3.1-fast-generate-001", "display_name": "Veo 3.1 Fast Generate", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "video_output": { "unit": "per_second", "price": "0.15" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "capabilities": {}, "intro": "Video model for prompt-guided generation, editing, and motion workflows", "released_at": "2025-10-15", "max_input_tokens": 0, "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "family": "veo", "model_type": "video_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/veo-3.1-fast-generate-001" ], "price_history": [ { "date": "2026-07-07", "kind": "capability", "note": "vision: true→false" }, { "date": "2026-07-03", "kind": "listed", "note": "Veo 3.1 Fast Generate" } ] }, { "slug": "google/veo-3.1-fast-generate-preview", "model_name": "veo-3.1-fast-generate-preview", "display_name": "Veo 3.1 fast", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "video_output": { "unit": "per_second", "price": "0.35" } }, "provenance": { "base_charges": { "web_search": "llmdb", "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "video_output_720p": { "unit": "per_second", "price": "0.1" }, "video_output_1080p": { "unit": "per_second", "price": "0.12" }, "video_output_4k": { "unit": "per_second", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output_720p": "portkey", "video_output_1080p": "portkey", "video_output_4k": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "intro": "Video model for prompt-guided generation, editing, and motion workflows", "released_at": "2025-10-15", "max_input_tokens": 480, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "family": "veo", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "video_input": true, "pdf_input": true }, "model_type": "video_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "我们最新的视频生成模型，供Gemini API付费用户使用。", "zh-TW": "我們最新的影像生成模型，供Gemini API付費層的開發者使用。", "ja-JP": "Gemini APIの有料ティアで開発者が利用可能な最新のビデオ生成モデル。", "ru-RU": "Наша последняя модель генерации видео, доступная разработчикам на платной основе через API Gemini." }, "price_history": [ { "date": "2026-07-25", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-25", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-25", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Veo 3.1 fast" } ] }, { "slug": "google/veo-3.1-fast-generate-preview-gt-128k", "model_name": "veo-3.1-fast-generate-preview-gt-128k", "display_name": "veo-3.1-fast-generate-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output_720p": { "unit": "per_second", "price": "0.1" }, "video_output_1080p": { "unit": "per_second", "price": "0.12" }, "video_output_4k": { "unit": "per_second", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output_720p": "portkey", "video_output_1080p": "portkey", "video_output_4k": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "veo-3.1-fast-generate-preview-gt-128k" } ] }, { "slug": "google/veo-3.1-fast-generate-preview-lte-128k", "model_name": "veo-3.1-fast-generate-preview-lte-128k", "display_name": "veo-3.1-fast-generate-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output_720p": { "unit": "per_second", "price": "0.1" }, "video_output_1080p": { "unit": "per_second", "price": "0.12" }, "video_output_4k": { "unit": "per_second", "price": "0.3" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output_720p": "portkey", "video_output_1080p": "portkey", "video_output_4k": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "veo-3.1-fast-generate-preview-lte-128k" } ] }, { "slug": "google/veo-3.1-generate-001", "model_name": "veo-3.1-generate-001", "display_name": "Veo 3.1", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "video_output": { "unit": "per_second", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "capabilities": {}, "intro": "Video model for prompt-guided generation, editing, and motion workflows", "released_at": "2025-10-15", "max_input_tokens": 0, "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "video" ] }, "family": "veo", "model_type": "video_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/veo-3.1-generate-001" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Veo 3.1" } ] }, { "slug": "google/veo-3.1-generate-preview", "model_name": "veo-3.1-generate-preview", "display_name": "Veo 3.1", "vendor": "google", "pricing": [ { "provider": "google", "provider_name": "Google", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "web_search": { "unit": "per_k_calls", "price": "35" }, "video_output": { "unit": "per_second", "price": "0.6" } }, "provenance": { "base_charges": { "web_search": "llmdb", "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } }, { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "video_output_720p": { "unit": "per_second", "price": "0.4" }, "video_output_1080p": { "unit": "per_second", "price": "0.4" }, "video_output_4k": { "unit": "per_second", "price": "0.6" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output_720p": "portkey", "video_output_1080p": "portkey", "video_output_4k": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "intro": "Video model for prompt-guided generation, editing, and motion workflows", "released_at": "2025-10-15", "max_input_tokens": 480, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "family": "veo", "status": "beta", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "pdf_input": true }, "model_type": "video_generation", "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "intro_i18n": { "zh-CN": "我们最新的视频生成模型，供Gemini API付费用户使用。", "zh-TW": "我們最新的影像生成模型，供Gemini API付費層的開發者使用。", "ja-JP": "Gemini APIの有料ティアで開発者が利用可能な最新のビデオ生成モデル。", "ru-RU": "Наша последняя модель генерации видео, доступная разработчикам на платной основе через API Gemini." }, "price_history": [ { "date": "2026-07-25", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-25", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Veo 3.1" } ] }, { "slug": "google/veo-3.1-generate-preview-gt-128k", "model_name": "veo-3.1-generate-preview-gt-128k", "display_name": "veo-3.1-generate-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output_720p": { "unit": "per_second", "price": "0.4" }, "video_output_1080p": { "unit": "per_second", "price": "0.4" }, "video_output_4k": { "unit": "per_second", "price": "0.6" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output_720p": "portkey", "video_output_1080p": "portkey", "video_output_4k": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "veo-3.1-generate-preview-gt-128k" } ] }, { "slug": "google/veo-3.1-generate-preview-lte-128k", "model_name": "veo-3.1-generate-preview-lte-128k", "display_name": "veo-3.1-generate-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output_720p": { "unit": "per_second", "price": "0.4" }, "video_output_1080p": { "unit": "per_second", "price": "0.4" }, "video_output_4k": { "unit": "per_second", "price": "0.6" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output_720p": "portkey", "video_output_1080p": "portkey", "video_output_4k": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "veo-3.1-generate-preview-lte-128k" } ] }, { "slug": "google/veo-3.1-lite-generate-preview", "model_name": "veo-3.1-lite-generate-preview", "display_name": "Veo 3.1 lite", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "portkey", "charges": { "video_output_720p": { "unit": "per_second", "price": "0.05" }, "video_output_1080p": { "unit": "per_second", "price": "0.08" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output_720p": "portkey", "video_output_1080p": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "intro": "Video model for prompt-guided generation, editing, and motion workflows", "released_at": "2026-03-31", "max_input_tokens": 480, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "family": "veo", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "pdf_input": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-27", "kind": "listed", "note": "Veo 3.1 lite" } ] }, { "slug": "google/veo-3.1-lite-generate-preview-gt-128k", "model_name": "veo-3.1-lite-generate-preview-gt-128k", "display_name": "veo-3.1-lite-generate-preview-gt-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output_720p": { "unit": "per_second", "price": "0.05" }, "video_output_1080p": { "unit": "per_second", "price": "0.08" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output_720p": "portkey", "video_output_1080p": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-27", "kind": "listed", "note": "veo-3.1-lite-generate-preview-gt-128k" } ] }, { "slug": "google/veo-3.1-lite-generate-preview-lte-128k", "model_name": "veo-3.1-lite-generate-preview-lte-128k", "display_name": "veo-3.1-lite-generate-preview-lte-128k", "vendor": "google", "pricing": [ { "provider": "google", "official": true, "source": "portkey", "charges": { "video_output_720p": { "unit": "per_second", "price": "0.05" }, "video_output_1080p": { "unit": "per_second", "price": "0.08" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "video_output_720p": "portkey", "video_output_1080p": "portkey", "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "model_type": "video_generation", "price_history": [ { "date": "2026-07-27", "kind": "listed", "note": "veo-3.1-lite-generate-preview-lte-128k" } ] }, { "slug": "google/video-speech-transcription", "model_name": "video-speech-transcription", "display_name": "video-speech-transcription", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0008" } }, "provenance": { "base_charges": { "audio_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/video-speech-transcription" } ], "modalities": { "input": [ "video", "audio" ], "output": [ "text" ] }, "model_type": "speech_recognition", "capabilities": { "audio_input": true, "video_input": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/video-speech-transcription" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "video-speech-transcription" } ] }, { "slug": "google/video-text-detection", "model_name": "video-text-detection", "display_name": "video-text-detection", "vendor": "google", "pricing": [ { "provider": "google-vertex", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0025" } }, "provenance": { "base_charges": { "audio_input": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "google/video-text-detection" } ], "modalities": { "input": [ "video" ], "output": [ "text" ] }, "model_type": "video_generation", "capabilities": { "video_input": true }, "endpoints": { "inbound": [ "google-gemini", "openai-compatible" ], "outbound": [ "google-gemini" ] }, "aliases": [ "google/video-text-detection" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "video-text-detection" } ] }, { "slug": "inception/mercury", "model_name": "mercury", "display_name": "Mercury", "vendor": "inception", "pricing": [ { "provider": "inception", "provider_name": "Inception", "official": true, "source": "llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.25" }, "cache_write": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb", "cache_read": "llmdb", "cache_write": "llmdb" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-06-26", "knowledge_cutoff": "2023-10", "max_input_tokens": 128000, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "mercury", "capabilities": { "function_calling": true, "prompt_caching": true, "stream": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "inception/mercury" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Mercury" } ] }, { "slug": "inception/mercury-2", "model_name": "mercury-2", "display_name": "Mercury 2", "vendor": "inception", "pricing": [ { "provider": "inception", "provider_name": "Inception", "official": true, "source": "models-dev+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.75" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "released_at": "2026-02-24", "knowledge_cutoff": "2025-01", "max_input_tokens": 128000, "max_output_tokens": 50000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mercury", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "stream": true }, "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 21.9, "coding_index": 31.1, "agentic_index": 9.5 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "response_format", "stop", "structured_outputs", "temperature", "tool_choice", "tools" ], "defaults": { "temperature": 0.75 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "inception/mercury-2" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "inception/mercury-coder", "model_name": "mercury-coder", "display_name": "Mercury Coder", "vendor": "inception", "pricing": [ { "provider": "inception", "provider_name": "Inception", "official": true, "source": "llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.25" }, "cache_write": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb", "cache_read": "llmdb", "cache_write": "llmdb" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-02-26", "knowledge_cutoff": "2023-10", "max_input_tokens": 128000, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "family": "mercury", "capabilities": { "function_calling": true, "prompt_caching": true, "stream": true, "structured_output": true }, "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "inception/mercury-coder" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Mercury Coder" } ] }, { "slug": "inception/mercury-edit", "model_name": "mercury-edit", "display_name": "Mercury Edit", "vendor": "inception", "pricing": [ { "provider": "inception", "provider_name": "Inception", "official": true, "source": "llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.75" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "llmdb", "completion": "llmdb", "cache_read": "llmdb" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-02-24", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "capabilities": { "reasoning": true, "prompt_caching": true, "stream": true }, "knowledge_cutoff": "2025-01", "family": "mercury", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "inception/mercury-edit" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Mercury Edit" } ] }, { "slug": "inception/mercury-edit-2", "model_name": "mercury-edit-2", "display_name": "Mercury Edit 2", "vendor": "inception", "pricing": [ { "provider": "inception", "provider_name": "Inception", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.75" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Reasoning model for deliberate analysis, multi-step problem solving, and tool use", "released_at": "2026-03-30", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "reasoning": true, "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation" }, { "slug": "jina/jina-deepsearch-v1", "model_name": "jina-deepsearch-v1", "display_name": "Jina DeepSearch v1", "vendor": "jina", "pricing": [ { "provider": "jina", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.02" }, "completion": { "unit": "per_M_tokens", "price": "0.02" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 1000000, "model_type": "vision_understanding", "capabilities": { "reasoning": true, "web_search": true, "vision": true, "pdf_input": true }, "modalities": { "input": [ "image", "text" ], "output": [] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "DeepSearch 结合了网页搜索、阅读与推理，适用于深入研究任务。它就像一个智能代理，接收你的研究任务后，进行多轮广泛搜索，最终才生成答案。整个过程包含持续的信息检索、逻辑推理和多角度问题解决，区别于仅依赖预训练数据的传统大模型或一次性检索的RAG系统。", "zh-TW": "DeepSearch 結合網頁搜尋、閱讀與推理，進行深入調查。它如同一位代理人，接收你的研究任務後，進行多輪廣泛搜尋，最終才產出答案。整個過程包含持續研究、推理與多角度問題解決，與僅依賴預訓練資料的標準 LLM 或一次性檢索的傳統 RAG 系統截然不同。", "ja-JP": "DeepSearch は、ウェブ検索、読解、推論を組み合わせて徹底的な調査を行うエージェントのようなモデルです。調査タスクを受け取り、複数回の広範な検索を行った後に回答を生成します。継続的な調査と多角的な問題解決を行う点で、従来の LLM や一度きりの検索に依存する RAG システムとは根本的に異なります。", "ru-RU": "DeepSearch объединяет веб-поиск, чтение и логический анализ для глубокого исследования. Представьте себе агента, который берет вашу исследовательскую задачу, проводит многократный поиск, анализирует и только потом выдает ответ. Этот процесс включает непрерывное исследование, логическое мышление и многогранное решение задач, что принципиально отличается от стандартных LLM, отвечающих на основе предобученных данных или традиционных RAG-систем с одноразовым поиском." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Jina DeepSearch v1" } ] }, { "slug": "longcat/longcat-2.0:thinking", "model_name": "longcat-2.0:thinking", "display_name": "LongCat-2.0", "vendor": "longcat", "pricing": [ { "provider": "longcat", "provider_name": "LongCat", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.75" }, "completion": { "unit": "per_M_tokens", "price": "2.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.015" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "cross_checked" }, "provider_model_id": "LongCat-2.0" } ], "intro": "Meituan LongCat-2.0, a reasoning model with tool calling and a 1M-token context window", "released_at": "2026-06-30", "max_input_tokens": 1000000, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "longcat", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true }, "model_type": "deep_thinking", "deprecated": true, "status": "deprecated", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "LongCat-2.0", "longcat-2.0", "longcat-2.0-free", "meituan-longcat/LongCat-2.0", "meituan-longcat/longcat-2.0", "meituan/longcat-2.0" ], "intro_i18n": { "zh-CN": "LongCat-2.0 是美团推出的 1600B MoE 语言模型，专为代理开发场景设计。它原生支持工具调用、多步推理和长上下文任务，在代码生成、自动化工作流和复杂指令执行方面表现出色。深度集成了包括 Claude Code、OpenClaw、OpenCode 和 Kilo Code 在内的生产力工具。", "zh-TW": "LongCat-2.0 是美團設計的 1600B MoE 語言模型，專為代理開發場景而設計。它原生支持工具調用、多步推理和長上下文任務，在代碼生成、自動化工作流和複雜指令執行方面表現出色。它深度集成了包括 Claude Code、OpenClaw、OpenCode 和 Kilo Code 在內的生產力工具。", "ja-JP": "LongCat-2.0は、Meituanがエージェント開発シナリオ向けに設計した1600B MoE言語モデルです。ツール呼び出し、マルチステップ推論、長コンテキストタスクをネイティブでサポートし、コード生成、自動化ワークフロー、複雑な指示実行において優れた性能を発揮します。Claude Code、OpenClaw、OpenCode、Kilo Codeなどの生産性ツールと深く統合されています。", "ru-RU": "LongCat-2.0 — это языковая модель MoE с 1600 млрд параметров от Meituan, разработанная для сценариев разработки агентов. Она изначально поддерживает вызов инструментов, многошаговое рассуждение и задачи с длинным контекстом, демонстрируя высокую производительность в генерации кода, автоматизации рабочих процессов и выполнении сложных инструкций. Модель глубоко интегрирована с инструментами повышения производительности, включая Claude Code, OpenClaw, OpenCode и Kilo Code." }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-22", "kind": "listed", "note": "LongCat-2.0" } ] }, { "slug": "meta/cerebras-llama-4-maverick-17b-128e-instruct", "model_name": "cerebras-llama-4-maverick-17b-128e-instruct", "display_name": "Cerebras-Llama-4-Maverick-17B-128E-Instruct", "vendor": "meta", "pricing": [ { "provider": "llama", "provider_name": "Llama", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Open multimodal Llama model for strong reasoning and fast responses", "released_at": "2025-04-05", "knowledge_cutoff": "2025-01", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "llama", "capabilities": { "function_calling": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation" }, { "slug": "meta/cerebras-llama-4-scout-17b-16e-instruct", "model_name": "cerebras-llama-4-scout-17b-16e-instruct", "display_name": "Cerebras-Llama-4-Scout-17B-16E-Instruct", "vendor": "meta", "pricing": [ { "provider": "llama", "provider_name": "Llama", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Open multimodal Llama model for long-context analysis and efficient agents", "released_at": "2025-04-05", "knowledge_cutoff": "2025-01", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "llama", "capabilities": { "function_calling": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation" }, { "slug": "meta/groq-llama-4-maverick-17b-128e-instruct", "model_name": "groq-llama-4-maverick-17b-128e-instruct", "display_name": "Groq-Llama-4-Maverick-17B-128E-Instruct", "vendor": "meta", "pricing": [ { "provider": "llama", "provider_name": "Llama", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Open multimodal Llama model for strong reasoning and fast responses", "released_at": "2025-04-05", "knowledge_cutoff": "2025-01", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "llama", "capabilities": { "function_calling": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation" }, { "slug": "meta/llama-3.3-70b-instruct", "model_name": "llama-3.3-70b-instruct", "display_name": "Llama-3.3-70B-Instruct", "vendor": "meta", "pricing": [ { "provider": "llama", "provider_name": "Llama", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding", "released_at": "2024-12-06", "knowledge_cutoff": "2023-12", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "llama", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://nebius.com/prices-ai-studio", "model_type": "text_generation", "deprecated": true, "benchmarks": { "intelligence_index": null, "coding_index": 11.9, "agentic_index": null }, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Llama-3.3-70B-Instruct", "deepinfra/meta-llama/Llama-3.3-70B-Instruct", "hf:meta-llama/Llama-3.3-70B-Instruct", "llama-3-3-70b-instruct", "llama-3.3-70b-instruct:free", "meta-llama/Llama-3.3-70B-Instruct", "meta-llama/llama-3-3-70b-instruct", "meta-llama/llama-3.3-70b-instruct", "meta-llama/llama-3.3-70b-instruct:free", "meta/llama-3.3-70b-instruct", "nebius/meta-llama/Llama-3.3-70B-Instruct", "novita/meta-llama/llama-3.3-70b-instruct" ], "intro_i18n": { "zh-CN": "Llama 3.3 是最先进的多语言开源 Llama 模型，以极低成本实现接近 405B 的性能。基于 Transformer 架构，结合 SFT 与 RLHF 提升实用性与安全性。指令微调版本针对多语言对话优化，在行业基准测试中超越众多开源与闭源模型。知识截止时间：2023 年 12 月。", "zh-TW": "Llama 3.3 是最先進的多語言開源 Llama 模型，以極低成本提供接近 405B 的效能。基於 Transformer 架構，並透過 SFT 與 RLHF 提升實用性與安全性。指令微調版本針對多語言對話進行優化，在業界基準測試中超越多數開源與封閉模型。知識截止時間：2023 年 12 月。", "ja-JP": "Llama 3.3は最も高度な多言語対応のオープンソースLlamaモデルで、非常に低コストで405Bに近い性能を提供します。Transformerベースで、SFTとRLHFにより有用性と安全性が向上。命令調整版は多言語チャットに最適化され、業界ベンチマークで多くのオープン・クローズドチャットモデルを上回ります。知識カットオフ：2023年12月。", "ru-RU": "Llama 3.3 — самая продвинутая многоязычная модель Llama с открытым исходным кодом, обеспечивающая производительность, близкую к 405B, при очень низкой стоимости. Основана на архитектуре Transformer и улучшена с помощью SFT и RLHF для повышения полезности и безопасности. Вариант, настроенный на инструкции, оптимизирован для многоязычного чата и превосходит многие открытые и закрытые модели в отраслевых бенчмарках. Дата отсечения знаний: декабрь 2023." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "meta/llama-3.3-8b-instruct", "model_name": "llama-3.3-8b-instruct", "display_name": "Llama-3.3-8B-Instruct", "vendor": "meta", "pricing": [ { "provider": "llama", "provider_name": "Llama", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding", "released_at": "2024-12-06", "knowledge_cutoff": "2023-12", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "llama", "capabilities": { "function_calling": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation" }, { "slug": "meta/llama-4-maverick-17b-128e-instruct-fp8", "model_name": "llama-4-maverick-17b-128e-instruct-fp8", "display_name": "Llama-4-Maverick-17B-128E-Instruct-FP8", "vendor": "meta", "pricing": [ { "provider": "llama", "provider_name": "Llama", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Open multimodal Llama model for strong reasoning and fast responses", "released_at": "2025-04-05", "knowledge_cutoff": "2024-08", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "llama", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "parallel_function_calling": true, "stream": true }, "model_type": "vision_understanding", "docs_url": "https://azure.microsoft.com/en-us/blog/introducing-the-llama-4-herd-in-azure-ai-foundry-and-azure-databricks/", "parameters": { "supported": [ "frequency_penalty", "functions", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Llama-4-Maverick-17B-128E-Instruct-FP8", "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "hf:meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "meta-llama/llama-4-maverick-17b-128e-instruct-fp8", "novita/meta-llama/llama-4-maverick-17b-128e-instruct-fp8" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "meta/llama-4-scout-17b-16e-instruct-fp8", "model_name": "llama-4-scout-17b-16e-instruct-fp8", "display_name": "Llama-4-Scout-17B-16E-Instruct-FP8", "vendor": "meta", "pricing": [ { "provider": "llama", "provider_name": "Llama", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Open multimodal Llama model for long-context analysis and efficient agents", "released_at": "2025-04-05", "knowledge_cutoff": "2024-08", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "llama", "capabilities": { "vision": true, "function_calling": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "vision_understanding" }, { "slug": "meta/muse-spark-1.1", "model_name": "muse-spark-1.1", "display_name": "Muse Spark 1.1", "vendor": "meta", "pricing": [ { "provider": "meta", "provider_name": "Meta", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "4.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.", "released_at": "2026-04-08", "max_input_tokens": 1000000, "max_output_tokens": 32000, "modalities": { "input": [ "text", "image", "pdf", "video" ], "output": [ "text" ] }, "family": "muse", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true }, "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 53.2, "coding_index": 71.3, "agentic_index": 39.7 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "meta/muse-spark-1.1", "muse-spark-1-1" ], "price_history": [ { "date": "2026-07-16", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-09", "kind": "listed", "note": "Muse Spark 1.1" } ] }, { "slug": "meta/muse-spark-1.2", "model_name": "muse-spark-1.2", "display_name": "Muse Spark 1.2", "vendor": "meta", "pricing": [ { "provider": "meta", "provider_name": "Meta", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "4.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.", "released_at": "2026-08-05", "max_input_tokens": 1048576, "max_output_tokens": 131072, "modalities": { "input": [ "text", "image", "video", "pdf", "audio" ], "output": [ "text" ] }, "family": "muse", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true }, "model_type": "deep_thinking", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "meta/muse-spark-1.2", "muse-spark-1-2" ], "price_history": [ { "date": "2026-08-06", "kind": "limit", "old": "1048576", "new": "131072", "note": "max_output_tokens" }, { "date": "2026-08-05", "kind": "listed", "note": "Muse Spark 1.2" } ] }, { "slug": "meta/muse-spark-1.2-contributor", "model_name": "muse-spark-1.2-contributor", "display_name": "Muse Spark 1.2 Contributor", "vendor": "meta", "pricing": [ { "provider": "meta", "provider_name": "Meta", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.002" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.", "released_at": "2026-08-05", "max_input_tokens": 1048576, "max_output_tokens": 131072, "modalities": { "input": [ "text", "image", "video", "pdf", "audio" ], "output": [ "text" ] }, "family": "muse", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "meta/muse-spark-1.2-contributor", "muse-spark-1-2-contributor" ], "price_history": [ { "date": "2026-08-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-08-06", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-08-06", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-08-06", "kind": "limit", "old": "1048576", "new": "131072", "note": "max_output_tokens" }, { "date": "2026-08-05", "kind": "listed", "note": "Muse Spark 1.2 Contributor" } ] }, { "slug": "minimax/image-01", "model_name": "image-01", "display_name": "Image 01", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.003676" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-02-28", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "一款全新图像生成模型，细节表现出色，支持文本生成图像与图像转图像。", "zh-TW": "一款全新圖像生成模型，具備精細細節，支援文字轉圖像與圖像轉圖像功能。", "ja-JP": "細部まで表現可能な新しい画像生成モデルで、テキストから画像、画像から画像の生成に対応しています。", "ru-RU": "Новая модель генерации изображений с высокой детализацией, поддерживает генерацию по тексту и по изображению." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Image 01" } ] }, { "slug": "minimax/image-01-live", "model_name": "image-01-live", "display_name": "Image 01 Live", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.003676" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-02-28", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "一款细节精致的图像生成模型，支持文本生成图像与可控风格预设。", "zh-TW": "一款具備精細細節的圖像生成模型，支援文字轉圖像與可控風格預設。", "ja-JP": "細部まで表現可能な画像生成モデルで、テキストから画像生成およびスタイルの制御プリセットに対応しています。", "ru-RU": "Модель генерации изображений с высокой детализацией, поддерживает генерацию по тексту и управляемые стили." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Image 01 Live" } ] }, { "slug": "minimax/M2-her", "model_name": "M2-her", "display_name": "MiniMax M2-her", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.308824" }, "completion": { "unit": "per_M_tokens", "price": "1.235294" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-01-23", "max_input_tokens": 65536, "max_output_tokens": 2048, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true }, "intro": "MiniMax M2 variant tuned for conversational and character-driven agent interactions", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "minimax", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "minimax/m2-her" ], "intro_i18n": { "zh-CN": "一个专为角色扮演和多轮对话设计的文本对话模型，支持角色定制和情感表达。", "zh-TW": "一款專為角色扮演和多輪對話設計的文本對話模型，支持角色定制和情感表達。", "ja-JP": "ロールプレイやマルチターン会話のために設計されたテキスト対話モデルで、キャラクターのカスタマイズや感情表現が可能です。", "ru-RU": "Модель текстового диалога, разработанная для ролевых игр и многоходовых разговоров, с возможностью настройки персонажей и выражения эмоций." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-08-10", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-08-10", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "MiniMax M2-her" } ] }, { "slug": "minimax/MiniMax-Hailuo-02", "model_name": "MiniMax-Hailuo-02", "display_name": "MiniMax Hailuo 02", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_request", "price": "0.088235" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-06-18", "model_type": "video_generation", "capabilities": { "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "minimax-hailuo-02" ], "intro_i18n": { "zh-CN": "下一代视频生成模型MiniMax Hailuo 02正式发布，支持1080P分辨率和10秒视频生成。", "zh-TW": "下一代影像生成模型MiniMax Hailuo 02正式發布，支持1080P解析度及10秒影像生成。", "ja-JP": "次世代ビデオ生成モデル「MiniMax Hailuo 02」が正式リリースされ、1080P解像度と10秒間のビデオ生成をサポート。", "ru-RU": "Модель генерации видео следующего поколения MiniMax Hailuo 02 официально выпущена, поддерживает разрешение 1080P и генерацию видео длиной до 10 секунд." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "MiniMax Hailuo 02" } ] }, { "slug": "minimax/MiniMax-Hailuo-2.3", "model_name": "MiniMax-Hailuo-2.3", "display_name": "MiniMax Hailuo 2.3", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_request", "price": "0.294118" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-10-28", "model_type": "video_generation", "capabilities": { "video_input": true, "pdf_input": true, "prompt_caching": true }, "modalities": { "input": [ "video" ], "output": [ "video" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "minimax-hailuo-2.3" ], "intro_i18n": { "zh-CN": "全新视频生成模型，在身体动作、物理真实感和指令遵循性方面全面升级。", "zh-TW": "全新影像生成模型，全面升級身體動作、物理真實性及指令遵循性。", "ja-JP": "身体動作、物理的リアリズム、指示追従性において全面的にアップグレードされた新しいビデオ生成モデル。", "ru-RU": "Совершенно новая модель генерации видео с комплексными улучшениями в движении тела, физическом реализме и следовании инструкциям." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "MiniMax Hailuo 2.3" } ] }, { "slug": "minimax/MiniMax-Hailuo-2.3-Fast", "model_name": "MiniMax-Hailuo-2.3-Fast", "display_name": "MiniMax Hailuo 2.3 Fast", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_request", "price": "0.198529" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-10-28", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "全新视频生成模型，在身体动作、物理真实感和指令遵循性方面全面升级。", "zh-TW": "全新影像生成模型，全面升級身體動作、物理真實性及指令遵循性。", "ja-JP": "身体動作、物理的リアリズム、指示追従性において全面的にアップグレードされた新しいビデオ生成モデル。", "ru-RU": "Совершенно новая модель генерации видео с комплексными улучшениями в движении тела, физическом реализме и следовании инструкциям." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "MiniMax Hailuo 2.3 Fast" } ] }, { "slug": "minimax/MiniMax-M1", "model_name": "MiniMax-M1", "display_name": "MiniMax M1", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.176471" }, "completion": { "unit": "per_M_tokens", "price": "2.352941" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-06-16", "max_input_tokens": 1000192, "max_output_tokens": 40000, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "prompt_caching": true, "open_weights": true, "stream": true }, "intro": "MiniMax model for chat, coding, office work, and agentic tasks", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "minimax", "knowledge_cutoff": "2024-06", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "minimax-m1", "minimax-m1:extended", "minimax/minimax-m1" ], "intro_i18n": { "zh-CN": "一款全新自研推理模型，支持 80K 思维链和 100 万输入，性能媲美全球顶尖模型。", "zh-TW": "一款內部開發的推理模型，具備 80K 思路鏈與 100 萬輸入，效能媲美全球頂尖模型。", "ja-JP": "80Kの思考連鎖と1Mの入力を備えた新しい社内推論モデルで、世界トップクラスのモデルに匹敵する性能を発揮します。", "ru-RU": "Новая внутренняя модель рассуждений с поддержкой 80K цепочек размышлений и 1M входных токенов, обеспечивающая производительность на уровне ведущих мировых моделей." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-06", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "MiniMax M1" } ] }, { "slug": "minimax/MiniMax-M2", "model_name": "MiniMax-M2", "display_name": "MiniMax-M2", "vendor": "minimax", "pricing": [ { "provider": "minimax", "provider_name": "MiniMax (minimax.io)", "official": true, "source": "models-dev+litellm+llmdb+lobehub-modelbank+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "1.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.375" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm", "cache_write": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.03" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.21", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0.375" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.625", "currency": "CNY" }, "message": "cache_write from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.1", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8.4", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "minimax-m2" } ], "intro": "Efficient open MiniMax model built for coding agents and tool-heavy workflows", "released_at": "2025-10-27", "max_input_tokens": 196608, "max_output_tokens": 128000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "minimax", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true, "parallel_function_calling": true, "web_search": true }, "model_type": "deep_thinking", "knowledge_cutoff": "2025-01", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "MiniMaxAI/MiniMax-M2", "accounts/fireworks/models/minimax-m2", "deepinfra/MiniMaxAI/MiniMax-M2", "hf:MiniMaxAI/MiniMax-M2", "minimax-m2", "minimax/minimax-m2", "minimaxai/minimax-m2", "minimaxi/minimax-m2" ], "intro_i18n": { "zh-CN": "MiniMax M2：上一代模型。", "zh-TW": "MiniMax M2：上一代模型。", "ja-JP": "MiniMax M2: 前世代モデル。", "ru-RU": "MiniMax M2: Модель предыдущего поколения." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.24516686", "new": "1.245565524" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311291715", "new": "0.311391381" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.245361572", "new": "1.24516686" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311340393", "new": "0.311291715" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.245260352", "new": "1.245361572" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311315088", "new": "0.311340393" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.244883276", "new": "1.245260352" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311220819", "new": "0.311315088" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.244792892", "new": "1.244883276" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311198223", "new": "0.311220819" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.244929392", "new": "1.244792892" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311232348", "new": "0.311198223" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.244949552", "new": "1.244929392" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311237388", "new": "0.311232348" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.244852532", "new": "1.244949552" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311213133", "new": "0.311237388" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.243065096", "new": "1.244852532" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.310766274", "new": "0.311213133" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "completion", "old": "1.57", "new": "1.405" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "prompt", "old": "0.39", "new": "0.349" } ] }, { "slug": "minimax/MiniMax-M2-Stable", "model_name": "MiniMax-M2-Stable", "display_name": "MiniMax M2 Stable", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.030882" }, "cache_write": { "unit": "per_M_tokens", "price": "0.386029" }, "prompt": { "unit": "per_M_tokens", "price": "0.308824" }, "completion": { "unit": "per_M_tokens", "price": "1.235294" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "cache_write": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-10-27", "max_input_tokens": 204800, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "专为高效编程与智能体工作流打造，具备更高并发能力，适用于商业场景。", "zh-TW": "專為高效編碼與代理流程設計，具備更高併發能力，適用於商業應用。", "ja-JP": "効率的なコーディングとエージェントワークフローのために設計され、商用利用における高い同時実行性を実現します。", "ru-RU": "Создана для эффективного программирования и работы агентов, с повышенной параллельностью для коммерческого использования." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "MiniMax M2 Stable" } ] }, { "slug": "minimax/MiniMax-M2.1", "model_name": "MiniMax-M2.1", "display_name": "MiniMax-M2.1", "vendor": "minimax", "pricing": [ { "provider": "minimax", "provider_name": "MiniMax (minimax.io)", "official": true, "source": "models-dev+litellm+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "1.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.375" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.03" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.21", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0.375" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.625", "currency": "CNY" }, "message": "cache_write from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.1", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8.4", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Earlier MiniMax agent model for practical coding and productivity tasks", "released_at": "2025-12-23", "max_input_tokens": 204800, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "minimax", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "parallel_function_calling": true, "web_search": true }, "model_type": "deep_thinking", "knowledge_cutoff": "2025-10", "reasoning_config": { "mandatory": true, "budget_min": 1024 }, "deprecated": true, "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "MiniMaxAI/MiniMax-M2.1", "Pro/MiniMaxAI/MiniMax-M2.1", "hf:MiniMaxAI/MiniMax-M2.1", "minimax-m2-1", "minimax-m2.1", "minimax-m2.1-free", "minimax/minimax-m2.1", "novita/minimax-m2.1" ], "intro_i18n": { "zh-CN": "MiniMax-M2.1 是 MiniMax 推出的旗舰开源大模型，专注于解决复杂的现实世界任务。其核心优势在于多语言编程能力以及作为智能体解决复杂任务的能力。", "zh-TW": "MiniMax-M2.1 是 MiniMax 推出的旗艦開源大型模型，專注於解決複雜的真實世界任務。其核心優勢在於多語言程式設計能力與作為智能代理執行複雜任務的能力。", "ja-JP": "MiniMax-M2.1は、MiniMaxが開発したフラッグシップのオープンソース大規模モデルで、複雑な現実世界のタスク解決に特化しています。多言語プログラミング能力とエージェントとしての高度なタスク処理能力が主な強みです。", "ru-RU": "MiniMax-M2.1 — это флагманская модель с открытым исходным кодом от MiniMax, ориентированная на решение сложных задач из реального мира. Её ключевые преимущества — поддержка многозадачного программирования и способность выступать в роли интеллектуального агента." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "minimax/MiniMax-M2.1-highspeed", "model_name": "MiniMax-M2.1-highspeed", "display_name": "MiniMax M2.1 highspeed", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.030882" }, "cache_write": { "unit": "per_M_tokens", "price": "0.386029" }, "prompt": { "unit": "per_M_tokens", "price": "0.617647" }, "completion": { "unit": "per_M_tokens", "price": "2.470588" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "cache_write": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-12-23", "max_input_tokens": 204800, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "minimax/minimax-m2.1-highspeed" ], "intro_i18n": { "zh-CN": "强大的多语言编程能力，全面升级的编程体验。更快、更高效。", "zh-TW": "強大的多語言編程能力，全面升級的編程體驗。速度更快，效率更高。", "ja-JP": "強力な多言語プログラミング機能を備え、プログラミング体験を包括的に向上。より高速かつ効率的です。", "ru-RU": "Мощные многоязычные программные возможности, всесторонне улучшенный опыт программирования. Быстрее и эффективнее." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "MiniMax M2.1 highspeed" } ] }, { "slug": "minimax/MiniMax-M2.1-lightning", "model_name": "MiniMax-M2.1-lightning", "display_name": "MiniMax-M2.1-lightning", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.375" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 1000000, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "intro": "Earlier MiniMax agent model for practical coding and productivity tasks", "released_at": "2025-12-23", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "minimax", "knowledge_cutoff": "2024-10", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "minimax-m2.1-lightning", "minimax/minimax-m2.1-lightning" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "minimax/MiniMax-M2.5", "model_name": "MiniMax-M2.5", "display_name": "MiniMax-M2.5", "vendor": "minimax", "pricing": [ { "provider": "minimax", "provider_name": "MiniMax (minimax.io)", "official": true, "source": "models-dev+litellm+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "1.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.375" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.03" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.21", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0.375" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.625", "currency": "CNY" }, "message": "cache_write from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.1", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8.4", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Prior MiniMax coding model for agent workflows, office edits, and automation", "released_at": "2026-02-12", "max_input_tokens": 204800, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "minimax", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "parallel_function_calling": true, "web_search": true }, "model_type": "deep_thinking", "knowledge_cutoff": "2025-06", "deprecated": true, "status": "deprecated", "docs_url": "https://openrouter.ai/minimax/minimax-m2.5", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "parallel_tool_calls", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ " MiniMaxAI/MiniMax-M2.5", "MiniMax/MiniMax-M2.5", "MiniMaxAI/MiniMax-M2.5", "Pro/MiniMaxAI/MiniMax-M2.5", "inceptron/minimax-m2.5", "minimax-m2-5", "minimax-m2.5", "minimax-m2.5-free", "minimax/minimax-m2.5", "minimax/minimax-m2.5:free", "minimaxi/minimax-m2.5", "nebius/minimaxi/minimax-m2.5" ], "intro_i18n": { "zh-CN": "MiniMax-M2.5 是 MiniMax 推出的旗舰开源大模型，专注于解决复杂的现实世界任务。其核心优势在于多语言编程能力以及作为 Agent 解决复杂任务的能力。", "zh-TW": "MiniMax-M2.5 是 MiniMax 推出的旗艦開源大型模型，專注於解決複雜的現實世界任務。其核心優勢包括多語言編程能力以及作為代理解決複雜任務的能力。", "ja-JP": "MiniMax-M2.5は、MiniMaxによるフラッグシップのオープンソース大規模モデルで、複雑な現実世界のタスクを解決することに焦点を当てています。その主な強みは、多言語プログラミング能力とエージェントとして複雑なタスクを解決する能力です。", "ru-RU": "MiniMax-M2.5 — это флагманская открытая крупная модель от MiniMax, ориентированная на решение сложных реальных задач. Её основные преимущества — многоязычные программные возможности и способность решать сложные задачи в качестве агента." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.139", "new": "0.1365" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.116", "new": "1.066" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.278", "new": "0.273" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.24516686", "new": "1.245565524" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311291715", "new": "0.311391381" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.09", "new": "1.116" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.245361572", "new": "1.24516686" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311340393", "new": "0.311291715" }, { "date": "2026-08-12", "kind": "price", "provider": "inceptron", "charge": "prompt", "old": "0.15", "new": "0.22" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.1285", "new": "0.139" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.006", "new": "1.09" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.257", "new": "0.278" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.245260352", "new": "1.245361572" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311315088", "new": "0.311340393" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.1465", "new": "0.1285" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.176", "new": "1.006" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.293", "new": "0.257" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.244883276", "new": "1.245260352" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311220819", "new": "0.311315088" }, { "date": "2026-08-10", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.1315", "new": "0.1465" } ] }, { "slug": "minimax/MiniMax-M2.5-highspeed", "model_name": "MiniMax-M2.5-highspeed", "display_name": "MiniMax-M2.5-highspeed", "vendor": "minimax", "pricing": [ { "provider": "minimax", "provider_name": "MiniMax (minimax.io)", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.06" }, "cache_write": { "unit": "per_M_tokens", "price": "0.375" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.06" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.21", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0.375" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.625", "currency": "CNY" }, "message": "cache_write from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4.2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "16.8", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "High-speed MiniMax model for low-latency coding and agent workflows", "released_at": "2026-02-13", "max_input_tokens": 204800, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "minimax", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "minimax-m2-5-highspeed", "minimax-m2.5-highspeed", "minimax/minimax-m2.5-highspeed", "minimaxi/minimax-m2.5-highspeed" ], "intro_i18n": { "zh-CN": "MiniMax M2.5 Highspeed：与M2.5性能相同，但推理速度更快。", "zh-TW": "MiniMax M2.5 高速版：與 M2.5 性能相同，但推理速度更快。", "ja-JP": "MiniMax M2.5 Highspeed: M2.5と同等の性能で推論速度が向上。", "ru-RU": "MiniMax M2.5 Highspeed: Та же производительность, что и у M2.5, но с ускоренным выводом." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "minimax/MiniMax-M2.5-lightning", "model_name": "MiniMax-M2.5-lightning", "display_name": "MiniMax-M2.5-lightning", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "2.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0.375" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 1000000, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "intro": "High-speed MiniMax model for low-latency coding and agent workflows", "released_at": "2026-02-13", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "minimax", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "minimax/minimax-m2.5-lightning" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-08-10", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "minimax/MiniMax-M2.7", "model_name": "MiniMax-M2.7", "display_name": "MiniMax-M2.7", "vendor": "minimax", "pricing": [ { "provider": "minimax", "provider_name": "MiniMax (minimax.io)", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "1.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.06" }, "cache_write": { "unit": "per_M_tokens", "price": "0.375" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.06" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.42", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0.375" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.625", "currency": "CNY" }, "message": "cache_write from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.1", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8.4", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Open MiniMax flagship for coding agents, office automation, and complex environments", "released_at": "2026-03-18", "max_input_tokens": 204800, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "minimax", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "deep_thinking", "knowledge_cutoff": "2025-01", "docs_url": "https://cloud.sambanova.ai/plans/pricing", "benchmarks": { "intelligence_index": 38.9, "coding_index": 52.6, "agentic_index": 25.9 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "MiniMax/MiniMax-M2.7", "MiniMaxAI/MiniMax-M2.7", "fireworks/minimax-m2.7", "minimax-m2-7", "minimax-m2.7", "minimax-m2.7:free", "minimax/minimax-m2.7", "minimaxai/minimax-m2.7", "minimaxi/minimax-m2.7", "novita/minimax/minimax-m2.7", "route/minimax-m2.7" ], "intro_i18n": { "zh-CN": "首个具备自进化能力的模型，拥有顶尖的编码与智能体性能（约 60 tps）。", "zh-TW": "首個具自我進化能力的模型，具備頂級編碼與智能體效能（約 60 tps）。", "ja-JP": "自己進化型モデルの第一弾で、トップクラスのコーディング性能とエージェント能力を備え、約 60 tps の高速性能を発揮します。", "ru-RU": "Первая саморазвивающаяся модель с высококлассной производительностью в кодировании и агентных задачах (~60 tps)." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "hyper", "charge": "cache_write", "old": "0.235", "new": "0.213" }, { "date": "2026-08-14", "kind": "price", "provider": "hyper", "charge": "completion", "old": "1.76", "new": "1.62" }, { "date": "2026-08-14", "kind": "price", "provider": "hyper", "charge": "prompt", "old": "0.47", "new": "0.426" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.235", "new": "0.213" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.76", "new": "1.62" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.47", "new": "0.426" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.24516686", "new": "1.245565524" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311291715", "new": "0.311391381" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "cache_write", "old": "0.218", "new": "0.235" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "completion", "old": "1.66", "new": "1.76" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "prompt", "old": "0.436", "new": "0.47" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.218", "new": "0.235" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "1.66", "new": "1.76" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.436", "new": "0.47" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.245361572", "new": "1.24516686" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311340393", "new": "0.311291715" }, { "date": "2026-08-12", "kind": "price", "provider": "hyper", "charge": "cache_write", "old": "0.235", "new": "0.218" }, { "date": "2026-08-12", "kind": "price", "provider": "hyper", "charge": "completion", "old": "1.76", "new": "1.66" }, { "date": "2026-08-12", "kind": "price", "provider": "hyper", "charge": "prompt", "old": "0.47", "new": "0.436" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.235", "new": "0.218" } ] }, { "slug": "minimax/MiniMax-M2.7-highspeed", "model_name": "MiniMax-M2.7-highspeed", "display_name": "MiniMax-M2.7-highspeed", "vendor": "minimax", "pricing": [ { "provider": "minimax", "provider_name": "MiniMax (minimax.io)", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.06" }, "cache_write": { "unit": "per_M_tokens", "price": "0.375" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.06" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.42", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0.375" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.625", "currency": "CNY" }, "message": "cache_write from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4.2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "16.8", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Low-latency M2.7 variant for interactive coding plans and agent loops", "released_at": "2026-03-18", "max_input_tokens": 204800, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "minimax", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "text_generation", "knowledge_cutoff": "2025-01", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "minimax-m2-7-highspeed", "minimax-m2.7-highspeed", "minimax/minimax-m2.7-highspeed", "minimaxi/minimax-m2.7-highspeed", "novita/minimax/minimax-m2.7-highspeed" ], "intro_i18n": { "zh-CN": "MiniMax M2.7 Highspeed：与M2.7性能相同，但推理速度显著提升。", "zh-TW": "MiniMax M2.7 高速版：與 M2.7 性能相同，但推理速度顯著提升。", "ja-JP": "MiniMax M2.7 Highspeed: M2.7と同等の性能で推論速度が大幅に向上。", "ru-RU": "MiniMax M2.7 Highspeed: Та же производительность, что и у M2.7, но с значительно ускоренным выводом." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" } ] }, { "slug": "minimax/MiniMax-M3", "model_name": "MiniMax-M3", "display_name": "MiniMax-M3", "vendor": "minimax", "pricing": [ { "provider": "minimax", "provider_name": "MiniMax (minimax.io)", "official": true, "source": "models-dev+litellm+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "1.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.06" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "tracks": [ { "label": "Context >512K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.1", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8.4", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.06" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.42", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "tier_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "threshold": 512000, "inclusive": false, "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4.2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "tier_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "threshold": 512000, "inclusive": false, "selected_charge": { "unit": "per_M_tokens", "price": "2.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "16.8", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "tier_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "threshold": 512000, "inclusive": false, "selected_charge": { "unit": "per_M_tokens", "price": "0.12" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.84", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >512K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 512000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "MiniMax multimodal model for long-context coding, perception, and agent planning", "released_at": "2026-06-01", "max_input_tokens": 1000000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "minimax", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true }, "model_type": "deep_thinking", "knowledge_cutoff": "2025-01", "reasoning_config": { "mandatory": false, "budget_min": 1 }, "deprecated": true, "status": "deprecated", "docs_url": "https://docs.fireworks.ai/serverless/pricing", "benchmarks": { "intelligence_index": 45.4, "coding_index": 58.6, "agentic_index": 36.1 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "MiniMaxAI/MiniMax-M3", "accounts/fireworks/models/minimax-m3", "cline-pass/minimax-m3", "fireworks/minimax-m3", "hf:MiniMaxAI/MiniMax-M3", "minimax-m3", "minimax-m3-free", "minimax/minimax-m3", "minimax/minimax-m3:thinking", "minimaxai/minimax-m3", "minimaxi/minimax-m3", "tensorx/minimax-m3" ], "intro_i18n": { "zh-CN": "MiniMax M3 是 MiniMax 的首款多模态模型，具备原生的图像和视频理解能力，以及强大的编程和代理能力。", "zh-TW": "MiniMax M3 是 MiniMax 的首款多模態模型，具備原生的影像和影片理解能力，以及強大的編程和代理能力。", "ja-JP": "MiniMax M3は、MiniMax初のマルチモーダルモデルで、画像や動画の理解に対応し、強力なコーディング能力とエージェント機能を備えています。", "ru-RU": "MiniMax M3 — первая мультимодальная модель MiniMax с нативным пониманием изображений и видео, а также мощными возможностями кодирования и агентных задач." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.24516686", "new": "1.245565524" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311291715", "new": "0.311391381" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.245361572", "new": "1.24516686" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311340393", "new": "0.311291715" }, { "date": "2026-08-13", "kind": "price", "provider": "zenmux", "charge": "cache_read", "old": "0.06", "new": "0.054" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.245260352", "new": "1.245361572" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311315088", "new": "0.311340393" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.244883276", "new": "1.245260352" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311220819", "new": "0.311315088" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.244792892", "new": "1.244883276" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311198223", "new": "0.311220819" }, { "date": "2026-08-10", "kind": "price", "provider": "wafer", "charge": "cache_read", "old": "0.06", "new": "0.07" }, { "date": "2026-08-10", "kind": "price", "provider": "wafer", "charge": "completion", "old": "1.2", "new": "1.32" }, { "date": "2026-08-10", "kind": "price", "provider": "wafer", "charge": "prompt", "old": "0.3", "new": "0.33" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.244929392", "new": "1.244792892" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311232348", "new": "0.311198223" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.244949552", "new": "1.244929392" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.311237388", "new": "0.311232348" }, { "date": "2026-08-08", "kind": "price", "provider": "zenmux", "charge": "cache_read", "old": "0.02746152", "new": "0.06" }, { "date": "2026-08-07", "kind": "price", "provider": "deepinfra", "charge": "cache_read", "old": "0.06", "new": "0.056" } ] }, { "slug": "minimax/MiniMax-Text-01", "model_name": "MiniMax-Text-01", "display_name": "MiniMax Text 01", "vendor": "minimax", "pricing": [ { "provider": "minimax", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.147059" }, "completion": { "unit": "per_M_tokens", "price": "1.176471" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-01-15", "max_input_tokens": 1000192, "max_output_tokens": 40000, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "vision": true, "image_output": true, "pdf_input": true, "open_weights": true, "prompt_caching": true }, "intro": "MiniMax model for chat, coding, office work, and agentic tasks", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "minimax", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "minimax-text-01" ], "intro_i18n": { "zh-CN": "MiniMax-01 引入超越传统 Transformer 的大规模线性注意力机制，拥有 4560 亿参数，每次激活 459 亿，支持最长 400 万上下文（为 GPT-4o 的 32 倍，Claude-3.5-Sonnet 的 20 倍），性能顶尖。", "zh-TW": "MiniMax-01 採用超越傳統 Transformer 的大規模線性注意力機制，擁有 4560 億參數，每次啟用 459 億，支援最多 400 萬字元上下文（為 GPT-4o 的 32 倍，Claude-3.5-Sonnet 的 20 倍），效能頂尖。", "ja-JP": "MiniMax-01は、従来のTransformerを超える大規模な線形アテンションを導入し、4560億のパラメータと1パスあたり45.9億のアクティブパラメータを持ちます。最大400万トークンのコンテキストをサポートし（GPT-4oの32倍、Claude-3.5-Sonnetの20倍）、最高水準の性能を実現します。", "ru-RU": "MiniMax-01 представляет масштабное линейное внимание, выходящее за рамки классических трансформеров, с 456B параметрами и 45.9B активируемыми за проход. Обеспечивает производительность высшего уровня и поддерживает до 4M токенов контекста (в 32 раза больше GPT-4o, в 20 раз больше Claude-3.5-Sonnet)." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "MiniMax Text 01" } ] }, { "slug": "mistral/codestral", "model_name": "codestral", "display_name": "Codestral", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.9" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Mistral's cutting-edge language model for coding. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.", "capabilities": { "function_calling": true, "open_weights": true, "stream": true }, "released_at": "2024-05-29", "knowledge_cutoff": "2024-10", "max_input_tokens": 256000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "codestral", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/codestral" ], "intro_i18n": { "zh-CN": "Codestral 是 Mistral AI 推出的首个代码模型，具备强大的代码生成能力。", "zh-TW": "Codestral 是 Mistral AI 推出的首款程式模型，具備強大的程式碼生成能力。", "ja-JP": "Codestralは、Mistral AIによる初のコードモデルで、強力なコード生成をサポートします。", "ru-RU": "Codestral — первая модель для программирования от Mistral AI, обеспечивающая высокое качество генерации кода." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Codestral" } ] }, { "slug": "mistral/codestral-2405", "model_name": "codestral-2405", "display_name": "codestral-2405", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 32000, "max_output_tokens": 8191, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2025-06-16", "capabilities": { "structured_output": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/codestral-2501", "model_name": "codestral-2501", "display_name": "Codestral 25.01", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.9" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "capabilities": { "function_calling": true, "stream": true }, "intro": "Mistral coding model for code completion, generation, and developer workflows", "released_at": "2025-01-01", "knowledge_cutoff": "2024-03", "max_input_tokens": 256000, "max_output_tokens": 256000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "codestral", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/codestral-2501" ], "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-25", "kind": "limit", "old": "32000", "new": "256000", "note": "max_input_tokens" }, { "date": "2026-07-25", "kind": "limit", "old": "8192", "new": "256000", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Codestral 25.01" } ] }, { "slug": "mistral/codestral-2508", "model_name": "codestral-2508", "display_name": "codestral-2508", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.9" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "docs_url": "https://mistral.ai/news/codestral-25-08", "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "open_weights": true, "stream": true }, "intro": "Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.", "modalities": { "input": [ "text", "code" ], "output": [ "text", "code" ] }, "released_at": "2025-07-30", "knowledge_cutoff": "2025-03", "family": "mistral", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "prediction", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "defaults": { "temperature": 0.3 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/codestral-2508" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/codestral-embed", "model_name": "codestral-embed", "display_name": "codestral-embed", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 8192, "model_type": "text_embedding", "capabilities": {}, "modalities": { "input": [ "text", "code" ], "output": [ "embedding" ] }, "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2025-05-28", "max_output_tokens": 1536, "family": "codestral-embed", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/codestral-embed" ], "intro_i18n": { "zh-CN": "一款代码嵌入模型，用于嵌入代码库和仓库，支持编程助手。", "zh-TW": "一款用於嵌入代碼庫與儲存庫的代碼嵌入模型，支援編碼助手應用。", "ja-JP": "コードベースやリポジトリの埋め込みに対応したコード埋め込みモデルで、コーディングアシスタントを支援します。", "ru-RU": "Модель для встраивания кода, предназначенная для индексирования кодовых баз и репозиториев в помощь ассистентам по программированию." } }, { "slug": "mistral/codestral-embed-2505", "model_name": "codestral-embed-2505", "display_name": "codestral-embed-2505", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 8192, "model_type": "text_embedding", "capabilities": { "stream": true }, "modalities": { "input": [ "text", "code" ], "output": [ "embedding" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/codestral-embed-2505" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/codestral-latest", "model_name": "codestral-latest", "display_name": "Codestral", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.9" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.9" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Mistral code model for completions, refactors, and developer IDE workflows", "released_at": "2024-05-29", "knowledge_cutoff": "2024-10", "max_input_tokens": 256000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "codestral", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "assistant_prefill": true, "stream": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/codestral-latest" ], "intro_i18n": { "zh-CN": "Codestral 是我们最先进的代码模型；v2（2025年1月）专为低延迟、高频任务（如 FIM、代码修复和测试生成）而设计。", "zh-TW": "Codestral 是我們最先進的程式模型；v2（2025 年 1 月）針對低延遲、高頻率任務如 FIM、程式碼修正與測試生成進行優化。", "ja-JP": "Codestralは、最も高度なコーディングモデルで、v2（2025年1月）はFIM、コード修正、テスト生成などの低レイテンシ・高頻度タスクに最適化されています。", "ru-RU": "Codestral — наша самая продвинутая модель для программирования; версия v2 (январь 2025) оптимизирована для задач с низкой задержкой и высокой частотой, таких как FIM, исправление кода и генерация тестов." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/codestral-mamba-latest", "model_name": "codestral-mamba-latest", "display_name": "codestral-mamba-latest", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://mistral.ai/technology/", "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": { "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "mistral/devstral-2512", "model_name": "devstral-2512", "display_name": "Devstral 2", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.04" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "intro": "Mistral's coding-agent model for repository work, terminal tasks, and software fixes", "released_at": "2025-12-09", "knowledge_cutoff": "2025-12", "max_input_tokens": 262144, "max_output_tokens": 262144, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "devstral", "status": "deprecated", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "assistant_prefill": true, "stream": true }, "docs_url": "https://mistral.ai/news/devstral-2-vibe-cli", "model_type": "text_generation", "deprecation_date": "2026-07-31", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/devstral-2512", "mistralai/devstral-2512", "mistralai/devstral-2512:free" ], "intro_i18n": { "zh-CN": "Devstral 2 是一款企业级文本模型，擅长使用工具探索代码库、编辑多个文件，并为软件工程 Agent 提供支持。", "zh-TW": "Devstral 2 是一款企業級文本模型，擅長使用工具探索代碼庫、編輯多個文件並驅動軟件工程代理。", "ja-JP": "Devstral 2は、コードベースの探索、複数ファイルの編集、ソフトウェアエンジニアリングエージェントの強化に優れたエンタープライズレベルのテキストモデルです。", "ru-RU": "Devstral 2 — это корпоративная текстовая модель, которая превосходно справляется с использованием инструментов для исследования кодовых баз, редактирования нескольких файлов и поддержки агентов для разработки программного обеспечения." }, "price_history": [ { "date": "2026-08-01", "kind": "capability", "note": "pdf_input: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/devstral-latest", "model_name": "devstral-latest", "display_name": "Devstral 2", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Legacy model retained for compatibility with older integrations", "released_at": "2025-12-09", "knowledge_cutoff": "2025-12", "max_input_tokens": 262144, "max_output_tokens": 262144, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "devstral", "status": "deprecated", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "assistant_prefill": true }, "docs_url": "https://mistral.ai/news/devstral-2-vibe-cli", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/devstral-latest" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" } ] }, { "slug": "mistral/devstral-medium-2507", "model_name": "devstral-medium-2507", "display_name": "Devstral Medium", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Legacy model retained for compatibility with older integrations", "released_at": "2025-07-10", "knowledge_cutoff": "2025-05", "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "devstral", "status": "deprecated", "capabilities": { "function_calling": true, "structured_output": true, "open_weights": true, "assistant_prefill": true, "stream": true }, "docs_url": "https://mistral.ai/news/devstral", "model_type": "text_generation", "deprecation_date": "2026-05-31", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/devstral-medium-2507" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/devstral-medium-251121", "model_name": "devstral-medium-251121", "display_name": "devstral-medium-251121", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 262144, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "capabilities": { "function_calling": true, "structured_output": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "devstral-medium-251121" } ] }, { "slug": "mistral/devstral-medium-latest", "model_name": "devstral-medium-latest", "display_name": "Devstral 2", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Legacy model retained for compatibility with older integrations", "released_at": "2025-12-02", "knowledge_cutoff": "2025-12", "max_input_tokens": 262144, "max_output_tokens": 262144, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "devstral", "status": "deprecated", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true, "stream": true }, "docs_url": "https://mistral.ai/news/devstral-2-vibe-cli", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/devstral-medium-latest" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-06", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-06", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/devstral-small", "model_name": "devstral-small", "display_name": "Mistral: Devstral Small 1.1", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.12" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%).", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "stream": true, "open_weights": true }, "max_input_tokens": 131072, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "released_at": "2025-07-10", "max_output_tokens": 26215, "knowledge_cutoff": "2024-10", "family": "devstral", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/devstral-small", "mistralai/devstral-small" ], "intro_i18n": { "zh-CN": "Devstral 是一款面向软件工程任务的智能体大语言模型，是软件工程智能体的强力选择。", "zh-TW": "Devstral 是一款專為軟體工程任務設計的代理型大型語言模型，是軟體工程代理的強力選擇。", "ja-JP": "Devstralは、ソフトウェアエンジニアリングタスク向けのエージェント型LLMで、ソフトウェアエンジニアリングエージェントに最適です。", "ru-RU": "Devstral — агентная LLM для задач в области разработки ПО, отличный выбор для инженерных агентов." }, "price_history": [ { "date": "2026-07-14", "kind": "limit", "old": "128000", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-07-14", "kind": "limit", "old": "64000", "new": "26215", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Devstral Small 1.1" } ] }, { "slug": "mistral/devstral-small-2505", "model_name": "devstral-small-2505", "display_name": "Devstral Small 2505", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Legacy model retained for compatibility with older integrations", "released_at": "2025-05-07", "knowledge_cutoff": "2025-05", "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "devstral", "status": "deprecated", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "assistant_prefill": true, "stream": true }, "docs_url": "https://mistral.ai/news/devstral", "model_type": "text_generation", "deprecation_date": "2025-11-30", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "accounts/fireworks/models/devstral-small-2505", "devstral-small-2505:free", "mistralai/Devstral-Small-2505" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/devstral-small-2507", "model_name": "devstral-small-2507", "display_name": "Devstral Small", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Legacy model retained for compatibility with older integrations", "released_at": "2025-07-10", "knowledge_cutoff": "2025-05", "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "devstral", "status": "deprecated", "capabilities": { "function_calling": true, "structured_output": true, "open_weights": true, "assistant_prefill": true, "stream": true }, "docs_url": "https://mistral.ai/news/devstral", "model_type": "text_generation", "deprecation_date": "2026-05-31", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/devstral-small-2507", "mistralai/devstral-small-2507" ], "price_history": [ { "date": "2026-07-15", "kind": "capability", "note": "prompt_caching: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/devstral-small-latest", "model_name": "devstral-small-latest", "display_name": "devstral-small-latest", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://docs.mistral.ai/models/devstral-small-2-25-12", "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "parallel_function_calling": true }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "released_at": "2026-04-22", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/devstral-small-latest" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" } ] }, { "slug": "mistral/labs-devstral-small-2512", "model_name": "labs-devstral-small-2512", "display_name": "Devstral Small 2", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Legacy model retained for compatibility with older integrations", "released_at": "2025-12-09", "knowledge_cutoff": "2025-12", "max_input_tokens": 256000, "max_output_tokens": 256000, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "devstral", "status": "deprecated", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "open_weights": true, "assistant_prefill": true }, "docs_url": "https://docs.mistral.ai/models/devstral-small-2-25-12", "model_type": "vision_understanding", "deprecation_date": "2026-03-31", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Devstral Small 2 擅长使用工具探索代码库、编辑多个文件，并为软件工程 Agent 提供支持。", "zh-TW": "Devstral Small 2 擅長使用工具探索代碼庫、編輯多個文件並驅動軟件工程代理。", "ja-JP": "Devstral Small 2は、コードベースの探索、複数ファイルの編集、ソフトウェアエンジニアリングエージェントの強化に優れています。", "ru-RU": "Devstral Small 2 превосходно справляется с использованием инструментов для исследования кодовых баз, редактирования нескольких файлов и поддержки агентов для разработки программного обеспечения." } }, { "slug": "mistral/labs-leanstral-1-5", "model_name": "labs-leanstral-1-5", "display_name": "labs-leanstral-1-5", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://docs.mistral.ai/models/model-cards/leanstral-1-5", "max_input_tokens": 262144, "max_output_tokens": 131072, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "limit", "new": "131072", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "labs-leanstral-1-5" } ] }, { "slug": "mistral/labs-leanstral-1-5-1", "model_name": "labs-leanstral-1-5-1", "display_name": "labs-leanstral-1-5-1", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 262144, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "assistant_prefill": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "labs-leanstral-1-5-1" } ] }, { "slug": "mistral/labs-leanstral-2603", "model_name": "labs-leanstral-2603", "display_name": "Leanstral", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 196608, "deprecated": true, "modalities": { "input": [ "image", "text", "code" ], "output": [ "text", "code" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "assistant_prefill": true, "vision": true }, "released_at": "2026-03-16", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Mistral的首个开源代码代理，专为Lean 4设计，适用于现实存储库中的形式化证明工程。拥有1190亿参数，其中65亿为激活参数。", "zh-TW": "Mistral首款開源代碼代理，專為Lean 4設計，適用於現實存儲庫中的形式化證明工程。119B參數，6.5B激活。", "ja-JP": "Lean 4用に設計されたMistralの最初のオープンソースコードエージェントで、現実的なリポジトリでの形式的証明エンジニアリングに対応。119Bパラメータ、6.5Bアクティブ。", "ru-RU": "Первая модель открытого исходного кода для работы с кодом от Mistral, разработанная для Lean 4, созданная для формального доказательства в реалистичных репозиториях. 119B параметров с 6.5B активных." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Leanstral" } ] }, { "slug": "mistral/labs-mistral-small-creative", "model_name": "labs-mistral-small-creative", "display_name": "labs-mistral-small-creative", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "labs-mistral-small-creative" } ] }, { "slug": "mistral/magistral-medium", "model_name": "magistral-medium", "display_name": "Magistral Medium", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Magistral is Mistral's first reasoning model. It is ideal for general purpose use requiring longer thought processing and better accuracy than with non-reasoning LLMs. From legal research and financial forecasting to software development and creative storytelling — this model solves multi-step challenges where transparency and precision are critical.", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "open_weights": true, "pdf_input": true, "stream": true }, "released_at": "2025-03-17", "knowledge_cutoff": "2025-06", "max_input_tokens": 128000, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "magistral-medium", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "anthropic/pioneer/magistral-medium", "mistral/magistral-medium" ], "intro_i18n": { "zh-CN": "通过深度理解支持复杂思维，具备可追踪、可验证的透明推理能力。即使在任务中途，也能在多语言环境中保持高保真推理。", "zh-TW": "透過深層理解支援複雜思維，並提供可追溯與可驗證的透明推理。即使在任務中途，也能維持跨語言的高保真推理能力。", "ja-JP": "深い理解に基づく複雑な思考を支援し、透明性のある推論を提供します。タスク中でも言語間で高精度な推論を維持します。", "ru-RU": "Сложное мышление, поддерживаемое глубоким пониманием и прозрачной логикой, которую можно проследить и проверить. Сохраняет точность рассуждений на разных языках даже в середине задачи." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Magistral Medium" } ] }, { "slug": "mistral/magistral-medium-1-2-2509", "model_name": "magistral-medium-1-2-2509", "display_name": "magistral-medium-1-2-2509", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://mistral.ai/news/magistral", "max_input_tokens": 40000, "max_output_tokens": 40000, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-07-31", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/magistral-medium-2506", "model_name": "magistral-medium-2506", "display_name": "magistral-medium-2506", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://mistral.ai/news/magistral", "max_input_tokens": 40000, "max_output_tokens": 40000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2025-11-30", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "magistral-medium-2506:thinking" ], "price_history": [ { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/magistral-medium-2509", "model_name": "magistral-medium-2509", "display_name": "magistral-medium-2509", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://mistral.ai/news/magistral", "max_input_tokens": 40000, "max_output_tokens": 40000, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-07-31", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true }, "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Magistral Medium 1.2是Mistral AI的前沿推理模型（2025年9月），支持视觉功能。", "zh-TW": "Magistral Medium 1.2是Mistral AI的前沿推理模型（2025年9月），支持視覺功能。", "ja-JP": "Magistral Medium 1.2は、Mistral AIによるフロンティア推論モデル（2025年9月）で、ビジョンサポートを備えています。", "ru-RU": "Magistral Medium 1.2 — передовая модель рассуждений от Mistral AI (сентябрь 2025) с поддержкой визуализации." }, "price_history": [ { "date": "2026-08-02", "kind": "capability", "note": "prompt_caching: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/magistral-medium-latest", "model_name": "magistral-medium-latest", "display_name": "Magistral Medium", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Mistral reasoning model for transparent analysis, math, and complex decisions", "released_at": "2025-03-17", "knowledge_cutoff": "2025-06", "max_input_tokens": 128000, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "magistral-medium", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://mistral.ai/news/magistral", "model_type": "text_generation", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/magistral-medium-latest" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/magistral-small", "model_name": "magistral-small", "display_name": "Magistral Small", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+pydantic-prices+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Mistral reasoning model for transparent analysis, math, and complex decisions", "released_at": "2025-03-17", "knowledge_cutoff": "2025-06", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "magistral-small", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "open_weights": true, "pdf_input": true, "stream": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/magistral-small" ], "intro_i18n": { "zh-CN": "通过深度理解支持复杂思维，具备可追踪、可验证的透明推理能力。即使在任务中途，也能在多语言环境中保持高保真推理。", "zh-TW": "透過深層理解支援複雜思維，並提供可追溯與可驗證的透明推理。即使在任務中途，也能維持跨語言的高保真推理能力。", "ja-JP": "深い理解に基づく複雑な思考を支援し、透明性のある推論を提供します。タスク中でも言語間で高精度な推論を維持します。", "ru-RU": "Сложное мышление, поддерживаемое глубоким пониманием и прозрачной логикой, которую можно проследить и проверить. Сохраняет точность рассуждений на разных языках даже в середине задачи." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/magistral-small-1-2-2509", "model_name": "magistral-small-1-2-2509", "display_name": "magistral-small-1-2-2509", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://mistral.ai/pricing#api-pricing", "max_input_tokens": 40000, "max_output_tokens": 40000, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-07-31", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/magistral-small-2506", "model_name": "magistral-small-2506", "display_name": "magistral-small-2506", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://mistral.ai/pricing#api-pricing", "max_input_tokens": 40000, "max_output_tokens": 40000, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2025-11-30", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "open_weights": true, "stream": true }, "intro": "Mistral reasoning model for transparent analysis, math, and complex decisions", "released_at": "2025-09-25", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2025-01", "family": "magistral-small", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/Magistral-Small-2506", "mistralai/magistral-small-2506" ], "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-08-10", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-08-05", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/Magistral-Small-2509", "model_name": "Magistral-Small-2509", "display_name": "Magistral Small 1.2", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry+portkey+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "cross_checked" }, "provider_model_id": "magistral-small-2509" } ], "max_input_tokens": 131072, "deprecated": true, "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "reasoning": true, "vision": true, "pdf_input": true, "open_weights": true }, "intro": "Mistral reasoning model for transparent analysis, math, and complex decisions", "released_at": "2025-12-02", "max_output_tokens": 40000, "family": "magistral", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "magistral-small-2509", "mistral.magistral-small-2509", "mistralai/Magistral-Small-2509" ], "intro_i18n": { "zh-CN": "Magistral Small 1.2 是 Mistral AI 于 2025 年 9 月发布的开源小型推理模型，支持视觉输入。", "zh-TW": "Magistral Small 1.2 是 Mistral AI 推出的開源小型推理模型（2025 年 9 月），支援視覺任務。", "ja-JP": "Magistral Small 1.2はMistral AIによるオープンソースの小型推論モデルで、視覚入力をサポートします。", "ru-RU": "Magistral Small 1.2 — это компактная модель рассуждений с открытым исходным кодом от Mistral AI (сентябрь 2025 года) с поддержкой обработки изображений." }, "price_history": [ { "date": "2026-08-02", "kind": "capability", "note": "prompt_caching: true→false" }, { "date": "2026-07-03", "kind": "listed", "note": "Magistral Small 1.2" } ] }, { "slug": "mistral/magistral-small-latest", "model_name": "magistral-small-latest", "display_name": "magistral-small-latest", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://mistral.ai/pricing#api-pricing", "max_input_tokens": 40000, "max_output_tokens": 40000, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "assistant_prefill": true }, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/magistral-small-latest" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/ministral-14b-2512", "model_name": "ministral-14b-2512", "display_name": "ministral-14b-2512", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.02" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "intro": "The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart.", "capabilities": { "function_calling": true, "structured_output": true, "assistant_prefill": true, "vision": true, "prompt_caching": true, "pdf_input": true, "open_weights": true, "stream": true, "image_output": true }, "max_input_tokens": 262144, "modalities": { "input": [ "text", "image", "doc" ], "output": [ "text" ] }, "model_type": "vision_understanding", "released_at": "2025-12-03", "max_output_tokens": 256000, "parameters": { "unsupported": [ "temperature" ] }, "family": "ministral", "knowledge_cutoff": "2024-12", "benchmarks": { "intelligence_index": 11.2, "coding_index": 14.4, "agentic_index": 2.2 }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/ministral-14b-2512" ], "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "256000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "32768", "new": "256000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "32768", "new": "256000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "256000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "32768", "new": "256000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "256000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "32768", "new": "256000", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "256000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "128000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-07-07", "kind": "capability", "note": "assistant_prefill: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "ministral-14b-2512" } ] }, { "slug": "mistral/ministral-14b-latest", "model_name": "ministral-14b-latest", "display_name": "ministral-14b-latest", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry+portkey", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.02" }, "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 262144, "modalities": { "input": [ "text", "image", "doc" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "parallel_function_calling": true, "structured_output": true, "assistant_prefill": true, "prompt_caching": true, "vision": true, "pdf_input": true }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/ministral-14b-latest" ], "price_history": [ { "date": "2026-07-16", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-06", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "ministral-14b-latest" } ] }, { "slug": "mistral/ministral-3-14b-2512", "model_name": "ministral-3-14b-2512", "display_name": "ministral-3-14b-2512", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://mistral.ai/pricing", "max_input_tokens": 262144, "max_output_tokens": 262144, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "mistral/ministral-3-3b-2512", "model_name": "ministral-3-3b-2512", "display_name": "ministral-3-3b-2512", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://mistral.ai/pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "mistral/ministral-3-8b-2512", "model_name": "ministral-3-8b-2512", "display_name": "ministral-3-8b-2512", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://mistral.ai/pricing", "max_input_tokens": 262144, "max_output_tokens": 262144, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "mistral/ministral-3b", "model_name": "ministral-3b", "display_name": "Ministral 3B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.04" }, "completion": { "unit": "per_M_tokens", "price": "0.04" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Ministral 3B is a 3B parameter model optimized for on-device and edge computing. It excels in knowledge, commonsense reasoning, and function-calling, outperforming larger models like Mistral 7B on most benchmarks. Supporting up to 128k context length, it's ideal for orchestrating agentic workflows and specialist tasks with efficient inference.", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "open_weights": true, "pdf_input": true, "stream": true }, "released_at": "2024-10-22", "knowledge_cutoff": "2024-03", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "ministral", "docs_url": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.ministral-3b-2410-offer?tab=Overview", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "anthropic/pioneer/ministral-3b", "mistral/ministral-3b", "mistralai/ministral-3b" ], "intro_i18n": { "zh-CN": "一款紧凑高效的模型，适用于设备端任务，如助手和本地分析，提供低延迟性能。", "zh-TW": "一款緊湊高效的模型，適用於裝置端任務，如助手與本地分析，提供低延遲效能。", "ja-JP": "アシスタントやローカル分析などのオンデバイスタスク向けのコンパクトで高効率なモデルで、低遅延性能を実現します。", "ru-RU": "Компактная и эффективная модель для задач на устройстве, таких как ассистенты и локальная аналитика, с низкой задержкой." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-03", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-08-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-08-01", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-15", "kind": "limit", "old": "128000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Ministral 3B" } ] }, { "slug": "mistral/ministral-3b-2512", "model_name": "ministral-3b-2512", "display_name": "ministral-3b-2512", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "intro": "The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.", "capabilities": { "function_calling": true, "structured_output": true, "vision": true, "prompt_caching": true, "pdf_input": true, "open_weights": true, "stream": true, "image_output": true }, "max_input_tokens": 131072, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "released_at": "2025-12-03", "max_output_tokens": 256000, "parameters": { "unsupported": [ "temperature" ] }, "family": "ministral", "benchmarks": { "intelligence_index": 7.1, "coding_index": 4.8, "agentic_index": 1.6 }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/ministral-3b-2512" ], "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "256000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "32768", "new": "256000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "32768", "new": "256000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "256000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "32768", "new": "256000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "256000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "32768", "new": "256000", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "256000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "8192", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Ministral 3B" } ] }, { "slug": "mistral/ministral-3b-latest", "model_name": "ministral-3b-latest", "display_name": "Ministral 3B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.04" }, "completion": { "unit": "per_M_tokens", "price": "0.04" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.04" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.04" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.04" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.04" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "completion from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1.25", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "released_at": "2024-10-01", "knowledge_cutoff": "2024-10", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "ministral", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "parallel_function_calling": true, "assistant_prefill": true, "stream": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/ministral-3b-latest" ], "intro_i18n": { "zh-CN": "Ministral 3B 是 Mistral 推出的顶级边缘模型。", "zh-TW": "Ministral 3B 是 Mistral 的頂級邊緣模型。", "ja-JP": "Ministral 3Bは、Mistralの最上位エッジモデルです。", "ru-RU": "Ministral 3B — это флагманская модель edge-класса от Mistral." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-06", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "assistant_prefill: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/ministral-8b", "model_name": "ministral-8b", "display_name": "Ministral 8B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.", "capabilities": { "vision": true, "function_calling": true, "open_weights": true, "pdf_input": true, "stream": true }, "released_at": "2024-10-01", "knowledge_cutoff": "2024-10", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "ministral", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/ministral-8b", "mistralai/ministral-8b" ], "intro_i18n": { "zh-CN": "一款更强大的模型，推理速度更快、内存效率更高，适用于复杂工作流和高要求的边缘应用。", "zh-TW": "一款更強大的模型，具備更快且記憶體效率更高的推理能力，適合複雜工作流程與高需求邊緣應用。", "ja-JP": "より高性能でメモリ効率の良い推論を実現し、複雑なワークフローや高負荷なエッジアプリケーションに最適です。", "ru-RU": "Более мощная модель с быстрой и экономной по памяти инференцией, идеально подходит для сложных рабочих процессов и требовательных edge-приложений." }, "price_history": [ { "date": "2026-08-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-08-01", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Ministral 8B" } ] }, { "slug": "mistral/ministral-8b-2512", "model_name": "ministral-8b-2512", "display_name": "ministral-8b-2512", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://mistral.ai/pricing", "max_input_tokens": 262144, "max_output_tokens": 262144, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "open_weights": true, "stream": true, "image_output": true }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "intro": "Ministral 3 8B is a balanced, efficient multimodal model offering strong text and vision capabilities, optimized for edge and local deployment.", "released_at": "2025-12-03", "parameters": { "unsupported": [ "temperature" ] }, "family": "ministral", "benchmarks": { "intelligence_index": 9, "coding_index": 9.7, "agentic_index": 1.2 }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/ministral-8b-2512" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "mistral/ministral-8b-latest", "model_name": "ministral-8b-latest", "display_name": "Ministral 8B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "completion from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads", "released_at": "2024-10-01", "knowledge_cutoff": "2024-10", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "ministral", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://mistral.ai/pricing", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/ministral-8b-latest" ], "intro_i18n": { "zh-CN": "Ministral 8B 是 Mistral 推出的高性价比边缘模型。", "zh-TW": "Ministral 8B 是 Mistral 推出的高性價比邊緣模型。", "ja-JP": "Ministral 8Bは、Mistralによる高コストパフォーマンスのエッジモデルです。", "ru-RU": "Ministral 8B — высокоэффективная модель edge-класса от Mistral с оптимальным соотношением цена/качество." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/mistral-7b", "model_name": "mistral-7b", "display_name": "Mistral 7B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "capabilities": { "prompt_caching": true, "open_weights": true }, "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "text_generation", "family": "Mistral", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "accounts/fireworks/models/mistral-7b" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Mistral 7B" } ] }, { "slug": "mistral/mistral-code-fim-latest", "model_name": "mistral-code-fim-latest", "display_name": "mistral-code-fim-latest", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.9" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 256000, "modalities": { "input": [ "text", "code" ], "output": [ "text", "code" ] }, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "mistral-code-fim-latest" } ] }, { "slug": "mistral/mistral-code-latest", "model_name": "mistral-code-latest", "display_name": "Mistral Code Latest", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.9" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 256000, "modalities": { "input": [ "text", "code" ], "output": [ "text", "code" ] }, "model_type": "text_generation", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2026-06-02", "max_output_tokens": 32768, "family": "mistral", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Mistral Code Latest" } ] }, { "slug": "mistral/mistral-embed", "model_name": "mistral-embed", "display_name": "Mistral Embed", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "completion from pydantic-prices conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2023-12-11", "max_input_tokens": 8000, "max_output_tokens": 3072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mistral-embed", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": {}, "model_type": "text_embedding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-embed" ], "intro_i18n": { "zh-CN": "一款通用文本嵌入模型，适用于语义搜索、相似度计算、聚类和 RAG 工作流。", "zh-TW": "一款通用文本嵌入模型，適用於語意搜尋、相似度分析、聚類與 RAG 工作流程。", "ja-JP": "意味検索、類似性評価、クラスタリング、RAGワークフローに対応した汎用テキスト埋め込みモデルです。", "ru-RU": "Универсальная модель встраивания текста для семантического поиска, оценки схожести, кластеризации и RAG-процессов." } }, { "slug": "mistral/mistral-embed-2312", "model_name": "mistral-embed-2312", "display_name": "Mistral: Mistral Embed 2312", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "portkey" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 8192, "model_type": "text_embedding", "capabilities": { "stream": true }, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/mistral-embed-2312" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Mistral: Mistral Embed 2312" } ] }, { "slug": "mistral/mistral-embed-dim128-2510", "model_name": "mistral-embed-dim128-2510", "display_name": "mistral-embed-dim128-2510", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "model_type": "text_embedding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "mistral-embed-dim128-2510" } ] }, { "slug": "mistral/mistral-embed-dim256-2510", "model_name": "mistral-embed-dim256-2510", "display_name": "mistral-embed-dim256-2510", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "embedding" ] }, "model_type": "text_embedding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "mistral-embed-dim256-2510" } ] }, { "slug": "mistral/mistral-large", "model_name": "mistral-large", "display_name": "Mistral Large 2411", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement here.", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "released_at": "2024-01-01", "max_input_tokens": 128000, "max_output_tokens": 256000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mistral-large", "knowledge_cutoff": "2024-11", "model_type": "text_generation", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "defaults": { "temperature": 0.3 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-large", "mistralai/mistral-large" ], "intro_i18n": { "zh-CN": "Mixtral Large 是 Mistral 的旗舰模型，结合代码生成、数学和推理能力，支持 128K 上下文窗口。", "zh-TW": "Mixtral Large 是 Mistral 的旗艦模型，結合代碼生成、數學與推理能力，支援 128K 上下文視窗。", "ja-JP": "Mixtral Largeは、Mistralのフラッグシップモデルで、コード生成、数学、推論を128Kのコンテキストウィンドウで実現します。", "ru-RU": "Mixtral Large — флагманская модель от Mistral, сочетающая генерацию кода, математику и рассуждение с контекстным окном на 128K." }, "price_history": [ { "date": "2026-07-15", "kind": "limit", "old": "25600", "new": "256000", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Mistral Large" } ] }, { "slug": "mistral/mistral-large-2402", "model_name": "mistral-large-2402", "display_name": "mistral-large-2402", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 32000, "max_output_tokens": 8191, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2025-06-16", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "assistant_prefill": true, "stream": true }, "intro": "Mistral Large (24.02) is Mistral AI’s most advanced language model, built for complex multilingual reasoning, code generation, and deep text understanding.", "released_at": "2025-05-26", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "family": "mistral-large", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral.mistral-large-2402-v1:0" ], "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/mistral-large-2407", "model_name": "mistral-large-2407", "display_name": "mistral-large-2407", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "9" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "prompt from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "9" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2025-03-30", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "stream": true }, "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "released_at": "2024-11-19", "knowledge_cutoff": "2024-03", "modalities": { "input": [ "text", "pdf" ], "output": [ "text" ] }, "family": "mistral-large", "docs_url": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-ai-large-2407-offer?tab=Overview", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "defaults": { "temperature": 0.3 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Mistral-large-2407", "mistral.mistral-large-2407-v1:0", "mistralai/mistral-large-2407" ], "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "open_weights: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/mistral-large-2411", "model_name": "mistral-large-2411", "display_name": "Mistral Large 2.1", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "prompt from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from portkey conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "released_at": "2024-11-18", "knowledge_cutoff": "2024-11", "max_input_tokens": 131072, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mistral-large", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "assistant_prefill": true, "stream": true }, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-05-31", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-large-2411", "mistralai/mistral-large-2411" ], "intro_i18n": { "zh-CN": "Mistral 的旗舰模型，适用于需要大规模推理或专业化的复杂任务（如合成文本生成、代码生成、RAG 或智能体）。", "zh-TW": "Mistral 的旗艦模型，適用於需要大規模推理或專業化的複雜任務（如合成文本生成、代碼生成、RAG 或智能代理）。", "ja-JP": "Mistralのフラッグシップモデルで、大規模な推論や専門性を要する複雑なタスク（合成テキスト生成、コード生成、RAG、エージェントなど）に対応します。", "ru-RU": "Флагманская модель Mistral для сложных задач, требующих масштабного рассуждения или специализации (генерация синтетического текста, кода, RAG или агенты)." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/mistral-large-2512", "model_name": "mistral-large-2512", "display_name": "Mistral Large 3", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "pydantic-prices" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+pydantic-prices", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "pydantic-prices" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Mistral's largest general model for enterprise agents, coding, and multilingual reasoning", "released_at": "2024-11-01", "knowledge_cutoff": "2024-11", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "mistral-large", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "assistant_prefill": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://docs.mistral.ai/models/mistral-large-3-25-12", "model_type": "vision_understanding", "benchmarks": { "intelligence_index": 15.9, "coding_index": 20.1, "agentic_index": 5.5 }, "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "defaults": { "temperature": 0.0645 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-large-2512", "mistralai/mistral-large-2512" ], "intro_i18n": { "zh-CN": "Mistral Large 3是一款最先进的开源权重通用多模态模型，采用精细的专家混合架构。拥有410亿激活参数和6750亿总参数。", "zh-TW": "Mistral Large 3是一款最先進的開源權重通用多模態模型，採用精細的專家混合架構。具有41B激活參數及675B總參數。", "ja-JP": "Mistral Large 3は、最先端のオープンウェイト汎用マルチモーダルモデルで、粒度の細かいエキスパートの混合アーキテクチャを備えています。41Bアクティブパラメータ、675B総パラメータを特徴とします。", "ru-RU": "Mistral Large 3 — передовая мультимодальная модель общего назначения с открытым весом и архитектурой Mixture of Experts. Имеет 41B активных параметров и 675B общих параметров." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/mistral-large-3", "model_name": "mistral-large-3", "display_name": "mistral-large-3", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://docs.mistral.ai/models/mistral-large-3-25-12", "max_input_tokens": 262144, "max_output_tokens": 262144, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "open_weights": true }, "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "released_at": "2025-12-02", "knowledge_cutoff": "2024-10", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "mistral-large", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-large-3", "mistralai/mistral-large-3" ], "price_history": [ { "date": "2026-08-05", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-05", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-09", "kind": "capability", "note": "open_weights: true→false" } ] }, { "slug": "mistral/mistral-large-latest", "model_name": "mistral-large-latest", "display_name": "Mistral Large", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+truefoundry", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "prompt from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6" }, "message": "completion from llm-prices-www conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Flagship Mistral model for advanced reasoning, coding, and multilingual work", "released_at": "2024-11-01", "knowledge_cutoff": "2024-11", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "mistral-large", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true, "stream": true }, "docs_url": "https://docs.mistral.ai/models/mistral-large-3-25-12", "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-large-latest" ], "intro_i18n": { "zh-CN": "Mistral Large是旗舰模型，擅长多语言任务、复杂推理和代码生成，非常适合高端应用。", "zh-TW": "Mistral Large是旗艦模型，擅長多語言任務、複雜推理及代碼生成，非常適合高端應用。", "ja-JP": "Mistral Largeは、マルチリンガルタスク、複雑な推論、コード生成に優れたフラッグシップモデルで、高度なアプリケーションに最適です。", "ru-RU": "Mistral Large — флагманская модель, превосходящая в многоязычных задачах, сложных рассуждениях и генерации кода для высококлассных приложений." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/mistral-large-pixtral-2411", "model_name": "mistral-large-pixtral-2411", "display_name": "mistral-large-pixtral-2411", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "vision_understanding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "mistral-large-pixtral-2411" } ] }, { "slug": "mistral/mistral-large-veteran-2512", "model_name": "mistral-large-veteran-2512", "display_name": "mistral-large-veteran-2512", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 262144, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "mistral-large-veteran-2512" } ] }, { "slug": "mistral/mistral-medium", "model_name": "mistral-medium", "display_name": "mistral-medium", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.7" }, "completion": { "unit": "per_M_tokens", "price": "8.1" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.7" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "prompt from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "8.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "completion from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 32000, "max_output_tokens": 8191, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "stream": true }, "modalities": { "input": [ "image" ], "output": [] }, "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "released_at": "2025-05-07", "knowledge_cutoff": "2024-10", "family": "mistral-medium", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-medium", "mistralai/mistral-medium" ], "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "mistral/mistral-medium-2312", "model_name": "mistral-medium-2312", "display_name": "mistral-medium-2312", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.7" }, "completion": { "unit": "per_M_tokens", "price": "8.1" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 32000, "max_output_tokens": 8191, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2025-06-16", "capabilities": { "structured_output": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/mistral-medium-2505", "model_name": "mistral-medium-2505", "display_name": "Mistral Medium 3", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "released_at": "2025-05-07", "knowledge_cutoff": "2025-05", "max_input_tokens": 131072, "max_output_tokens": 131072, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "mistral-medium", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "stream": true, "parallel_function_calling": true }, "model_type": "vision_understanding", "deprecation_date": "2026-08-31", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-medium-2505" ], "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-30", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-09", "kind": "capability", "note": "video_input: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/mistral-medium-2508", "model_name": "mistral-medium-2508", "display_name": "Mistral Medium 3.1", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "released_at": "2025-08-12", "knowledge_cutoff": "2025-05", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "mistral-medium", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://mistral.ai/news/mistral-medium-3", "model_type": "vision_understanding", "deprecation_date": "2026-08-31", "deprecated": true, "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Mistral Medium 3.1以8倍更低的成本提供最先进的性能，并简化企业部署。", "zh-TW": "Mistral Medium 3.1以8倍更低的成本提供最先進性能，簡化企業部署。", "ja-JP": "Mistral Medium 3.1は、8倍低コストで最先端のパフォーマンスを提供し、エンタープライズ展開を簡素化します。", "ru-RU": "Mistral Medium 3.1 обеспечивает передовую производительность при 8-кратном снижении затрат и упрощает развертывание в корпоративной среде." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/mistral-medium-2604", "model_name": "mistral-medium-2604", "display_name": "Mistral Medium 3.5", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+truefoundry", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Balanced Mistral model for enterprise assistants, multilingual work, and tools", "released_at": "2026-04-29", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "mistral-medium", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true }, "docs_url": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "mistral/mistral-medium-3", "model_name": "mistral-medium-3", "display_name": "Mistral Medium 3", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "intro": "Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost compared to traditional large models, making it suitable for scalable deployments across professional and industrial use cases.", "capabilities": { "function_calling": true, "structured_output": true, "vision": true, "pdf_input": true, "prompt_caching": true, "stream": true }, "max_input_tokens": 262144, "deprecated": true, "modalities": { "input": [ "image", "text", "pdf", "doc" ], "output": [ "text" ] }, "model_type": "vision_understanding", "released_at": "2025-09-25", "max_output_tokens": 32768, "family": "mistral-medium", "knowledge_cutoff": "2025-03", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "defaults": { "temperature": 0.3 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/mistral-medium-3" ], "price_history": [ { "date": "2026-07-15", "kind": "limit", "old": "40000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-07-13", "kind": "limit", "old": "26215", "new": "40000", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Mistral: Mistral Medium 3" } ] }, { "slug": "mistral/mistral-medium-3-1-2508", "model_name": "mistral-medium-3-1-2508", "display_name": "mistral-medium-3-1-2508", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://mistral.ai/news/mistral-medium-3", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "vision_understanding", "deprecation_date": "2026-08-31", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "mistral/mistral-medium-3-5", "model_name": "mistral-medium-3-5", "display_name": "mistral-medium-3-5", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+truefoundry", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "truefoundry" } } ], "verification_status": "cross_checked" }, "provider_model_id": "mistral-medium-3.5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "max_input_tokens": 262144, "max_output_tokens": 262144, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "open_weights": true }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "released_at": "2026-04-30", "knowledge_cutoff": "2024-11", "intro": "Mistral Medium 3.5 is a frontier multimodal 128B model combining reasoning, coding, and instruction-following with strong agentic performance and efficient deployment.", "parameters": { "unsupported": [ "temperature" ] }, "family": "mistral-medium", "benchmarks": { "intelligence_index": 30.4, "coding_index": 46.9, "agentic_index": 19.2 }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral-medium-3.5", "mistral/mistral-medium-3-5", "mistral/mistral-medium-3.5", "mistral/mistral-medium-3.5:thinking", "mistralai/mistral-medium-3-5" ], "intro_i18n": { "zh-CN": "Mistral Medium 3.5 是一款前沿级多模态模型，针对代理和编程用例进行了优化，以修改后的 MIT 许可证形式发布为开源权重。", "zh-TW": "Mistral Medium 3.5 是一款前沿級多模態模型，針對代理和編程使用場景進行了優化，並以修改版 MIT 許可證形式發布為開源權重。", "ja-JP": "Mistral Medium 3.5は、エージェントおよびコーディングユースケース向けに最適化されたフロンティアクラスのマルチモーダルモデルで、修正版MITライセンスの下でオープンウェイトとしてリリースされています。", "ru-RU": "Mistral Medium 3.5 — это передовая мультимодальная модель, оптимизированная для агентных и программных сценариев использования, выпущенная с открытым весом по модифицированной лицензии MIT." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "berget", "charge": "completion", "old": "5.7681632", "new": "5.76166795" }, { "date": "2026-08-14", "kind": "price", "provider": "berget", "charge": "prompt", "old": "1.73044896", "new": "1.728500385" }, { "date": "2026-08-13", "kind": "price", "provider": "berget", "charge": "completion", "old": "5.7728041", "new": "5.7681632" }, { "date": "2026-08-13", "kind": "price", "provider": "berget", "charge": "prompt", "old": "1.73184123", "new": "1.73044896" }, { "date": "2026-08-12", "kind": "price", "provider": "berget", "charge": "completion", "old": "5.77674015", "new": "5.7728041" }, { "date": "2026-08-12", "kind": "price", "provider": "berget", "charge": "prompt", "old": "1.733022045", "new": "1.73184123" }, { "date": "2026-08-11", "kind": "price", "provider": "berget", "charge": "completion", "old": "5.7801792", "new": "5.77674015" }, { "date": "2026-08-11", "kind": "price", "provider": "berget", "charge": "prompt", "old": "1.73405376", "new": "1.733022045" }, { "date": "2026-08-10", "kind": "price", "provider": "berget", "charge": "completion", "old": "5.77930585", "new": "5.7801792" }, { "date": "2026-08-10", "kind": "price", "provider": "berget", "charge": "prompt", "old": "1.733791755", "new": "1.73405376" }, { "date": "2026-08-09", "kind": "price", "provider": "berget", "charge": "completion", "old": "5.76162225", "new": "5.77930585" }, { "date": "2026-08-09", "kind": "price", "provider": "berget", "charge": "prompt", "old": "1.728486675", "new": "1.733791755" }, { "date": "2026-08-08", "kind": "price", "provider": "berget", "charge": "completion", "old": "5.7764259", "new": "5.76162225" }, { "date": "2026-08-08", "kind": "price", "provider": "berget", "charge": "prompt", "old": "1.73292777", "new": "1.728486675" }, { "date": "2026-08-07", "kind": "price", "provider": "berget", "charge": "completion", "old": "5.768647", "new": "5.7764259" }, { "date": "2026-08-07", "kind": "price", "provider": "berget", "charge": "prompt", "old": "1.7305941", "new": "1.73292777" }, { "date": "2026-08-06", "kind": "price", "provider": "berget", "charge": "completion", "old": "5.75504175", "new": "5.768647" }, { "date": "2026-08-06", "kind": "price", "provider": "berget", "charge": "prompt", "old": "1.726512525", "new": "1.7305941" }, { "date": "2026-08-05", "kind": "price", "provider": "berget", "charge": "completion", "old": "5.76461085", "new": "5.75504175" }, { "date": "2026-08-05", "kind": "price", "provider": "berget", "charge": "prompt", "old": "1.729383255", "new": "1.726512525" } ] }, { "slug": "mistral/mistral-medium-3-5-0", "model_name": "mistral-medium-3-5-0", "display_name": "mistral-medium-3-5-0", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 262144, "modalities": { "input": [ "text", "image", "doc" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "reasoning": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "mistral-medium-3-5-0" } ] }, { "slug": "mistral/mistral-medium-c21211-r0-75", "model_name": "mistral-medium-c21211-r0-75", "display_name": "mistral-medium-c21211-r0-75", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 262144, "modalities": { "input": [ "text", "image", "doc" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "mistral-medium-c21211-r0-75" } ] }, { "slug": "mistral/mistral-medium-latest", "model_name": "mistral-medium-latest", "display_name": "Mistral Medium", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+truefoundry", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "prompt from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "7.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "completion from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "7.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Balanced Mistral model for enterprise assistants, multilingual work, and tools", "released_at": "2026-04-29", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "mistral-medium", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true, "stream": true }, "docs_url": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04", "model_type": "vision_understanding", "knowledge_cutoff": "2025-05", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-medium-latest" ], "price_history": [ { "date": "2026-08-01", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-04", "kind": "price", "provider": "mistral", "charge": "completion", "old": "2", "new": "7.5" }, { "date": "2026-07-04", "kind": "price", "provider": "mistral", "charge": "prompt", "old": "0.4", "new": "1.5" }, { "date": "2026-07-02", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/mistral-moderation-2411", "model_name": "mistral-moderation-2411", "display_name": "mistral-moderation-2411", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 8192, "deprecated": true, "model_type": "safety_detection", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "mistral-moderation-2411" } ] }, { "slug": "mistral/mistral-moderation-2603", "model_name": "mistral-moderation-2603", "display_name": "mistral-moderation-2603", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "safety_detection", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "mistral-moderation-2603" } ] }, { "slug": "mistral/mistral-moderation-latest", "model_name": "mistral-moderation-latest", "display_name": "mistral-moderation-latest", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 8192, "deprecated": true, "modalities": { "input": [ "text" ], "output": [] }, "model_type": "safety_detection", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-07", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-03", "kind": "listed", "note": "mistral-moderation-latest" } ] }, { "slug": "mistral/mistral-nemo", "model_name": "mistral-nemo", "display_name": "Mistral Nemo", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+pydantic-prices+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Efficient Mistral-NVIDIA open model for multilingual chat and local deployment", "released_at": "2024-07-01", "knowledge_cutoff": "2024-07", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mistral-nemo", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "model_type": "text_generation", "docs_url": "https://azuremarketplace.microsoft.com/en/marketplace/apps/000-000.mistral-nemo-12b-2407?tab=PlansAndPrice", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.3 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral-nemo:free", "mistral/mistral-nemo", "mistralai/mistral-nemo", "novita/mistralai/mistral-nemo" ], "intro_i18n": { "zh-CN": "Mistral Nemo 是一款前沿大语言模型，在其参数规模下具备最先进的推理、世界知识和编程能力。", "zh-TW": "Mistral Nemo 是一款先進的大型語言模型，具備同級最佳的推理能力、世界知識與編碼能力。", "ja-JP": "Mistral Nemoは、同サイズ帯で最先端の推論力、世界知識、コーディング能力を備えた先進的なLLMです。", "ru-RU": "Mistral Nemo — передовая LLM с выдающимися возможностями рассуждения, знаниями о мире и кодированием для своей размерности." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-08-01", "kind": "capability", "note": "prompt_caching: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/mistral-ocr-4", "model_name": "mistral-ocr-4", "display_name": "mistral-ocr-4", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "4000" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "vision_understanding", "price_history": [ { "date": "2026-08-04", "kind": "listed", "note": "mistral-ocr-4" } ] }, { "slug": "mistral/mistral-ocr-4-0", "model_name": "mistral-ocr-4-0", "display_name": "mistral-ocr-4-0", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "4000" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "vision_understanding", "price_history": [ { "date": "2026-08-04", "kind": "listed", "note": "mistral-ocr-4-0" } ] }, { "slug": "mistral/mistral-ocr-latest", "model_name": "mistral-ocr-latest", "display_name": "mistral-ocr-latest", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "4000" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "vision_understanding", "price_history": [ { "date": "2026-08-04", "kind": "listed", "note": "mistral-ocr-latest" } ] }, { "slug": "mistral/mistral-saba", "model_name": "mistral-saba", "display_name": "Mistral Saba", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional datasets, it supports multiple Indian-origin languages—including Tamil and Malayalam—alongside Arabic. This makes it a versatile option for a range of regional and multilingual applications. Read more at the blog post here", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "released_at": "2024-01-01", "max_input_tokens": 32000, "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mistral", "knowledge_cutoff": "2024-09", "deprecated": true, "model_type": "text_generation", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "defaults": { "temperature": 0.3 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/mistral-saba" ], "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "open_weights: true→false" }, { "date": "2026-08-03", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-15", "kind": "limit", "old": "32768", "new": "32000", "note": "max_input_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Mistral: Saba" } ] }, { "slug": "mistral/mistral-saba-latest", "model_name": "mistral-saba-latest", "display_name": "Mistral Saba", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Mistral Saba" } ] }, { "slug": "mistral/mistral-small", "model_name": "mistral-small", "display_name": "mistral-small", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.015" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+truefoundry", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.6" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.7" }, "message": "prompt from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.7" }, "message": "completion from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.75", "completion": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 32000, "max_output_tokens": 8191, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "parallel_function_calling": true, "open_weights": true, "stream": true }, "modalities": { "input": [ "text", "image", "doc" ], "output": [ "text" ] }, "intro": "Efficient Mistral model for fast chat, extraction, and production assistants", "released_at": "2025-06-20", "knowledge_cutoff": "2025-03", "family": "mistral-small", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-small", "mistralai/mistral-small" ], "intro_i18n": { "zh-CN": "Mistral Small 适用于任何需要高效率和低延迟的语言任务。", "zh-TW": "Mistral Small 適用於任何需要高效率與低延遲的語言任務。", "ja-JP": "Mistral Smallは、高効率かつ低遅延を求めるあらゆる言語タスクに適しています。", "ru-RU": "Mistral Small подходит для любых языковых задач, где важны высокая эффективность и низкая задержка." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.346089792", "new": "0.345700077" }, { "date": "2026-08-14", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.346089792", "new": "0.345700077" }, { "date": "2026-08-13", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.346368246", "new": "0.346089792" }, { "date": "2026-08-13", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.346368246", "new": "0.346089792" }, { "date": "2026-08-12", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.346604409", "new": "0.346368246" }, { "date": "2026-08-12", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.346604409", "new": "0.346368246" }, { "date": "2026-08-11", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.346810752", "new": "0.346604409" }, { "date": "2026-08-11", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.346810752", "new": "0.346604409" }, { "date": "2026-08-10", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.346758351", "new": "0.346810752" }, { "date": "2026-08-10", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.346758351", "new": "0.346810752" }, { "date": "2026-08-09", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.345697335", "new": "0.346758351" }, { "date": "2026-08-09", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.345697335", "new": "0.346758351" }, { "date": "2026-08-08", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.346585554", "new": "0.345697335" }, { "date": "2026-08-08", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.346585554", "new": "0.345697335" }, { "date": "2026-08-07", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.34611882", "new": "0.346585554" }, { "date": "2026-08-07", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.34611882", "new": "0.346585554" }, { "date": "2026-08-06", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.345302505", "new": "0.34611882" }, { "date": "2026-08-06", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.345302505", "new": "0.34611882" }, { "date": "2026-08-05", "kind": "price", "provider": "berget", "charge": "completion", "old": "0.345876651", "new": "0.345302505" }, { "date": "2026-08-05", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.345876651", "new": "0.345302505" } ] }, { "slug": "mistral/mistral-small-2409", "model_name": "mistral-small-2409", "display_name": "mistral-small-2409", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "mistral-small-2409" } ] }, { "slug": "mistral/Mistral-Small-24B-Instruct-2501", "model_name": "Mistral-Small-24B-Instruct-2501", "display_name": "Mistral Small 3", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.05" }, "completion": { "unit": "per_M_tokens", "price": "0.08" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" }, "provider_model_id": "mistral-small-24b-instruct-2501" } ], "intro": "Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment.", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "released_at": "2025-01-30", "knowledge_cutoff": "2023-10", "max_input_tokens": 32768, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mistral-small", "model_type": "text_generation", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p" ], "defaults": { "temperature": 0.3 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "accounts/fireworks/models/mistral-small-24b-instruct-2501", "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501", "mistral-small-24b-instruct-2501", "mistral-small-24b-instruct-2501:free", "mistralai/Mistral-Small-24B-Instruct-2501", "mistralai/mistral-small-24b-instruct-2501", "unsloth/Mistral-Small-24B-Instruct-2501" ], "intro_i18n": { "zh-CN": "一个拥有 240 亿参数的模型，具备与更大模型相当的先进能力。", "zh-TW": "一個具備 24B 參數的模型，擁有與更大型模型相當的先進能力。", "ja-JP": "24Bパラメータを持つモデルで、より大規模なモデルに匹敵する最先端の性能を発揮します。", "ru-RU": "Модель с 24 миллиардами параметров, обладающая передовыми возможностями, сопоставимыми с более крупными моделями." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Mistral: Mistral Small 3" } ] }, { "slug": "mistral/mistral-small-2501", "model_name": "mistral-small-2501", "display_name": "mistral-small-2501", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "mistral-small-2501" } ] }, { "slug": "mistral/mistral-small-2503", "model_name": "mistral-small-2503", "display_name": "mistral-small-2503", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "stream": true }, "intro": "Combines advanced text and vision capabilities with 24 billion parameters, supporting multilingual tasks and long contexts up to 131k tokens, making it versatile for various applications without sacrificing performance.", "released_at": "2025-03-20", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "knowledge_cutoff": "2024-09", "family": "mistral-small", "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-small-2503", "mistralai/mistral-small-2503" ], "intro_i18n": { "zh-CN": "Mistral Small 适用于任何需要高效率和低延迟的语言任务。", "zh-TW": "Mistral Small 適用於任何需要高效率與低延遲的語言任務。", "ja-JP": "Mistral Smallは、高効率かつ低遅延を求めるあらゆる言語タスクに適しています。", "ru-RU": "Mistral Small подходит для любых задач, связанных с языком, где важны высокая эффективность и низкая задержка." }, "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "128000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "32768", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "32768", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "128000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "32768", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "128000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "32768", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "128000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-03", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-09", "kind": "capability", "note": "video_input: true→false" }, { "date": "2026-07-09", "kind": "capability", "note": "open_weights: true→false" }, { "date": "2026-07-03", "kind": "listed", "note": "Mistral Small 3.1" } ] }, { "slug": "mistral/mistral-small-2506", "model_name": "mistral-small-2506", "display_name": "Mistral Small 3.2", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Efficient Mistral model for fast chat, extraction, and production assistants", "released_at": "2025-06-20", "knowledge_cutoff": "2025-03", "max_input_tokens": 128000, "max_output_tokens": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "mistral-small", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "parallel_function_calling": true, "stream": true }, "deprecated": true, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Mistral Small是翻译、摘要和情感分析的经济高效、快速且可靠的选择。", "zh-TW": "Mistral Small是一款成本效益高、快速且可靠的選擇，適用於翻譯、摘要及情感分析。", "ja-JP": "Mistral Smallは、翻訳、要約、感情分析においてコスト効率が高く、迅速かつ信頼性の高いオプションです。", "ru-RU": "Mistral Small — экономичный, быстрый и надежный вариант для перевода, суммаризации и анализа настроений." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/mistral-small-2603", "model_name": "mistral-small-2603", "display_name": "Mistral Small 4", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.015" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "intro": "Fast Mistral production model for chat, extraction, and cost-sensitive agents", "released_at": "2026-03-16", "knowledge_cutoff": "2025-06", "max_input_tokens": 256000, "max_output_tokens": 256000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "mistral-small", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true }, "docs_url": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03", "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 19.7, "coding_index": 26.6, "agentic_index": 4.6 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-small-2603", "mistralai/mistral-small-2603" ], "intro_i18n": { "zh-CN": "Mistral的强大混合模型，将指令、推理和编码能力统一于单一模型中。拥有1190亿参数，其中65亿为激活参数。", "zh-TW": "Mistral的強大混合模型，將指令、推理及編程能力統一於一個模型中。119B參數，6.5B激活。", "ja-JP": "Mistralの強力なハイブリッドモデルで、指示、推論、コーディング機能を単一モデルに統合しています。119Bパラメータ、6.5Bアクティブ。", "ru-RU": "Мощная гибридная модель Mistral, объединяющая возможности инструкций, рассуждений и кодирования в одной модели. 119B параметров с 6.5B активных." }, "price_history": [ { "date": "2026-07-14", "kind": "capability", "note": "assistant_prefill: false→true" } ] }, { "slug": "mistral/mistral-small-3-2-24b-instruct", "model_name": "mistral-small-3-2-24b-instruct", "display_name": "Mistral Small 3.2 24B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" }, "provider_model_id": "mistral-small-3.2-24b-instruct" } ], "intro": "Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling.", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "released_at": "2025-06-20", "knowledge_cutoff": "2023-10", "max_input_tokens": 256000, "max_output_tokens": 16384, "modalities": { "input": [ "image", "text" ], "output": [ "text" ] }, "family": "mistral-small", "model_type": "vision_understanding", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.3 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral-small-3.2-24b-instruct", "mistral-small-3.2-24b-instruct:free", "mistralai/mistral-small-3.2-24b-instruct" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Mistral Small 3.2 24B Instruct" } ] }, { "slug": "mistral/mistral-small-3-2-2506", "model_name": "mistral-small-3-2-2506", "display_name": "mistral-small-3-2-2506", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.06" }, "completion": { "unit": "per_M_tokens", "price": "0.18" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://mistral.ai/pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-07-31", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/mistral-small-latest", "model_name": "mistral-small-latest", "display_name": "Mistral Small", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.06" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.18" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from llm-prices-www conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "0.5", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Efficient Mistral model for fast chat, extraction, and production assistants", "released_at": "2026-03-16", "knowledge_cutoff": "2025-06", "max_input_tokens": 256000, "max_output_tokens": 256000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "mistral-small", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "image_output": true, "assistant_prefill": true, "parallel_function_calling": true, "stream": true }, "docs_url": "https://mistral.ai/pricing", "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/mistral-small-latest" ], "intro_i18n": { "zh-CN": "Mistral Small 是一款高性价比、快速且可靠的模型，适用于翻译、摘要和情感分析。", "zh-TW": "Mistral Small 是翻譯、摘要與情感分析等任務的高效、快速且可靠選擇。", "ja-JP": "Mistral Smallは、翻訳、要約、感情分析においてコスト効率が高く、迅速かつ信頼性の高い選択肢です。", "ru-RU": "Mistral Small — экономичное, быстрое и надежное решение для перевода, суммирования и анализа тональности." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/mistral-tiny", "model_name": "mistral-tiny", "display_name": "mistral-tiny", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 32000, "max_output_tokens": 8191, "model_type": "text_generation", "capabilities": { "structured_output": true, "assistant_prefill": true }, "intro": "Note: This model is being deprecated. Recommended replacement is the newer Ministral 8B", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/mistral-tiny" ], "price_history": [ { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/mistral-tiny-2407", "model_name": "mistral-tiny-2407", "display_name": "mistral-tiny-2407", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "capabilities": { "prompt_caching": true }, "released_at": "2026-08-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "mistral-tiny-2407" } ] }, { "slug": "mistral/mistral-tiny-latest", "model_name": "mistral-tiny-latest", "display_name": "mistral-tiny-latest", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "capabilities": { "prompt_caching": true }, "released_at": "2026-08-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "mistral-tiny-latest" } ] }, { "slug": "mistral/mistral-vibe-cli-fast", "model_name": "mistral-vibe-cli-fast", "display_name": "mistral-vibe-cli-fast", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 262144, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "vision": true, "prompt_caching": true }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "mistral-vibe-cli-fast" } ] }, { "slug": "mistral/mistral-vibe-cli-latest", "model_name": "mistral-vibe-cli-latest", "display_name": "mistral-vibe-cli-latest", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "7.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "prompt from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "7.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "completion from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 262144, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "reasoning": true, "vision": true, "prompt_caching": true }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "mistral-vibe-cli-latest" } ] }, { "slug": "mistral/mistral-vibe-cli-with-tools", "model_name": "mistral-vibe-cli-with-tools", "display_name": "mistral-vibe-cli-with-tools", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 131072, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "assistant_prefill": true, "reasoning": true, "vision": true, "prompt_caching": true }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-07", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "mistral-vibe-cli-with-tools" } ] }, { "slug": "mistral/mistralai/mistral-small-3.1-24b-instruct", "model_name": "mistralai/mistral-small-3.1-24b-instruct", "display_name": "Mistral Small 3.1 24B Instruct", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.351" }, "completion": { "unit": "per_M_tokens", "price": "0.555" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" }, "provider_model_id": "mistral-small-3.1-24b-instruct" } ], "intro": "Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities.", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "released_at": "2025-03-18", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mistral-small", "knowledge_cutoff": "2023-10", "model_type": "text_generation", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 0.3 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "@cf/mistralai/mistral-small-3.1-24b-instruct", "mistral-small-3.1-24b-instruct", "mistral-small-3.1-24b-instruct:free", "mistralai/mistral-small-3.1-24b-instruct:free", "workers-ai/@cf/mistralai/mistral-small-3.1-24b-instruct" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Mistral Small 3.1 24B Instruct" } ] }, { "slug": "mistral/mixtral-8x22b-instruct", "model_name": "mixtral-8x22b-instruct", "display_name": "Mistral: Mixtral 8x22B Instruct", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.9" }, "completion": { "unit": "per_M_tokens", "price": "0.9" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Mistral's official instruct fine-tuned version of Mixtral 8x22B. It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include:\n- strong math, coding, and reasoning\n- large context length (64k)\n- fluency in English, French, Italian, German, and Spanish", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "released_at": "2024-04-17", "max_input_tokens": 65536, "max_output_tokens": 13108, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2024-01", "family": "mistral", "model_type": "text_generation", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "defaults": { "temperature": 0.3 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "accounts/fireworks/models/mixtral-8x22b-instruct", "mistral/mixtral-8x22b-instruct", "mistralai/mixtral-8x22b-instruct" ], "intro_i18n": { "zh-CN": "Mixtral MoE 8x22B Instruct v0.1 是 Mixtral MoE 8x22B v0.1 的指令微调版本，启用了聊天补全 API。", "zh-TW": "Mixtral MoE 8x22B Instruct v0.1 是 Mixtral MoE 8x22B v0.1 的指令微調版本，已啟用聊天補全 API。", "ja-JP": "Mixtral MoE 8x22B Instruct v0.1は、Mixtral MoE 8x22B v0.1の命令調整済みバージョンで、チャット補完APIが有効化されています。", "ru-RU": "Mixtral MoE 8x22B Instruct v0.1 — это дообученная на инструкциях версия модели Mixtral MoE 8x22B v0.1 с включенной поддержкой API завершения чата." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Mistral: Mixtral 8x22B Instruct" } ] }, { "slug": "mistral/mixtral-8x7b", "model_name": "mixtral-8x7b", "display_name": "Mixtral 8x7B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.7" }, "completion": { "unit": "per_M_tokens", "price": "0.7" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "capabilities": { "prompt_caching": true, "open_weights": true }, "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "text_generation", "knowledge_cutoff": "2023-09", "family": "Mixtral", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "accounts/fireworks/models/mixtral-8x7b" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Mixtral 8x7B" } ] }, { "slug": "mistral/open-codestral-mamba", "model_name": "open-codestral-mamba", "display_name": "open-codestral-mamba", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "prompt from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://mistral.ai/technology/", "max_input_tokens": 256000, "max_output_tokens": 256000, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2025-06-06", "capabilities": { "assistant_prefill": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Codestral Mamba 是一款专注于代码生成的 Mamba 2 语言模型，支持高级编程与推理任务。", "zh-TW": "Codestral Mamba 是一款專注於程式碼生成的 Mamba 2 語言模型，支援進階程式設計與推理任務。", "ja-JP": "Codestral Mambaは、コード生成に特化したMamba 2言語モデルであり、高度なコーディングおよび推論タスクをサポートします。", "ru-RU": "Codestral Mamba — языковая модель Mamba 2, ориентированная на генерацию кода, поддерживающая сложные задачи программирования и рассуждения." }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/open-mistral-7b", "model_name": "open-mistral-7b", "display_name": "Mistral 7B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "released_at": "2023-09-27", "knowledge_cutoff": "2023-12", "max_input_tokens": 8000, "max_output_tokens": 8000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mistral", "capabilities": { "function_calling": true, "structured_output": true, "open_weights": true, "assistant_prefill": true, "stream": true }, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2025-03-30", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/open-mistral-7b" ], "intro_i18n": { "zh-CN": "Mistral 7B 是一款紧凑但高性能的模型，适合批量处理和分类、文本生成等简单任务，具备良好的推理能力。", "zh-TW": "Mistral 7B 體積小但效能強，適合批次處理與分類、文字生成等簡單任務，具備穩定推理能力。", "ja-JP": "Mistral 7Bはコンパクトながら高性能であり、バッチ処理や分類、テキスト生成などのシンプルなタスクに強く、堅実な推論能力を備えています。", "ru-RU": "Mistral 7B — компактная, но производительная модель, хорошо подходящая для пакетной обработки и простых задач, таких как классификация и генерация текста, с уверенными навыками рассуждения." }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/open-mistral-nemo", "model_name": "open-mistral-nemo", "display_name": "Open Mistral Nemo", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Legacy model retained for compatibility with older integrations", "released_at": "2024-07-01", "knowledge_cutoff": "2024-07", "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mistral-nemo", "status": "deprecated", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "assistant_prefill": true }, "docs_url": "https://mistral.ai/technology/", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Mistral Nemo 是与 Nvidia 联合开发的 12B 模型，在推理和编程方面表现强劲，易于集成。", "zh-TW": "Mistral Nemo 是與 Nvidia 共同開發的 12B 模型，具備強大的推理與程式設計能力，易於整合。", "ja-JP": "Mistral Nemoは、Nvidiaと共同開発された12Bモデルで、優れた推論およびコーディング性能を持ち、統合も容易です。", "ru-RU": "Mistral Nemo — модель на 12B параметров, совместно разработанная с Nvidia, демонстрирующая высокие результаты в рассуждении и программировании, с легкой интеграцией." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" } ] }, { "slug": "mistral/open-mistral-nemo-2407", "model_name": "open-mistral-nemo-2407", "display_name": "open-mistral-nemo-2407", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "prompt from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "completion from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://mistral.ai/technology/", "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-07-31", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "assistant_prefill": true }, "released_at": "2026-08-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" } ] }, { "slug": "mistral/open-mixtral-8x22b", "model_name": "open-mixtral-8x22b", "display_name": "Mixtral 8x22B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "released_at": "2024-04-17", "knowledge_cutoff": "2024-04", "max_input_tokens": 64000, "max_output_tokens": 64000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mixtral", "capabilities": { "function_calling": true, "structured_output": true, "open_weights": true, "assistant_prefill": true, "stream": true }, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2025-03-30", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Mixtral 8x22B 是一款大型 MoE 模型，适用于复杂任务，具备强大的推理能力和更高的吞吐量。", "zh-TW": "Mixtral 8x22B 是一款大型 MoE 模型，適用於複雜任務，具備強大推理能力與高吞吐量。", "ja-JP": "Mixtral 8x22Bは、複雑なタスクに対応する大型MoEモデルで、強力な推論能力と高いスループットを提供します。", "ru-RU": "Mixtral 8x22B — крупная модель MoE для сложных задач, обеспечивающая мощные рассуждения и высокую пропускную способность." }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/open-mixtral-8x7b", "model_name": "open-mixtral-8x7b", "display_name": "Mixtral 8x7B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.7" }, "completion": { "unit": "per_M_tokens", "price": "0.7" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "released_at": "2023-12-11", "knowledge_cutoff": "2024-01", "max_input_tokens": 32000, "max_output_tokens": 32000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mixtral", "capabilities": { "function_calling": true, "structured_output": true, "open_weights": true, "assistant_prefill": true, "stream": true }, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2025-03-30", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Mixtral 8x7B 是一款稀疏 MoE 模型，提升了推理速度，适用于多语言和代码生成任务。", "zh-TW": "Mixtral 8x7B 是一款稀疏 MoE 模型，提升推理速度，適合多語言與程式碼生成任務。", "ja-JP": "Mixtral 8x7Bは、推論速度を向上させるスパースMoEモデルであり、多言語およびコード生成タスクに適しています。", "ru-RU": "Mixtral 8x7B — разреженная модель MoE, ускоряющая вывод, подходящая для многоязычных задач и генерации кода." }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/pixtral-12b", "model_name": "pixtral-12b", "display_name": "Pixtral 12B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+pydantic-prices+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Mistral vision-language model for image understanding and multimodal chat", "released_at": "2024-09-01", "knowledge_cutoff": "2024-09", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "pixtral", "capabilities": { "vision": true, "function_calling": true, "open_weights": true, "pdf_input": true, "stream": true }, "model_type": "vision_understanding", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/pixtral-12b", "mistralai/pixtral-12b" ], "intro_i18n": { "zh-CN": "一款具备图像理解与文本处理能力的 120 亿参数模型。", "zh-TW": "一款具備圖像理解與文本處理能力的 12B 模型。", "ja-JP": "画像理解とテキスト処理を備えた12Bモデルです。", "ru-RU": "Модель на 12B параметров с пониманием изображений и текста." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/pixtral-12b-2409", "model_name": "pixtral-12b-2409", "display_name": "pixtral-12b-2409", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2025-12-31", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "assistant_prefill": true, "open_weights": true, "stream": true }, "modalities": { "input": [ "image" ], "output": [] }, "intro": "Pixtral 2409 12B is a state-of-the-art multimodal model with 12B parameters and a 400M vision encoder, natively trained on interleaved text and image data. It excels in tasks spanning vision-language reasoning, instruction following, and pure text understanding, making it highly effective for real-world multimodal applications.", "released_at": "2024-11-09", "parameters": { "unsupported": [ "temperature" ] }, "knowledge_cutoff": "2024-09", "family": "pixtral", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/Pixtral-12B-2409" ], "intro_i18n": { "zh-CN": "Pixtral 擅长图表/图像理解、文档问答、多模态推理和指令遵循。支持原始分辨率/比例图像输入，能在 128K 上下文窗口中处理任意数量图像。", "zh-TW": "Pixtral 擅長圖表/圖像理解、文件問答、多模態推理與指令遵循。可原生解析圖像解析度與比例，並在 128K 上下文中處理任意數量圖像。", "ja-JP": "Pixtralは、グラフや画像の理解、文書QA、マルチモーダル推論、指示の追従に優れています。ネイティブ解像度・アスペクト比で画像を処理し、128Kのコンテキストウィンドウ内で任意の数の画像を扱えます。", "ru-RU": "Pixtral отлично справляется с анализом графиков и изображений, вопросами по документам, мультимодальным рассуждением и выполнением инструкций. Он обрабатывает изображения в их исходном разрешении и соотношении сторон, поддерживая любое количество изображений в контексте до 128K." }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-08-05", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "mistral/pixtral-large", "model_name": "pixtral-large", "display_name": "Pixtral Large (latest)", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Pixtral Large is a 124B parameter, open-weight, multimodal model built on top of Mistral Large 2. The model is able to understand documents, charts and natural images.", "capabilities": { "vision": true, "function_calling": true, "stream": true, "open_weights": true, "pdf_input": true }, "released_at": "2024-11-01", "knowledge_cutoff": "2024-11", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "family": "pixtral", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/pixtral-large" ], "intro_i18n": { "zh-CN": "Pixtral Large 是我们多模态系列的第二款模型，具备前沿级图像理解能力。可处理文档、图表和自然图像，同时保留 Mistral Large 2 的领先文本理解能力。", "zh-TW": "Pixtral Large 是我們多模態系列的第二款模型，具備前沿級圖像理解能力。可處理文件、圖表與自然圖像，同時保有 Mistral Large 2 的頂尖文本理解能力。", "ja-JP": "Pixtral Largeは、マルチモーダルファミリーの第2弾で、最先端の画像理解を備えています。文書、チャート、自然画像を処理しつつ、Mistral Large 2の優れたテキスト理解力を維持します。", "ru-RU": "Pixtral Large — вторая модель в нашей мультимодальной линейке с передовым пониманием изображений. Обрабатывает документы, графики и естественные изображения, сохраняя при этом выдающееся понимание текста от Mistral Large 2." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Pixtral Large" } ] }, { "slug": "mistral/pixtral-large-2411", "model_name": "pixtral-large-2411", "display_name": "pixtral-large-2411", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 128000, "max_output_tokens": 128000, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-05-31", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "assistant_prefill": true, "stream": true }, "modalities": { "input": [ "image" ], "output": [] }, "released_at": "2024-11-19", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistralai/pixtral-large-2411" ], "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "pdf_input: true→false" }, { "date": "2026-08-03", "kind": "capability", "note": "open_weights: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/pixtral-large-latest", "model_name": "pixtral-large-latest", "display_name": "Pixtral Large", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Mistral's larger vision model for document-heavy image understanding and chat", "released_at": "2024-11-01", "knowledge_cutoff": "2024-11", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "pixtral", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true, "stream": true }, "model_type": "vision_understanding", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/pixtral-large-latest" ], "intro_i18n": { "zh-CN": "Pixtral Large 是基于 Mistral Large 2 构建的 124B 参数开源多模态模型，是我们多模态系列中的第二款，具备前沿级图像理解能力。", "zh-TW": "Pixtral Large 是一款擁有 124B 參數的開源多模態模型，基於 Mistral Large 2 架構，是我們多模態系列中的第二代，具備前沿級圖像理解能力。", "ja-JP": "Pixtral Largeは、Mistral Large 2を基盤とした124Bパラメータのオープンマルチモーダルモデルで、最先端の画像理解を備えたPixtralファミリーの第2世代です。", "ru-RU": "Pixtral Large — это открытая мультимодальная модель с 124 миллиардами параметров, построенная на базе Mistral Large 2. Это вторая модель в нашей мультимодальной линейке, обладающая передовыми возможностями понимания изображений." }, "price_history": [ { "date": "2026-07-15", "kind": "capability", "note": "prompt_caching: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "mistral/voxtral-mini-2507", "model_name": "voxtral-mini-2507", "display_name": "voxtral-mini-2507", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0000166667" }, "prompt": { "unit": "per_M_tokens", "price": "0.04" }, "completion": { "unit": "per_M_tokens", "price": "0.04" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 16384, "deprecated": true, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "model_type": "speech_recognition", "capabilities": { "audio_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "voxtral-mini-2507" } ] }, { "slug": "mistral/voxtral-mini-2602", "model_name": "voxtral-mini-2602", "display_name": "voxtral-mini-2602", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.00005" } }, "provenance": { "base_charges": { "audio_input": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-26-02", "model_type": "speech_recognition", "capabilities": { "audio_input": true, "structured_output": true }, "max_input_tokens": 16384, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "voxtral-mini-2602" } ] }, { "slug": "mistral/voxtral-mini-latest", "model_name": "voxtral-mini-latest", "display_name": "Voxtral Mini", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.00001666666667" }, "prompt": { "unit": "per_M_tokens", "price": "0.04" }, "completion": { "unit": "per_M_tokens", "price": "0.04" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "intro": "Speech transcription model for accurate audio-to-text and captioning workflows", "released_at": "2026-02-01", "max_input_tokens": 0, "max_output_tokens": 0, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "family": "voxtral", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "audio_input": true }, "model_type": "speech_recognition", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-05", "kind": "capability", "note": "pdf_input: true→false" }, { "date": "2026-08-02", "kind": "limit", "old": "16384", "new": "0", "note": "max_input_tokens" }, { "date": "2026-08-02", "kind": "limit", "new": "0", "note": "max_output_tokens" }, { "date": "2026-07-06", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "voxtral-mini-latest" } ] }, { "slug": "mistral/voxtral-mini-realtime-2602", "model_name": "voxtral-mini-realtime-2602", "display_name": "voxtral-mini-realtime-2602", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0001" } }, "provenance": { "base_charges": { "audio_input": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "model_type": "realtime_omni", "capabilities": { "structured_output": true, "assistant_prefill": true, "audio_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "voxtral-mini-realtime-2602" } ] }, { "slug": "mistral/voxtral-mini-realtime-latest", "model_name": "voxtral-mini-realtime-latest", "display_name": "voxtral-mini-realtime-latest", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0001" } }, "provenance": { "base_charges": { "audio_input": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "model_type": "realtime_omni", "capabilities": { "structured_output": true, "audio_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "voxtral-mini-realtime-latest" } ] }, { "slug": "mistral/voxtral-mini-transcribe-2507", "model_name": "voxtral-mini-transcribe-2507", "display_name": "voxtral-mini-transcribe-2507", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0000333333" } }, "provenance": { "base_charges": { "audio_input": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 16384, "deprecated": true, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "model_type": "speech_recognition", "capabilities": { "audio_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "voxtral-mini-transcribe-2507" } ] }, { "slug": "mistral/voxtral-mini-transcribe-realtime-2602", "model_name": "voxtral-mini-transcribe-realtime-2602", "display_name": "voxtral-mini-transcribe-realtime-2602", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "litellm+truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0001" } }, "provenance": { "base_charges": { "audio_input": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://docs.mistral.ai/models/model-cards/voxtral-mini-transcribe-realtime-26-02", "model_type": "realtime_speech_recognition", "capabilities": { "audio_input": true, "structured_output": true }, "max_input_tokens": 32768, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "voxtral-mini-transcribe-realtime-2602" } ] }, { "slug": "mistral/voxtral-mini-tts-260213", "model_name": "voxtral-mini-tts-260213", "display_name": "voxtral-mini-tts-260213", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "16" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" } } ], "modalities": { "input": [ "text", "audio" ], "output": [ "audio" ] }, "model_type": "speech_synthesis", "capabilities": { "audio_input": true, "audio_output": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "voxtral-mini-tts-260213" } ] }, { "slug": "mistral/voxtral-mini-tts-2603", "model_name": "voxtral-mini-tts-2603", "display_name": "voxtral-mini-tts-2603", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "16" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "model_type": "speech_synthesis", "capabilities": { "function_calling": true, "audio_output": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "voxtral-mini-tts-2603" } ] }, { "slug": "mistral/voxtral-mini-tts-latest", "model_name": "voxtral-mini-tts-latest", "display_name": "Voxtral Mini TTS", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+truefoundry", "charges": { "speech_input": { "unit": "per_M_characters", "price": "16" } }, "provenance": { "base_charges": { "speech_input": "truefoundry" }, "verification_status": "aggregator_only" } } ], "intro": "Multilingual text-to-speech model with zero-shot voice cloning", "released_at": "2026-03-01", "max_input_tokens": 0, "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "family": "voxtral", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "function_calling": true, "audio_output": true }, "model_type": "speech_synthesis", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-02", "kind": "limit", "old": "4096", "new": "0", "note": "max_input_tokens" }, { "date": "2026-08-02", "kind": "limit", "new": "0", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "voxtral-mini-tts-latest" } ] }, { "slug": "mistral/Voxtral-Small-24B-2507", "model_name": "Voxtral-Small-24B-2507", "display_name": "Voxtral Small 24B", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "aggregator_only" }, "provider_model_id": "voxtral-small-24b-2507" } ], "intro": "Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.", "capabilities": { "function_calling": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "released_at": "2025-07-15", "knowledge_cutoff": "2025-07", "max_input_tokens": 32768, "max_output_tokens": 16384, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "family": "mistral", "model_type": "text_generation", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ], "defaults": { "temperature": 0.2, "top_p": 0.95 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral.voxtral-small-24b-2507", "mistralai/Voxtral-Small-24B-2507", "mistralai/voxtral-small-24b-2507", "voxtral-small-24b-2507" ], "price_history": [ { "date": "2026-07-30", "kind": "limit", "old": "32000", "new": "32768", "note": "max_input_tokens" }, { "date": "2026-07-30", "kind": "limit", "old": "32000", "new": "16384", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Voxtral Small 24B" } ] }, { "slug": "mistral/voxtral-small-2507", "model_name": "voxtral-small-2507", "display_name": "voxtral-small-2507", "vendor": "mistral", "pricing": [ { "provider": "mistral", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0000666667" }, "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "audio_input": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "modalities": { "input": [ "audio" ], "output": [] }, "model_type": "text_generation", "capabilities": { "function_calling": true, "audio_input": true, "prompt_caching": true, "structured_output": true, "pdf_input": true }, "intro": "Voxtral Small is a multimodal model with audio input, combining advanced speech capabilities with strong text performance for transcription, translation, and audio understanding.", "released_at": "2026-02-02", "max_output_tokens": 32000, "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-05", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-08-05", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-08-05", "kind": "limit", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "voxtral-small-2507" } ] }, { "slug": "mistral/voxtral-small-latest", "model_name": "voxtral-small-latest", "display_name": "Voxtral Small", "vendor": "mistral", "pricing": [ { "provider": "mistral", "provider_name": "Mistral", "official": true, "source": "models-dev+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "audio_input": { "unit": "per_second", "price": "0.0000666667" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "audio_input": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Instruct model with native audio input for speech understanding and tool use", "released_at": "2025-07-15", "max_input_tokens": 32000, "max_output_tokens": 32000, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "family": "voxtral", "capabilities": { "function_calling": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral/voxtral-small-latest" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-02", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-08-02", "kind": "limit", "old": "32768", "new": "32000", "note": "max_input_tokens" }, { "date": "2026-08-02", "kind": "limit", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-08-02", "kind": "price", "provider": "mistral", "charge": "completion", "old": "0.4", "new": "0.3" }, { "date": "2026-07-06", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "voxtral-small-latest" } ] }, { "slug": "moonshotai/Kimi-K2", "model_name": "Kimi-K2", "display_name": "Kimi K2", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.57" }, "completion": { "unit": "per_M_tokens", "price": "2.3" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" }, "provider_model_id": "kimi-k2" } ], "intro": "Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass.", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true }, "released_at": "2025-08-05", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2024-10", "family": "kimi-k2", "deprecated": true, "status": "deprecated", "model_type": "text_generation", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "kimi-k2", "kimi-k2:free", "moonshotai/Kimi-K2", "moonshotai/kimi-k2", "vertex/kimi-k2" ], "intro_i18n": { "zh-CN": "Kimi K2 是 Moonshot AI 推出的超大规模 MoE 模型，拥有 1 万亿总参数和每次前向传播 320 亿激活参数，专为高级工具使用、推理和代码合成等智能体能力优化。", "zh-TW": "Kimi K2 是 Moonshot AI 推出的大型 MoE 模型，總參數達 1 兆，每次前向傳遞啟用 32B，針對智能代理能力（如進階工具使用、推理與程式碼合成）進行優化。", "ja-JP": "Kimi K2は、Moonshot AIによる大規模MoEモデルで、総パラメータ1兆、1回のフォワードパスで32Bのアクティブパラメータを持ち、高度なツール使用、推論、コード合成などのエージェント機能に最適化されています。", "ru-RU": "Kimi K2 — крупная модель MoE от Moonshot AI с 1 триллионом параметров и 32 миллиардами активных на проход, оптимизирована для агентных возможностей, включая продвинутую работу с инструментами, логическое мышление и синтез кода." }, "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "128000", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "128000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "131072", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "32768", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "131072", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "32768", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "128000", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "128000", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "131072", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "32768", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "128000", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "128000", "new": "32768", "note": "max_output_tokens" } ] }, { "slug": "moonshotai/kimi-k2-0711-preview", "model_name": "kimi-k2-0711-preview", "display_name": "Kimi K2 0711", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "provider_name": "Moonshot AI", "official": true, "source": "models-dev+litellm+pydantic-prices+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Kimi model for long-context chat, coding, and agentic reasoning", "released_at": "2025-07-14", "knowledge_cutoff": "2024-10", "max_input_tokens": 131072, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "kimi-k2", "capabilities": { "function_calling": true, "prompt_caching": true, "open_weights": true, "web_search": true, "stream": true }, "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-05-25", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "moonshotai/kimi-k2-0905-preview", "model_name": "kimi-k2-0905-preview", "display_name": "Kimi K2 0905", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "provider_name": "Moonshot AI", "official": true, "source": "models-dev+litellm+pydantic-prices+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Kimi model for long-context chat, coding, and agentic reasoning", "released_at": "2025-09-05", "knowledge_cutoff": "2024-10", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "kimi-k2", "capabilities": { "function_calling": true, "prompt_caching": true, "open_weights": true, "web_search": true, "stream": true }, "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-05-25", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "moonshotai/kimi-k2-thinking", "model_name": "kimi-k2-thinking", "display_name": "Kimi K2 Thinking", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "provider_name": "Moonshot AI", "official": true, "source": "models-dev+litellm+pydantic-prices+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Thinking Kimi model for slower research passes, planning, and hard technical questions", "released_at": "2025-11-06", "knowledge_cutoff": "2024-08", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "kimi-thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "web_search": true, "stream": true, "parallel_function_calling": true }, "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-05-25", "status": "deprecated", "reasoning_config": { "mandatory": true, "budget_min": 1 }, "parameters": { "unsupported": [ "temperature" ] }, "benchmarks": { "intelligence_index": null, "coding_index": 21, "agentic_index": null }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Kimi-K2-Thinking", "Pro/moonshotai/Kimi-K2-Thinking", "accounts/fireworks/models/kimi-k2-thinking", "deepinfra/moonshotai/Kimi-K2-Thinking", "fireworks/kimi-k2-thinking", "hf:moonshotai/Kimi-K2-Thinking", "moonshotai/Kimi-K2-Thinking", "moonshotai/kimi-k2-thinking", "novita/kimi-k2-thinking" ], "intro_i18n": { "zh-CN": "kimi-k2-thinking 是 Moonshot AI 的推理模型，具有通用代理和推理能力。它擅长深度推理，并能通过多步工具使用解决复杂问题。", "zh-TW": "kimi-k2-thinking 是 Moonshot AI 的思考模型，具有通用代理和推理能力。它擅長深度推理，能通過多步工具使用解決難題。", "ja-JP": "kimi-k2-thinkingはMoonshot AIの思考モデルで、一般的なエージェント能力と推論能力を備えています。深い推論に優れ、マルチステップツールを使用して難しい問題を解決できます。", "ru-RU": "kimi-k2-thinking — это модель мышления от Moonshot AI с общими агентными и рассуждающими способностями. Она превосходно справляется с глубокими рассуждениями и может решать сложные задачи с использованием многошаговых инструментов." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.3717464", "new": "2.37250576" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.37211728", "new": "2.3717464" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59302932", "new": "0.5929366" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.37192448", "new": "2.37211728" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59298112", "new": "0.59302932" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.37120624", "new": "2.37192448" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59280156", "new": "0.59298112" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.37103408", "new": "2.37120624" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59275852", "new": "0.59280156" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.37129408", "new": "2.37103408" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59282352", "new": "0.59275852" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.37133248", "new": "2.37129408" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59283312", "new": "0.59282352" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.37114768", "new": "2.37133248" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59278692", "new": "0.59283312" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.36774304", "new": "2.37114768" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59193576", "new": "0.59278692" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.3692536", "new": "2.36774304" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.5923134", "new": "0.59193576" } ] }, { "slug": "moonshotai/kimi-k2-thinking-turbo", "model_name": "kimi-k2-thinking-turbo", "display_name": "Kimi K2 Thinking Turbo", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "provider_name": "Moonshot AI", "official": true, "source": "models-dev+litellm+pydantic-prices+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.15" }, "completion": { "unit": "per_M_tokens", "price": "8" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Kimi reasoning model for long-horizon research, planning, and tool use", "released_at": "2025-11-06", "knowledge_cutoff": "2024-08", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "kimi-thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "open_weights": true, "web_search": true, "stream": true }, "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-05-25", "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "moonshotai/kimi-k2-thinking-turbo" ], "intro_i18n": { "zh-CN": "Kimi K2 Thinking Turbo 是 Kimi K2 Thinking 的高速版本，在保持深度推理能力的同时显著降低延迟。", "zh-TW": "Kimi K2 Thinking Turbo 是 Kimi K2 Thinking 的高速版本，在保留深度推理能力的同時大幅降低延遲。", "ja-JP": "Kimi K2 Thinking Turboは、Kimi K2 Thinkingの高速バージョンで、深い推論能力を維持しながらレイテンシを大幅に低減します。", "ru-RU": "Kimi K2 Thinking Turbo — высокоскоростная версия Kimi K2 Thinking, значительно снижает задержку при сохранении глубины рассуждений." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "moonshotai/kimi-k2-turbo-preview", "model_name": "kimi-k2-turbo-preview", "display_name": "Kimi K2 Turbo", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "provider_name": "Moonshot AI", "official": true, "source": "models-dev+litellm+pydantic-prices+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.4" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.6" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.15" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "cache_read from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.15" }, "message": "prompt from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8" }, "message": "completion from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "cache_read from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.15" }, "message": "prompt from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8" }, "message": "completion from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "cache_read from llm-prices-www conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Fast Kimi model for responsive chat, coding help, and agent loops", "released_at": "2025-09-05", "knowledge_cutoff": "2024-10", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "kimi-k2", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "web_search": true, "stream": true }, "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-05-25", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "moonshotai/kimi-k2.5", "model_name": "kimi-k2.5", "display_name": "Kimi K2.5", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "provider_name": "Moonshot AI", "official": true, "source": "models-dev+litellm+pydantic-prices+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.1" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.7", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "21", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Earlier Kimi frontier model for long-context agents, coding, and multimodal work", "released_at": "2026-01", "knowledge_cutoff": "2025-01", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "kimi-k2", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "parallel_function_calling": true }, "docs_url": "https://platform.moonshot.ai/docs/guide/kimi-k2-5-quickstart", "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "deprecated": true, "status": "deprecated", "benchmarks": { "intelligence_index": 36, "coding_index": 46.8, "agentic_index": 21.7 }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Kimi-K2.5", "Pro/moonshotai/Kimi-K2.5", "hf:moonshotai/Kimi-K2.5", "kimi-k2-5", "kimi-k2.5-free", "kimi/kimi-k2.5", "moonshot/kimi-k2.5", "moonshotai/Kimi-K2.5", "moonshotai/kimi-k2-5", "moonshotai/kimi-k2.5", "moonshotai/kimi-k2.5:thinking", "novita/kimi-k2.5" ], "intro_i18n": { "zh-CN": "Kimi K2.5 是目前最强大的 Kimi 模型，在智能体任务、编码与视觉理解方面达成开源 SOTA。支持多模态输入，并提供思维模式与非思维模式两种运行方式。", "zh-TW": "Kimi K2.5 是最強大的 Kimi 模型，在智能體任務、編碼與視覺理解上達到開源 SOTA。支援多模態輸入，並具備思考模式與非思考模式。", "ja-JP": "Kimi K2.5 は Kimi シリーズで最も高性能なモデルで、エージェントタスク、コーディング、画像理解においてオープンソース最先端性能を発揮します。マルチモーダル入力に対応し、思考モードと非思考モードの両方をサポートします。", "ru-RU": "Kimi K2.5 — самая мощная модель Kimi, обеспечивающая SOTA среди открытых моделей в агентных задачах, программировании и визуальном понимании. Поддерживает мультимодальные входы и режимы с размышлением и без него." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "3.05", "new": "4.52" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.58", "new": "0.86" }, { "date": "2026-08-14", "kind": "price", "provider": "hyper", "charge": "cache_write", "old": "0.266", "new": "0.279" }, { "date": "2026-08-14", "kind": "price", "provider": "hyper", "charge": "completion", "old": "2.8", "new": "2.94" }, { "date": "2026-08-14", "kind": "price", "provider": "hyper", "charge": "prompt", "old": "0.532", "new": "0.558" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.266", "new": "0.279" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "completion", "old": "2.8", "new": "2.94" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.532", "new": "0.558" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.11291715", "new": "3.11391381" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "completion", "old": "2.12625", "new": "3.675" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "prompt", "old": "0.39375", "new": "0.588" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "cache_write", "old": "0.279", "new": "0.266" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "completion", "old": "2.94", "new": "2.8" }, { "date": "2026-08-13", "kind": "price", "provider": "hyper", "charge": "prompt", "old": "0.558", "new": "0.532" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.279", "new": "0.266" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "2.94", "new": "2.8" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.558", "new": "0.532" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.11340393", "new": "3.11291715" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59302932", "new": "0.5929366" } ] }, { "slug": "moonshotai/kimi-k2.6", "model_name": "kimi-k2.6", "display_name": "Kimi K2.6", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "provider_name": "Moonshot AI", "official": true, "source": "models-dev+litellm+pydantic-prices+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.95" }, "completion": { "unit": "per_M_tokens", "price": "4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.16" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.16" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.1", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.95" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6.5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "27", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Multimodal Kimi workhorse for agent loops, coding tasks, and visual context", "released_at": "2026-04-21", "knowledge_cutoff": "2025-01", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "kimi-k2", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "assistant_prefill": true }, "docs_url": "https://platform.kimi.ai/docs/pricing/chat-k26", "model_type": "deep_thinking", "status": "beta", "deprecated": true, "reasoning_config": { "mandatory": false, "budget_min": 1 }, "parameters": { "unsupported": [ "temperature" ] }, "benchmarks": { "intelligence_index": 45.1, "coding_index": 61.8, "agentic_index": 31.2 }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "@cf/moonshotai/kimi-k2.6", "Kimi-K2.6", "Pro/moonshotai/Kimi-K2.6", "TEE/kimi-k2.6", "cline-pass/kimi-k2.6", "deepinfra/moonshotai/Kimi-K2.6", "fireworks/kimi-k2.6", "inceptron/kimi-k2.6", "kimi-k2-6", "kimi-k2-6:free", "kimi/kimi-k2.6", "moonshot/kimi-k2.6", "moonshotai/Kimi-K2.6", "moonshotai/kimi-k2-6", "moonshotai/kimi-k2.6", "moonshotai/kimi-k2.6:free", "moonshotai/kimi-k2.6:thinking", "nebius/moonshotai/kimi-k2.6", "novita/kimi-k2.6", "route/kimi-k2.6", "workers-ai/@cf/moonshotai/kimi-k2.6" ], "intro_i18n": { "zh-CN": "Kimi K2.6是Moonshot AI推出的开源原生多模态代理模型，在多个主流基准测试中实现了开源领域的最先进性能，包括HLE（带工具）、SWE-Bench Pro和BrowseComp。该模型采用MoE架构，总参数量达1万亿，活跃参数量为320亿，支持256K标记上下文窗口，并集成了原生多模态功能。", "zh-TW": "Kimi K2.6 是 Moonshot AI 推出的開源原生多模態代理模型，在多個主流基準測試中達到開源最先進性能，包括 HLE（配合工具）、SWE-Bench Pro 和 BrowseComp。該模型採用 MoE 架構，擁有1萬億總參數和320億活躍參數，支持256K標記上下文窗口，並整合原生多模態能力。", "ja-JP": "Kimi K2.6はMoonshot AIによるオープンソースのネイティブマルチモーダルエージェントモデルで、HLE（ツール付き）、SWE-Bench Pro、BrowseCompを含む複数の主流ベンチマークでオープンソースの最先端性能を達成しています。このモデルは1Tの総パラメータと32Bのアクティブパラメータを持つMoEアーキテクチャを採用し、256Kトークンのコンテキストウィンドウをサポートし、ネイティブなマルチモーダル機能を統合しています。", "ru-RU": "Kimi K2.6 — это открытая мультимодальная агентная модель от Moonshot AI, демонстрирующая передовые результаты на нескольких основных бенчмарках, включая HLE (с инструментами), SWE-Bench Pro и BrowseComp. Модель использует архитектуру MoE с общим количеством параметров 1T и активными параметрами 32B, поддерживает контекстное окно на 256K токенов и интегрирует встроенные мультимодальные возможности." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.435", "new": "0.42993" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "completion", "old": "3.864", "new": "3.64456" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.87", "new": "0.85986" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "4.00232205", "new": "4.00360347" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.963521975", "new": "0.963830465" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.0944", "new": "0.16" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.16", "new": "0.0976" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "2.36", "new": "4" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "4", "new": "2.44" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.5605", "new": "0.95" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.95", "new": "0.5795" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "completion", "old": "4.2", "new": "3.675" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "prompt", "old": "0.9975", "new": "0.7875" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.434", "new": "0.435" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "3.862", "new": "3.864" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.868", "new": "0.87" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "4.00294791", "new": "4.00232205" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.963672645", "new": "0.963521975" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.0976", "new": "0.16" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.16", "new": "0.1088" } ] }, { "slug": "moonshotai/kimi-k2.7-code", "model_name": "kimi-k2.7-code", "display_name": "Kimi K2.7 Code", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "provider_name": "Moonshot AI", "official": true, "source": "models-dev+pydantic-prices+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.95" }, "completion": { "unit": "per_M_tokens", "price": "4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.19" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.19" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.3", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.95" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6.5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "27", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "released_at": "2026-06-12", "knowledge_cutoff": "2025-01", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "kimi-k2", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "deep_thinking", "status": "beta", "reasoning_config": { "mandatory": true, "budget_min": 1 }, "docs_url": "https://www.alibabacloud.com/help/en/model-studio/models", "benchmarks": { "intelligence_index": 43, "coding_index": 60.8, "agentic_index": 30.3 }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "@cf/moonshotai/kimi-k2.7-code", "Kimi-K2.7-Code", "cline-pass/kimi-k2.7-code", "fireworks/kimi-k2.7-code", "hf:moonshotai/Kimi-K2.7-Code", "inceptron/kimi-k2.7-Code", "kimi-k2-7-code", "kimi-k2-7-code:free", "kimi/kimi-k2.7-code", "moonshot-ai/kimi-k2.7-code", "moonshot/kimi-k2.7-code", "moonshotai/Kimi-K2.7-Code", "moonshotai/kimi-k2-7-code", "moonshotai/kimi-k2.7-code", "moonshotai/kimi-k2.7-code-free", "parasail/kimi-k2.7-code", "tensorx/kimi-k2.7-code", "workers-ai/@cf/moonshotai/kimi-k2.7-code" ], "intro_i18n": { "zh-CN": "Kimi K2.7 Code是Moonshot AI基于Kimi K2.6开发的专注于编程的智能代理模型，在实际长周期编程任务上有显著提升，同时思考Token使用量减少约30%。", "zh-TW": "Kimi K2.7 Code 是 Moonshot AI 基於 Kimi K2.6 開發的專注於編程的代理模型，在真實世界的長期編程任務中有顯著改進，並將思考 token 的使用量降低了約 30%。", "ja-JP": "Kimi K2.7 Codeは、Moonshot AIが開発したコーディングに特化したエージェントモデルで、Kimi K2.6を基盤に、実世界の長期的なコーディングタスクにおいて大幅な改善を実現し、思考トークンの使用量を約30%削減しています。", "ru-RU": "Kimi K2.7 Code — это модель, ориентированная на программирование, от Moonshot AI, построенная на основе Kimi K2.6, с существенными улучшениями в реальных задачах программирования с длинным горизонтом и примерно на 30% меньшим использованием токенов для мышления." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "0.2", "new": "10.91" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.2", "new": "2.62" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.509", "new": "0.507" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "completion", "old": "4.53", "new": "4.528" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "1.018", "new": "1.014" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "4.00232205", "new": "4.00360347" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.963521975", "new": "0.963830465" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "3.4", "new": "3.5" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.67", "new": "0.71" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "completion", "old": "4.2", "new": "3.675" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "prompt", "old": "0.9975", "new": "0.7875" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.51", "new": "0.509" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "4.548", "new": "4.53" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "1.02", "new": "1.018" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "4.00294791", "new": "4.00232205" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.963672645", "new": "0.963521975" }, { "date": "2026-08-12", "kind": "price", "provider": "inceptron", "charge": "cache_read", "old": "0.2", "new": "0.15" }, { "date": "2026-08-12", "kind": "price", "provider": "inceptron", "charge": "completion", "old": "3.5", "new": "3.4" }, { "date": "2026-08-12", "kind": "price", "provider": "inceptron", "charge": "prompt", "old": "0.75", "new": "0.67" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.430916", "new": "0.51" } ] }, { "slug": "moonshotai/kimi-k2.7-code-highspeed", "model_name": "kimi-k2.7-code-highspeed", "display_name": "Kimi K2.7 Code HighSpeed", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "provider_name": "Moonshot AI", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.9" }, "completion": { "unit": "per_M_tokens", "price": "8" }, "cache_read": { "unit": "per_M_tokens", "price": "0.38" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.38" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.6", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.9" }, "discarded_charge": { "unit": "per_M_tokens", "price": "13", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "54", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking", "released_at": "2026-06-12", "knowledge_cutoff": "2025-01", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "kimi-k2", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "deep_thinking", "reasoning_config": { "budget_min": 1 }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "kimi-k2-7-code-highspeed", "moonshot/kimi-k2.7-code-highspeed", "moonshotai/kimi-k2.7-code-highspeed" ], "intro_i18n": { "zh-CN": "Kimi K2.7 Code HighSpeed 是 Kimi K2.7 Code 的高速版本。与 Kimi K2.7 Code 为同一模型，但输出速度约为 180 Tokens/s，短上下文场景下可达 260 Tokens/s，带来更极致的编程体验。", "zh-TW": "Kimi K2.7 Code HighSpeed 是 Kimi K2.7 Code 的高速版本。該模型與 Kimi K2.7 Code 相同，但輸出速度約為 180 Tokens/s，短上下文場景下可達 260 Tokens/s，帶來更極致的編程體驗。", "ja-JP": "Kimi K2.7 Code HighSpeedはKimi K2.7 Codeの高速モデルです。同じモデルですが、出力速度は約180トークン/秒で、短いコンテキストシナリオでは260トークン/秒に達し、より極限的なプログラミング体験を提供します。", "ru-RU": "Kimi K2.7 Code HighSpeed ​​— это высокоскоростная версия модели Kimi K2.7 Code. Это та же модель, что и Kimi K2.7 Code, но скорость вывода составляет около 180 токенов/с, а в сценариях с коротким контекстом достигает 260 токенов/с, обеспечивая более экстремальный опыт программирования." } }, { "slug": "moonshotai/kimi-k3", "model_name": "kimi-k3", "display_name": "Kimi K3", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "provider_name": "Moonshot AI", "official": true, "source": "models-dev+pydantic-prices+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "100" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work", "released_at": "2026-07-16", "max_input_tokens": 1048576, "max_output_tokens": 131072, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "kimi-k3", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 1024 }, "benchmarks": { "intelligence_index": 59.7, "coding_index": 76.2, "agentic_index": 54.3 }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Kimi-K3", "TEE/kimi-k3", "accounts/fireworks/models/kimi-k3", "cline-pass/kimi-k3", "fireworks/kimi-k3", "hf:moonshotai/Kimi-K3", "kimi/kimi-k3", "moonshot-ai/kimi-k3", "moonshot/kimi-k3", "moonshotai/Kimi-K3", "moonshotai/kimi-k3", "moonshotai/kimi-k3-free", "nebius/kimi-k3", "sference/kimi-k3", "tensorx/kimi-k3", "k3" ], "intro_i18n": { "zh-CN": "Kimi K3 是 Kimi 至今最强大的型号，拥有 2.8 万亿参数。基于 Kimi Delta Attention 和 Attention Residuals 构建，它提供原生视觉理解能力以及 1M 令牌上下文窗口，适用于软件工程、知识工作和深度推理等前沿智能场景。推理功能始终开启，可通过顶级字段 reasoning_effort 配置。", "zh-TW": "Kimi K3 是 Kimi 至今最強大的模型，擁有 2.8 兆參數。基於 Kimi Delta Attention 和 Attention Residuals 架構，提供原生視覺理解能力以及 1M-token 的上下文窗口，適用於前沿智能場景，例如軟體工程、知識工作和深度推理。推理功能始終啟用，可透過頂層的 reasoning_effort 欄位進行配置。", "ja-JP": "Kimi K3は、Kimiのこれまでで最も高性能なモデルであり、2.8兆のパラメーターを備えています。Kimi Delta AttentionとAttention Residualsを基盤として構築されており、ネイティブな視覚理解と1Mトークンのコンテキストウィンドウを提供します。これにより、ソフトウェアエンジニアリング、知識作業、深い推論などの最前線のインテリジェンスシナリオに対応します。推論は常にオンであり、トップレベルのreasoning_effortフィールドを介して設定されます。", "ru-RU": "Kimi K3 — самая мощная модель Kimi на сегодняшний день, с 2,8 триллионами параметров. Построенная на основе Kimi Delta Attention и Attention Residuals, она обеспечивает естественное визуальное понимание и контекстное окно на 1 миллион токенов для передовых интеллектуальных сценариев, таких как разработка программного обеспечения, работа с знаниями и глубокое рассуждение. Режим рассуждения всегда включен, настраивается через поле reasoning_effort верхнего уровня." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "1.65", "new": "1.95" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "completion", "old": "16.5", "new": "18" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "3.3", "new": "3.9" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "14.823415", "new": "14.828161" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "2.964683", "new": "2.9656322" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "completion", "old": "6.3", "new": "13.3875" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "prompt", "old": "2.1", "new": "2.6775" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "14.825733", "new": "14.823415" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "2.9651466", "new": "2.964683" }, { "date": "2026-08-13", "kind": "price", "provider": "tokenrouter", "charge": "audio_input", "old": "3", "new": "1.5" }, { "date": "2026-08-13", "kind": "price", "provider": "tokenrouter", "charge": "audio_output", "old": "3", "new": "1.5" }, { "date": "2026-08-13", "kind": "price", "provider": "tokenrouter", "charge": "cache_read", "old": "0.3", "new": "0.15" }, { "date": "2026-08-13", "kind": "price", "provider": "tokenrouter", "charge": "cache_write", "old": "3", "new": "1.5" }, { "date": "2026-08-13", "kind": "price", "provider": "tokenrouter", "charge": "completion", "old": "15", "new": "7.5" }, { "date": "2026-08-13", "kind": "price", "provider": "tokenrouter", "charge": "prompt", "old": "3", "new": "1.5" }, { "date": "2026-08-13", "kind": "price", "provider": "zenmux", "charge": "web_search", "old": "5", "new": "4.5" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "14.824528", "new": "14.825733" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "2.9649056", "new": "2.9651466" }, { "date": "2026-08-12", "kind": "price", "provider": "tinfoil", "charge": "completion", "old": "6", "new": "20" }, { "date": "2026-08-12", "kind": "price", "provider": "tinfoil", "charge": "prompt", "old": "2", "new": "4" } ] }, { "slug": "moonshotai/kimi-latest", "model_name": "kimi-latest", "display_name": "kimi-latest", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-01-28", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "open_weights": true }, "intro": "Kimi multimodal agent model for visual understanding, coding, and planning", "released_at": "2026-05-03", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "kimi", "knowledge_cutoff": "2025-01", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "moonshotai/kimi-latest", "~moonshotai/kimi-latest" ], "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "open_weights: false→true" } ] }, { "slug": "moonshotai/kimi-latest-128k", "model_name": "kimi-latest-128k", "display_name": "kimi-latest-128k", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-01-28", "capabilities": { "vision": true, "function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "moonshotai/kimi-latest-32k", "model_name": "kimi-latest-32k", "display_name": "kimi-latest-32k", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 32768, "max_output_tokens": 32768, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-01-28", "capabilities": { "vision": true, "function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "moonshotai/kimi-latest-8k", "model_name": "kimi-latest-8k", "display_name": "kimi-latest-8k", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 8192, "max_output_tokens": 8192, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-01-28", "capabilities": { "vision": true, "function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "moonshotai/kimi-thinking-preview", "model_name": "kimi-thinking-preview", "display_name": "kimi-thinking-preview", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing/chat#generation-model-kimi-k2", "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2025-11-11", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "pdf_input: true→false" } ] }, { "slug": "moonshotai/moonshot-v1-128k", "model_name": "moonshot-v1-128k", "display_name": "moonshot-v1-128k", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm+pydantic-prices+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "30", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true }, "released_at": "2026-08-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "moonshotai/moonshot-v1-128k" ], "intro_i18n": { "zh-CN": "Moonshot V1 128K 提供超长上下文能力，支持最多 128,000 个 token 的文本生成，适用于科研、学术和长文档场景。", "zh-TW": "Moonshot V1 128K 提供超長上下文能力，支援最多 128,000 個 token，適用於研究、學術與長文檔場景。", "ja-JP": "Moonshot V1 128Kは、最大128,000トークンの超長文コンテキストに対応し、研究、学術、大規模文書の生成に最適です。", "ru-RU": "Moonshot V1 128K предоставляет сверхдлинный контекст для генерации очень длинных текстов, обрабатывая до 128 000 токенов — идеально для исследований, академических задач и работы с большими документами." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "moonshotai/moonshot-v1-128k-0430", "model_name": "moonshot-v1-128k-0430", "display_name": "moonshot-v1-128k-0430", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2024-04-30", "capabilities": { "function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "moonshotai/moonshot-v1-128k-vision-preview", "model_name": "moonshot-v1-128k-vision-preview", "display_name": "moonshot-v1-128k-vision-preview", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "30", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "structured_output": true }, "released_at": "2025-01-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "moonshotai/moonshot-v1-128k-vision-preview" ], "intro_i18n": { "zh-CN": "Kimi 视觉模型（包括 moonshot-v1-8k-vision-preview、moonshot-v1-32k-vision-preview、moonshot-v1-128k-vision-preview）可理解图像内容，如文字、颜色和物体形状。", "zh-TW": "Kimi 視覺模型（包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview）能理解圖像內容，如文字、顏色與物體形狀。", "ja-JP": "Kimi Visionモデル（moonshot-v1-8k-vision-preview / moonshot-v1-32k-vision-preview / moonshot-v1-128k-vision-preview）は、テキスト、色、物体の形状などの画像内容を理解できます。", "ru-RU": "Модели Kimi Vision (включая moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview) способны понимать содержимое изображений, включая текст, цвета и формы объектов." } }, { "slug": "moonshotai/moonshot-v1-32k", "model_name": "moonshot-v1-32k", "display_name": "moonshot-v1-32k", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm+pydantic-prices+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true }, "released_at": "2026-08-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "moonshotai/moonshot-v1-32k" ], "intro_i18n": { "zh-CN": "Moonshot V1 32K 支持 32,768 个 token 的中等长度上下文，适用于内容创作、报告和聊天系统中的长文档与复杂对话。", "zh-TW": "Moonshot V1 32K 支援 32,768 個 token 的中長上下文，適合內容創作、報告與聊天系統中的長文檔與複雜對話。", "ja-JP": "Moonshot V1 32Kは、32,768トークンの中程度の長さのコンテキストをサポートし、長文ドキュメントや複雑な対話に最適で、コンテンツ制作、レポート、チャットシステムに適しています。", "ru-RU": "Moonshot V1 32K поддерживает 32 768 токенов для контекста средней длины, идеально подходит для длинных документов и сложных диалогов в создании контента, отчётах и чат-системах." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "moonshotai/moonshot-v1-32k-0430", "model_name": "moonshot-v1-32k-0430", "display_name": "moonshot-v1-32k-0430", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 32768, "max_output_tokens": 32768, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2024-04-30", "capabilities": { "function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "moonshotai/moonshot-v1-32k-vision-preview", "model_name": "moonshot-v1-32k-vision-preview", "display_name": "moonshot-v1-32k-vision-preview", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "3" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "structured_output": true }, "released_at": "2025-01-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "moonshotai/moonshot-v1-32k-vision-preview" ], "intro_i18n": { "zh-CN": "Kimi 视觉模型（包括 moonshot-v1-8k-vision-preview、moonshot-v1-32k-vision-preview、moonshot-v1-128k-vision-preview）可理解图像内容，如文字、颜色和物体形状。", "zh-TW": "Kimi 視覺模型（包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview）能理解圖像內容，如文字、顏色與物體形狀。", "ja-JP": "Kimi Visionモデル（moonshot-v1-8k-vision-preview / moonshot-v1-32k-vision-preview / moonshot-v1-128k-vision-preview）は、テキスト、色、物体の形状などの画像内容を理解できます。", "ru-RU": "Модели Kimi Vision (включая moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview) способны понимать содержимое изображений, включая текст, цвета и формы объектов." } }, { "slug": "moonshotai/moonshot-v1-8k", "model_name": "moonshot-v1-8k", "display_name": "moonshot-v1-8k", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm+pydantic-prices+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 8192, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true }, "released_at": "2024-07-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "moonshotai/moonshot-v1-8k" ], "intro_i18n": { "zh-CN": "Moonshot V1 8K 针对短文本生成进行了优化，性能高效，支持 8,192 个 token，适用于短对话、笔记和快速内容生成。", "zh-TW": "Moonshot V1 8K 針對短文本生成進行優化，支援 8,192 個 token，適用於短對話、筆記與快速內容生成。", "ja-JP": "Moonshot V1 8Kは、短文生成に最適化されており、効率的なパフォーマンスで8,192トークンを処理し、短いチャット、メモ、迅速なコンテンツ作成に適しています。", "ru-RU": "Moonshot V1 8K оптимизирована для генерации коротких текстов с высокой эффективностью, обрабатывает 8192 токена — подходит для коротких чатов, заметок и быстрого контента." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "moonshotai/moonshot-v1-8k-0430", "model_name": "moonshot-v1-8k-0430", "display_name": "moonshot-v1-8k-0430", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 8192, "max_output_tokens": 8192, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2024-04-30", "capabilities": { "function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "moonshotai/moonshot-v1-8k-vision-preview", "model_name": "moonshot-v1-8k-vision-preview", "display_name": "moonshot-v1-8k-vision-preview", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 8192, "max_output_tokens": 8192, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "structured_output": true, "pdf_input": true, "image_output": true }, "released_at": "2025-01-14", "modalities": { "input": [ "file", "image", "text" ], "output": [ "image", "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "moonshotai/moonshot-v1-8k-vision-preview" ], "intro_i18n": { "zh-CN": "Kimi 视觉模型（包括 moonshot-v1-8k-vision-preview、moonshot-v1-32k-vision-preview、moonshot-v1-128k-vision-preview）可理解图像内容，如文字、颜色和物体形状。", "zh-TW": "Kimi 視覺模型（包括 moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview）能理解圖像內容，如文字、顏色與物體形狀。", "ja-JP": "Kimi Visionモデル（moonshot-v1-8k-vision-preview、moonshot-v1-32k-vision-preview、moonshot-v1-128k-vision-previewを含む）は、テキスト、色、物体の形状などの画像内容を理解できます。", "ru-RU": "Модели Kimi Vision (включая moonshot-v1-8k-vision-preview/moonshot-v1-32k-vision-preview/moonshot-v1-128k-vision-preview) способны понимать содержимое изображений, включая текст, цвета и формы объектов." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "moonshotai/moonshot-v1-auto", "model_name": "moonshot-v1-auto", "display_name": "moonshot-v1-auto", "vendor": "moonshotai", "pricing": [ { "provider": "moonshotai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://platform.moonshot.ai/docs/pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "structured_output": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "morph/auto", "model_name": "auto", "display_name": "Auto", "vendor": "morph", "pricing": [ { "provider": "morph", "provider_name": "Morph", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.85" }, "completion": { "unit": "per_M_tokens", "price": "1.55" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Automatic model router for matching prompts to suitable backends and budgets", "released_at": "2024-06-01", "max_input_tokens": 32000, "max_output_tokens": 32000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "auto", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "text_generation", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "kilo/auto", "openrouter/auto", "orcarouter/auto", "pioneer/auto", "trustedrouter/auto" ], "intro_i18n": { "zh-CN": "根据上下文长度、主题和复杂度，自动将请求路由至 Llama 3 70B Instruct、Claude 3.5 Sonnet（自我审查）或 GPT-4o。", "zh-TW": "根據上下文長度、主題與複雜度，自動將請求路由至 Llama 3 70B Instruct、Claude 3.5 Sonnet（自我審核）或 GPT-4o。", "ja-JP": "コンテキスト長、トピック、複雑さに応じて、Llama 3 70B Instruct、Claude 3.5 Sonnet（自己モデレート）、またはGPT-4oにルーティングされます。", "ru-RU": "В зависимости от длины контекста, темы и сложности ваш запрос направляется в Llama 3 70B Instruct, Claude 3.5 Sonnet (с самомодерацией) или GPT-4o." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "morph/morph-v3-fast", "model_name": "morph-v3-fast", "display_name": "Morph v3 Fast", "vendor": "morph", "pricing": [ { "provider": "morph", "provider_name": "Morph", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "1.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Efficient model for low-latency assistance, extraction, and routine automation", "released_at": "2024-08-15", "max_input_tokens": 16000, "max_output_tokens": 16000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "morph", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "function_calling": true }, "deprecated": true, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "morph/morph-v3-fast" ], "intro_i18n": { "zh-CN": "Morph 提供专用模型，将前沿模型（如 Claude 或 GPT-4o）建议的代码更改快速应用于现有文件，速度达 4500+ tokens/秒，是 AI 编程流程的最后一步，支持 16k 输入/输出。", "zh-TW": "Morph 提供專門模型，能以超過 4500 個 token/秒的速度，將前沿模型（如 Claude 或 GPT-4o）建議的程式碼變更應用至現有檔案。作為 AI 程式開發流程的最後一步，支援 16K 輸入/輸出 token。", "ja-JP": "Morphは、ClaudeやGPT-4oなどの先端モデルが提案したコード変更を既存ファイルに適用するための専用モデルで、FAST 4500+トークン/秒の速度で動作します。AIコーディングワークフローの最終ステップとして、16Kの入出力トークンをサポートします。", "ru-RU": "Morph — специализированная модель для применения изменений в коде, предложенных передовыми моделями (например, Claude или GPT-4o), к существующим файлам со скоростью более 4500 токенов/сек. Это финальный этап в AI-пайплайне программирования, поддерживает 16k токенов на вход/выход." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "morph/morph-v3-large", "model_name": "morph-v3-large", "display_name": "Morph v3 Large", "vendor": "morph", "pricing": [ { "provider": "morph", "provider_name": "Morph", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.9" }, "completion": { "unit": "per_M_tokens", "price": "1.9" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Flagship model for demanding analysis, coding, and production agent workflows", "released_at": "2024-08-15", "max_input_tokens": 32000, "max_output_tokens": 32000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "morph", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "function_calling": true, "structured_output": true }, "deprecated": true, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "morph/morph-v3-large" ], "intro_i18n": { "zh-CN": "Morph 提供专用模型，将前沿模型（如 Claude 或 GPT-4o）建议的代码更改快速应用于现有文件，速度达 2500+ tokens/秒，是 AI 编程流程的最后一步，支持 16k 输入/输出。", "zh-TW": "Morph 提供專門模型，能以超過 2500 個 token/秒的速度，將前沿模型（如 Claude 或 GPT-4o）建議的程式碼變更應用至現有檔案。作為 AI 程式開發流程的最後一步，支援 16K 輸入/輸出 token。", "ja-JP": "Morphは、ClaudeやGPT-4oなどの先端モデルが提案したコード変更を既存ファイルに適用するための専用モデルで、FAST 2500+トークン/秒の速度で動作します。AIコーディングワークフローの最終ステップとして、16Kの入出力トークンをサポートします。", "ru-RU": "Morph — специализированная модель для применения изменений в коде, предложенных передовыми моделями (например, Claude или GPT-4o), к существующим файлам со скоростью более 2500 токенов/сек. Это финальный этап в AI-пайплайне программирования, поддерживает 16k токенов на вход/выход." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "nvidia/active-speaker-detection", "model_name": "active-speaker-detection", "display_name": "Active Speaker Detection", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/active-speaker-detection" } ], "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "released_at": "2026-04-16", "max_input_tokens": 0, "max_output_tokens": 4096, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "video_input": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/active-speaker-detection" ], "model_type": "vision_understanding" }, { "slug": "nvidia/bevformer", "model_name": "bevformer", "display_name": "bevformer", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/bevformer" } ], "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "released_at": "2025-03-18", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "capabilities": { "video_input": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/bevformer" ], "model_type": "vision_understanding" }, { "slug": "nvidia/cosmos-predict1-5b", "model_name": "cosmos-predict1-5b", "display_name": "cosmos-predict1-5b", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/cosmos-predict1-5b" } ], "intro": "Video model for prompt-guided generation, editing, and motion workflows", "released_at": "2025-03-18", "max_input_tokens": 0, "max_output_tokens": 4096, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "video_input": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/cosmos-predict1-5b" ], "model_type": "vision_understanding" }, { "slug": "nvidia/cosmos-reason2-8b", "model_name": "cosmos-reason2-8b", "display_name": "Cosmos Reason2 8B", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/cosmos-reason2-8b" } ], "intro": "Vision language model for physical-world understanding with structured reasoning on video and images", "released_at": "2025-12-01", "max_input_tokens": 131072, "max_output_tokens": 16384, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "video_input": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/cosmos-reason2-8b" ], "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-28", "kind": "listed", "note": "Cosmos Reason2 8B" } ] }, { "slug": "nvidia/cosmos-transfer1-7b", "model_name": "cosmos-transfer1-7b", "display_name": "cosmos-transfer1-7b", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/cosmos-transfer1-7b" } ], "intro": "Video model for prompt-guided generation, editing, and motion workflows", "released_at": "2025-06-13", "max_input_tokens": 0, "max_output_tokens": 4096, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "video_input": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/cosmos-transfer1-7b" ], "model_type": "vision_understanding" }, { "slug": "nvidia/cosmos-transfer2_5-2b", "model_name": "cosmos-transfer2_5-2b", "display_name": "cosmos-transfer2.5-2b", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/cosmos-transfer2_5-2b" } ], "intro": "Video model for prompt-guided generation, editing, and motion workflows", "released_at": "2026-02-26", "max_input_tokens": 0, "max_output_tokens": 4096, "modalities": { "input": [ "text", "image", "video" ], "output": [ "video" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "video_input": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/cosmos-transfer2_5-2b" ], "model_type": "vision_understanding" }, { "slug": "nvidia/gliner-pii", "model_name": "gliner-pii", "display_name": "gliner-pii", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/gliner-pii" } ], "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "released_at": "2026-03-03", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/gliner-pii" ], "model_type": "text_generation" }, { "slug": "nvidia/Inkling", "model_name": "Inkling", "display_name": "Inkling", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "thinkingmachines/inkling" } ], "intro": "Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio", "released_at": "2026-07-15", "max_input_tokens": 1048576, "max_output_tokens": 16384, "modalities": { "input": [ "text", "image", "audio" ], "output": [ "text" ] }, "family": "ling", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "video_generation", "benchmarks": { "intelligence_index": 42.3, "coding_index": 52.1, "agentic_index": 34.1 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "accounts/fireworks/models/inkling", "inkling", "thinkingmachines/Inkling", "thinkingmachines/inkling", "thinkingmachines/inkling:thinking" ], "price_history": [ { "date": "2026-07-28", "kind": "listed", "note": "Inkling" } ] }, { "slug": "nvidia/laguna-xs-2.1:free", "model_name": "laguna-xs-2.1:free", "display_name": "Laguna XS 2.1", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "poolside/laguna-xs-2.1" } ], "intro": "Agentic coding model from Poolside in the XS size class for local deployment", "released_at": "2026-07-02", "max_input_tokens": 262144, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "laguna", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "open_weights": true }, "model_type": "deep_thinking", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "temperature", "tool_choice", "tools" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "poolside/laguna-xs-2.1", "poolside/laguna-xs-2.1:free" ], "price_history": [ { "date": "2026-07-28", "kind": "listed", "note": "Laguna XS 2.1" } ] }, { "slug": "nvidia/llama-3_2-nemoretriever-300m-embed-v1", "model_name": "llama-3_2-nemoretriever-300m-embed-v1", "display_name": "llama-3_2-nemoretriever-300m-embed-v1", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/llama-3_2-nemoretriever-300m-embed-v1" } ], "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2025-07-24", "max_input_tokens": 32768, "max_output_tokens": 2048, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/llama-3_2-nemoretriever-300m-embed-v1" ], "model_type": "text_embedding" }, { "slug": "nvidia/llama-3.1-nemotron-70b-instruct", "model_name": "llama-3.1-nemotron-70b-instruct", "display_name": "Llama 3.1 Nemotron 70B Instruct", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/llama-3.1-nemotron-70b-instruct" } ], "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "released_at": "2025-04-15", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "model_type": "text_generation", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Llama-3.1-Nemotron-70B-Instruct", "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct", "nvidia/Llama-3.1-Nemotron-70B-Instruct", "nvidia/llama-3.1-nemotron-70b-instruct" ], "intro_i18n": { "zh-CN": "Llama-3.1-Nemotron-70B-Instruct 是 NVIDIA 定制的大语言模型，旨在提升模型响应的有用性。", "zh-TW": "Llama-3.1-Nemotron-70B-Instruct 是 NVIDIA 客製化模型，旨在提升大型語言模型回應的有用性。", "ja-JP": "Llama-3.1-Nemotron-70B-Instructは、NVIDIAがカスタマイズしたモデルで、LLMの応答の有用性を向上させるよう設計されています。", "ru-RU": "Llama-3.1-Nemotron-70B-Instruct — кастомизированная модель от NVIDIA, созданная для повышения полезности ответов LLM." }, "price_history": [ { "date": "2026-07-28", "kind": "listed", "note": "Llama 3.1 Nemotron 70B Instruct" } ] }, { "slug": "nvidia/llama-3.1-nemotron-nano-8b-v1", "model_name": "llama-3.1-nemotron-nano-8b-v1", "display_name": "Llama 3.1 Nemotron Nano 8B v1", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/llama-3.1-nemotron-nano-8b-v1" } ], "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "released_at": "2025-03-18", "max_input_tokens": 131072, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "reasoning": true, "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/llama-3.1-nemotron-nano-8b-v1" ], "model_type": "text_generation", "price_history": [ { "date": "2026-07-28", "kind": "listed", "note": "Llama 3.1 Nemotron Nano 8B v1" } ] }, { "slug": "nvidia/llama-3.1-nemotron-nano-vl-8b-v1", "model_name": "llama-3.1-nemotron-nano-vl-8b-v1", "display_name": "Llama 3.1 Nemotron Nano VL 8B v1", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/llama-3.1-nemotron-nano-vl-8b-v1" } ], "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "released_at": "2025-04-10", "max_input_tokens": 32768, "max_output_tokens": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/llama-3.1-nemotron-nano-vl-8b-v1" ], "model_type": "vision_understanding", "price_history": [ { "date": "2026-07-28", "kind": "listed", "note": "Llama 3.1 Nemotron Nano VL 8B v1" } ] }, { "slug": "nvidia/llama-3.1-nemotron-safety-guard-8b-v3", "model_name": "llama-3.1-nemotron-safety-guard-8b-v3", "display_name": "llama-3.1-nemotron-safety-guard-8b-v3", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/llama-3.1-nemotron-safety-guard-8b-v3" } ], "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows", "released_at": "2025-10-28", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/llama-3.1-nemotron-safety-guard-8b-v3" ], "model_type": "safety_detection", "price_history": [ { "date": "2026-07-28", "kind": "listed", "note": "llama-3.1-nemotron-safety-guard-8b-v3" } ] }, { "slug": "nvidia/llama-3.1-nemotron-ultra-253b-v1", "model_name": "llama-3.1-nemotron-ultra-253b-v1", "display_name": "Llama 3.1 Nemotron Ultra 253B", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/llama-3.1-nemotron-ultra-253b-v1" } ], "intro": "Flagship Nemotron model for high-throughput reasoning and complex agents", "released_at": "2025-04-07", "max_input_tokens": 128000, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "open_weights": true, "stream": true }, "parameters": { "unsupported": [ "temperature" ] }, "docs_url": "https://nebius.com/prices-ai-studio", "model_type": "text_generation", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Llama-3.1-Nemotron-Ultra-253B-v1", "llama-3.1-nemotron-ultra-253b-v1:free", "nvidia/llama-3.1-nemotron-ultra-253b-v1" ], "price_history": [ { "date": "2026-07-28", "kind": "listed", "note": "Llama 3.1 Nemotron Ultra 253B" } ] }, { "slug": "nvidia/llama-3.3-nemotron-super-49b-v1", "model_name": "llama-3.3-nemotron-super-49b-v1", "display_name": "Llama 3.3 Nemotron Super 49B v1", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/llama-3.3-nemotron-super-49b-v1" } ], "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "released_at": "2025-04-07", "max_input_tokens": 131072, "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "open_weights": true }, "docs_url": "https://nebius.com/prices-ai-studio", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Llama-3.3-Nemotron-Super-49B-v1", "nvidia/Llama-3.3-Nemotron-Super-49B-v1", "nvidia/llama-3.3-nemotron-super-49b-v1" ], "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-28", "kind": "listed", "note": "Llama 3.3 Nemotron Super 49B v1" } ] }, { "slug": "nvidia/llama-3.3-nemotron-super-49b-v1.5", "model_name": "llama-3.3-nemotron-super-49b-v1.5", "display_name": "Llama 3.3 Nemotron Super 49B v1.5", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/llama-3.3-nemotron-super-49b-v1.5" } ], "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "released_at": "2025-07-25", "max_input_tokens": 131072, "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "deprecated": true, "status": "deprecated", "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Llama-3.3-Nemotron-Super-49B-v1.5", "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5", "llama-3-3-nemotron-super-49b-v1-5", "nvidia/Llama-3.3-Nemotron-Super-49B-v1.5", "nvidia/llama-3.3-nemotron-super-49b-v1.5" ], "price_history": [ { "date": "2026-07-28", "kind": "listed", "note": "Llama 3.3 Nemotron Super 49B v1.5" } ] }, { "slug": "nvidia/llama-nemotron-embed-vl-1b-v2", "model_name": "llama-nemotron-embed-vl-1b-v2", "display_name": "llama-nemotron-embed-vl-1b-v2", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/llama-nemotron-embed-vl-1b-v2" } ], "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2026-02-10", "max_input_tokens": 32768, "max_output_tokens": 2048, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "nemotron", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "open_weights": true, "pdf_input": true }, "model_type": "multimodal_embedding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/llama-nemotron-embed-vl-1b-v2" ] }, { "slug": "nvidia/llama-nemotron-rerank-vl-1b-v2", "model_name": "llama-nemotron-rerank-vl-1b-v2", "display_name": "llama-nemotron-rerank-vl-1b-v2", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/llama-nemotron-rerank-vl-1b-v2" } ], "intro": "Reranking model for improving retrieval quality in search and recommendation systems", "released_at": "2026-03-31", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "nemotron", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/llama-nemotron-rerank-vl-1b-v2" ], "model_type": "text_rerank" }, { "slug": "nvidia/magpie-tts-zeroshot", "model_name": "magpie-tts-zeroshot", "display_name": "magpie-tts-zeroshot", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/magpie-tts-zeroshot" } ], "intro": "Speech generation model for controllable voice, narration, and audio delivery", "released_at": "2025-05-22", "max_input_tokens": 0, "max_output_tokens": 4096, "modalities": { "input": [ "text", "audio" ], "output": [ "audio" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "audio_input": true, "audio_output": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/magpie-tts-zeroshot" ], "model_type": "speech_synthesis" }, { "slug": "nvidia/nemotron-3-content-safety", "model_name": "nemotron-3-content-safety", "display_name": "nemotron-3-content-safety", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nemotron-3-content-safety" } ], "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows", "released_at": "2026-04-16", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/nemotron-3-content-safety" ], "model_type": "safety_detection" }, { "slug": "nvidia/nemotron-3-nano-30b-a3b", "model_name": "nemotron-3-nano-30b-a3b", "display_name": "nemotron-3-nano-30b-a3b", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nemotron-3-nano-30b-a3b" } ], "intro": "Small Nemotron 3 MoE for efficient coding, math, and long-context agents", "released_at": "2024-12", "knowledge_cutoff": "2024-09", "max_input_tokens": 131072, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 14.5, "coding_index": 14.4, "agentic_index": 2 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "deepinfra/nvidia/Nemotron-3-Nano-30B-A3B", "nvidia/Nemotron-3-Nano-30B-A3B", "nvidia/nemotron-3-nano-30b-a3b", "nvidia/nemotron-3-nano-30b-a3b:free" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "model_name": "nemotron-3-nano-omni-30b-a3b-reasoning", "display_name": "Nemotron 3 Nano Omni", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning" } ], "intro": "Open Nemotron omni model combining reasoning with text, vision, and audio", "released_at": "2026-04-28", "max_input_tokens": 256000, "max_output_tokens": 65536, "modalities": { "input": [ "text", "image", "video", "audio" ], "output": [ "text" ] }, "family": "nemotron", "reasoning_config": { "budget_min": -1 }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "deprecated": true, "status": "deprecated", "model_type": "omni", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "lightning-ai/nemotron-3-nano-omni-30b-a3b-reasoning", "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning", "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning", "nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free" ], "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-17", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "nvidia/nemotron-3-super-120b-a12b", "model_name": "nemotron-3-super-120b-a12b", "display_name": "Nemotron 3 Super", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.8" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nemotron-3-super-120b-a12b" } ], "intro": "Nemotron middle tier for collaborative agents and high-volume reasoning workloads", "released_at": "2026-03-11", "knowledge_cutoff": "2024-04", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true }, "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 25.7, "coding_index": 37.7, "agentic_index": 8.8 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nebius/nvidia/nemotron-3-super-120b-a12b", "nemotron-3-super-120b-a12b:free", "nvidia/nemotron-3-super-120b-a12b", "nvidia/nemotron-3-super-120b-a12b:free", "nvidia/nemotron-3-super-120b-a12b:thinking" ], "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "completion", "old": "0.945", "new": "0.42" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "prompt", "old": "0.315", "new": "0.08925" }, { "date": "2026-08-10", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "0.9", "new": "0.4" }, { "date": "2026-08-10", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.3", "new": "0.085" }, { "date": "2026-08-09", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "0.4", "new": "0.9" }, { "date": "2026-08-09", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.085", "new": "0.3" }, { "date": "2026-08-03", "kind": "price", "provider": "kilo", "charge": "completion", "old": "0.5", "new": "0.4" }, { "date": "2026-08-03", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "0.1", "new": "0.085" }, { "date": "2026-07-26", "kind": "price", "provider": "perplexity", "charge": "completion", "old": "0.45", "new": "0.4" }, { "date": "2026-07-26", "kind": "price", "provider": "perplexity", "charge": "prompt", "old": "0.08", "new": "0.085" }, { "date": "2026-07-25", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "0.45", "new": "0.4" }, { "date": "2026-07-25", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.08", "new": "0.085" }, { "date": "2026-07-22", "kind": "price", "provider": "perplexity", "charge": "completion", "old": "0.4", "new": "0.45" }, { "date": "2026-07-22", "kind": "price", "provider": "perplexity", "charge": "prompt", "old": "0.085", "new": "0.08" }, { "date": "2026-07-21", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "0.4", "new": "0.45" }, { "date": "2026-07-21", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.085", "new": "0.08" }, { "date": "2026-07-21", "kind": "price", "provider": "perplexity", "charge": "completion", "old": "0.455", "new": "0.4" }, { "date": "2026-07-21", "kind": "price", "provider": "perplexity", "charge": "prompt", "old": "0.21", "new": "0.085" }, { "date": "2026-07-20", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "0.455", "new": "0.4" }, { "date": "2026-07-20", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.21", "new": "0.085" } ] }, { "slug": "nvidia/nemotron-3-ultra-550b-a55b", "model_name": "nemotron-3-ultra-550b-a55b", "display_name": "Nemotron 3 Ultra 550B A55B", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nemotron-3-ultra-550b-a55b" } ], "intro": "Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy", "released_at": "2026-06-04", "max_input_tokens": 1000000, "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true }, "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 38.3, "coding_index": 49.3, "agentic_index": 27.5 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "lightning-ai/nemotron-3-ultra-550b-a55b", "nebius/nvidia/nemotron-3-ultra-550b-a55b", "nemotron-3-ultra-550b-a55b:free", "nvidia/nemotron-3-ultra-550b-a55b", "nvidia/nemotron-3-ultra-550b-a55b:free", "nvidia/nemotron-3-ultra-550b-a55b:thinking" ], "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "completion", "old": "2.52", "new": "1.26" }, { "date": "2026-08-14", "kind": "price", "provider": "trustedrouter", "charge": "prompt", "old": "0.63", "new": "0.4305" }, { "date": "2026-07-30", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.1", "new": "0.2" }, { "date": "2026-07-30", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "2.2", "new": "3.6" }, { "date": "2026-07-30", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.5", "new": "0.6" }, { "date": "2026-07-29", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.2", "new": "0.1" }, { "date": "2026-07-29", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "3.6", "new": "2.2" }, { "date": "2026-07-29", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.6", "new": "0.5" }, { "date": "2026-07-15", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.1", "new": "0.2" }, { "date": "2026-07-15", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "2.2", "new": "3.6" }, { "date": "2026-07-15", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.5", "new": "0.6" } ] }, { "slug": "nvidia/nemotron-3.5-lightning-30b-a3b", "model_name": "nemotron-3.5-lightning-30b-a3b", "display_name": "Nemotron 3.5 Lightning 30B A3B", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nemotron-3.5-lightning-30b-a3b" } ], "intro": "Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads", "released_at": "2026-08-11", "max_input_tokens": 262144, "max_output_tokens": 262144, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "reasoning": true, "structured_output": true, "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/nemotron-3.5-lightning-30b-a3b" ], "model_type": "text_generation", "price_history": [ { "date": "2026-08-11", "kind": "listed", "note": "Nemotron 3.5 Lightning 30B A3B" } ] }, { "slug": "nvidia/nemotron-content-safety-reasoning-4b", "model_name": "nemotron-content-safety-reasoning-4b", "display_name": "nemotron-content-safety-reasoning-4b", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nemotron-content-safety-reasoning-4b" } ], "intro": "Safety model for policy screening, moderation, and risk-aware routing workflows", "released_at": "2026-01-22", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "reasoning": true, "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/nemotron-content-safety-reasoning-4b" ], "model_type": "safety_detection" }, { "slug": "nvidia/nemotron-mini-4b-instruct", "model_name": "nemotron-mini-4b-instruct", "display_name": "nemotron-mini-4b-instruct", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nemotron-mini-4b-instruct" } ], "intro": "Compact Nemotron model for efficient reasoning and deployable AI agents", "released_at": "2024-08-21", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/nemotron-mini-4b-instruct" ], "model_type": "text_generation" }, { "slug": "nvidia/nemotron-nano-12b-v2-vl", "model_name": "nemotron-nano-12b-v2-vl", "display_name": "Nemotron Nano 12B v2 VL", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nemotron-nano-12b-v2-vl" } ], "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "released_at": "2025-10-28", "max_input_tokens": 128000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "video_input": true, "open_weights": true, "pdf_input": true, "stream": true }, "knowledge_cutoff": "2024-10", "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/nemotron-nano-12b-v2-vl", "nvidia/nemotron-nano-12b-v2-vl:free" ], "price_history": [ { "date": "2026-07-28", "kind": "limit", "old": "16384", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "131072", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "131072", "new": "16384", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Nvidia Nemotron Nano 12B V2 VL" } ] }, { "slug": "nvidia/nemotron-voicechat", "model_name": "nemotron-voicechat", "display_name": "nemotron-voicechat", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nemotron-voicechat" } ], "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "released_at": "2026-03-16", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "text", "audio" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "audio_input": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/nemotron-voicechat" ], "model_type": "text_generation" }, { "slug": "nvidia/nv-embed-v1", "model_name": "nv-embed-v1", "display_name": "nv-embed-v1", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nv-embed-v1" } ], "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2024-06-07", "max_input_tokens": 32768, "max_output_tokens": 2048, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/nv-embed-v1" ], "model_type": "text_embedding" }, { "slug": "nvidia/nv-embedcode-7b-v1", "model_name": "nv-embedcode-7b-v1", "display_name": "nv-embedcode-7b-v1", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nv-embedcode-7b-v1" } ], "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "released_at": "2025-03-17", "max_input_tokens": 32768, "max_output_tokens": 2048, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/nv-embedcode-7b-v1" ], "model_type": "text_embedding" }, { "slug": "nvidia/nvidia-nemotron-nano-9b-v2", "model_name": "nvidia-nemotron-nano-9b-v2", "display_name": "nvidia-nemotron-nano-9b-v2", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/nvidia-nemotron-nano-9b-v2" } ], "intro": "Compact Nemotron model for efficient reasoning and deployable AI agents", "released_at": "2025-08-18", "knowledge_cutoff": "2024-09", "max_input_tokens": 131072, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "nemotron", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "model_type": "text_generation", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "NVIDIA-Nemotron-Nano-9B-v2", "accounts/fireworks/models/nvidia-nemotron-nano-9b-v2", "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2", "nvidia.nemotron-nano-9b-v2", "nvidia/NVIDIA-Nemotron-Nano-9B-v2", "nvidia/nvidia-nemotron-nano-9b-v2" ], "price_history": [ { "date": "2026-07-17", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "nvidia/rerank-qa-mistral-4b", "model_name": "rerank-qa-mistral-4b", "display_name": "rerank-qa-mistral-4b", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/rerank-qa-mistral-4b" } ], "intro": "Reranking model for improving retrieval quality in search and recommendation systems", "released_at": "2024-03-17", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/rerank-qa-mistral-4b" ], "model_type": "text_rerank" }, { "slug": "nvidia/riva-translate-4b-instruct-v1.1", "model_name": "riva-translate-4b-instruct-v1.1", "display_name": "riva-translate-4b-instruct-v1_1", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/riva-translate-4b-instruct-v1.1" } ], "intro": "Translation model for multilingual conversion, localization, and cross-language workflows", "released_at": "2025-12-12", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/riva-translate-4b-instruct-v1.1" ], "model_type": "text_generation", "price_history": [ { "date": "2026-07-28", "kind": "listed", "note": "riva-translate-4b-instruct-v1_1" } ] }, { "slug": "nvidia/sarvam-m", "model_name": "sarvam-m", "display_name": "sarvam-m", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "sarvamai/sarvam-m" } ], "intro": "Efficient Indian-language reasoning model for chat, coding, and multilingual work", "released_at": "2025-07-25", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "function_calling": true, "reasoning": true, "open_weights": true }, "deprecated": true, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "sarvam-m:free", "sarvamai/sarvam-m" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "sarvam-m" } ] }, { "slug": "nvidia/sparsedrive", "model_name": "sparsedrive", "display_name": "sparsedrive", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/sparsedrive" } ], "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "released_at": "2025-03-18", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "capabilities": { "video_input": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/sparsedrive" ], "model_type": "vision_understanding" }, { "slug": "nvidia/streampetr", "model_name": "streampetr", "display_name": "streampetr", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/streampetr" } ], "intro": "Nemotron multimodal model for visual reasoning and agentic AI workflows", "released_at": "2025-11-13", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "capabilities": { "video_input": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/streampetr" ], "model_type": "vision_understanding" }, { "slug": "nvidia/studiovoice", "model_name": "studiovoice", "display_name": "studiovoice", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/studiovoice" } ], "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "released_at": "2024-10-03", "max_input_tokens": 128000, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/studiovoice" ], "model_type": "text_generation" }, { "slug": "nvidia/synthetic-video-detector", "model_name": "synthetic-video-detector", "display_name": "synthetic-video-detector", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/synthetic-video-detector" } ], "intro": "Video model for prompt-guided generation, editing, and motion workflows", "released_at": "2026-04-16", "max_input_tokens": 0, "max_output_tokens": 4096, "modalities": { "input": [ "video" ], "output": [ "text" ] }, "capabilities": { "video_input": true, "open_weights": true, "pdf_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/synthetic-video-detector" ], "model_type": "vision_understanding" }, { "slug": "nvidia/usdcode", "model_name": "usdcode", "display_name": "usdcode", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/usdcode" } ], "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "released_at": "2026-01-01", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/usdcode" ], "model_type": "text_generation" }, { "slug": "nvidia/usdvalidate", "model_name": "usdvalidate", "display_name": "usdvalidate", "vendor": "nvidia", "pricing": [ { "provider": "nvidia", "provider_name": "Nvidia", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "aggregator_only" }, "provider_model_id": "nvidia/usdvalidate" } ], "intro": "Nemotron model for efficient reasoning, coding, and specialized AI agents", "released_at": "2024-07-24", "max_input_tokens": 0, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "nvidia/usdvalidate" ], "model_type": "text_generation" }, { "slug": "openai/ada", "model_name": "ada", "display_name": "ada", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "capabilities": {}, "max_input_tokens": 8191, "model_type": "text_embedding", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "ada" } ] }, { "slug": "openai/ada-v2", "model_name": "ada-v2", "display_name": "ada-v2", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "ada-v2" } ] }, { "slug": "openai/babbage", "model_name": "babbage", "display_name": "babbage", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "babbage" } ] }, { "slug": "openai/babbage-002", "model_name": "babbage-002", "display_name": "babbage-002", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey+llmdb", "charge_sources": { "prompt": "portkey", "completion": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "capabilities": { "prompt_caching": true }, "released_at": "2023-08-21", "knowledge_cutoff": "2021-09", "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "babbage-002" } ] }, { "slug": "openai/chat-latest", "model_name": "chat-latest", "display_name": "Chat Latest", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "truefoundry+portkey+lobehub-modelbank+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "parallel_function_calling": true, "structured_output": true, "prompt_caching": true, "vision": true, "web_search": true, "pdf_input": true }, "released_at": "2026-05-05", "knowledge_cutoff": "2025-08", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/chat-latest" ], "intro_i18n": { "zh-CN": "ChatGPT 使用的最新即时模型。", "zh-TW": "ChatGPT 使用的最新即時模型。", "ja-JP": "ChatGPTで使用される最新のインスタントモデル。", "ru-RU": "Последняя мгновенная модель, используемая в ChatGPT." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Chat Latest" } ] }, { "slug": "openai/chatgpt-4o-latest", "model_name": "chatgpt-4o-latest", "display_name": "chatgpt-4o-latest", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "helicone-registry", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20" }, "message": "completion from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "helicone-registry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.25" }, "message": "cache_read from portkey conflicts with helicone-registry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 128000, "max_output_tokens": 4096, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-02-17", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "intro": "OpenAI ChatGPT 4o is continually updated by OpenAI to point to the current version of GPT-4o used by ChatGPT. It therefore differs slightly from the API version of GPT-4o in that it has additional RLHF. It is intended for research and evaluation.", "modalities": { "input": [ "image", "pdf" ], "output": [] }, "knowledge_cutoff": "2024-08", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_p" ] }, "released_at": "2024-08-14", "family": "gpt", "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/chatgpt-4o-latest" ], "intro_i18n": { "zh-CN": "ChatGPT-4o是一个实时更新的动态模型，结合了强大的语言理解和生成能力，适用于客户支持、教育和技术协助等大规模应用场景。", "zh-TW": "ChatGPT-4o 是一個實時更新的動態模型，結合了強大的語言理解和生成能力，適用於大規模使用場景，如客戶支持、教育和技術協助。", "ja-JP": "ChatGPT-4oはリアルタイムで更新される動的モデルです。強力な言語理解と生成能力を組み合わせ、カスタマーサポート、教育、技術支援などの大規模なユースケースに対応します。", "ru-RU": "ChatGPT-4o — это динамическая модель, обновляемая в реальном времени. Она сочетает в себе мощное понимание языка и генерацию для масштабных сценариев использования, таких как поддержка клиентов, образование и техническая помощь." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/chatgpt-image-latest", "model_name": "chatgpt-image-latest", "display_name": "chatgpt-image-latest", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+truefoundry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "cache_read": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "image_input": { "unit": "per_M_tokens", "price": "8" }, "image_output": { "unit": "per_M_tokens", "price": "32" }, "image_cache_read": { "unit": "per_M_tokens", "price": "2" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "cache_read": "litellm", "completion": "truefoundry", "image_input": "portkey", "image_output": "portkey", "image_cache_read": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8" }, "message": "prompt from ai-model-directory conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "32" }, "message": "completion from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "cache_read from ai-model-directory conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2025-12-16", "max_input_tokens": 0, "max_output_tokens": 0, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "family": "gpt-image", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "prompt_caching": true, "pdf_input": true, "image_output": true }, "model_type": "image_generation", "deprecation_date": "2026-12-01", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/codex-mini", "model_name": "codex-mini", "display_name": "Codex Mini", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.375" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "codex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "stream": true }, "released_at": "2025-05-16", "knowledge_cutoff": "2024-04", "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt-codex-mini", "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "model_type": "text_generation", "deprecation_date": "2026-11-15", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "aliases": [ "codex-mini-2025-05-16", "openai/codex-mini" ], "price_history": [ { "date": "2026-07-25", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-03", "kind": "listed", "note": "Codex Mini" } ] }, { "slug": "openai/codex-mini-latest", "model_name": "codex-mini-latest", "display_name": "codex-mini-latest", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+truefoundry+helicone-registry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.375" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "cache_write": "portkey", "file_search_call": "portkey" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-02-12", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "intro": "Latest version of Codex Mini, a compact specialized model for code generation and analysis", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "parameters": { "supported": [ "max_completion_tokens", "response_format", "seed", "stop", "tool_choice", "tools" ], "unsupported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "temperature", "top_logprobs", "top_p", "verbosity" ] }, "released_at": "2025-01-01", "family": "gpt-codex-mini", "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/computer-use", "model_name": "computer-use", "display_name": "computer-use", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "12" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "vision_understanding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "computer-use" } ] }, { "slug": "openai/computer-use-preview", "model_name": "computer-use-preview", "display_name": "computer-use-preview", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey+llmdb", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "computer-use-preview-2025-03-11", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 8192, "max_output_tokens": 1024, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "vision": true, "structured_output": true, "parallel_function_calling": true, "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "released_at": "2026-08-14", "aliases": [ "computer-use-preview-2025-03-11", "computer-use-preview-2025-04-15" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Computer Use Preview" } ] }, { "slug": "openai/curie", "model_name": "curie", "display_name": "curie", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "curie" } ] }, { "slug": "openai/dall-e-2", "model_name": "dall-e-2", "display_name": "dall-e-2", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+portkey+llmdb", "charges": { "image_input": { "unit": "per_image", "price": "0.02" }, "image_output": { "unit": "per_image", "price": "0.02" }, "image_output_1024px": { "unit": "per_image", "price": "0.02" }, "image_output_512px": { "unit": "per_image", "price": "0.018" }, "image_output_256x256": { "unit": "per_image", "price": "0.016" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "image_input": "litellm", "image_output": "portkey", "image_output_1024px": "portkey", "image_output_512px": "portkey", "image_output_256x256": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "cross_checked" } } ], "deprecated": true, "model_type": "image_generation", "deprecation_date": "2026-05-12", "capabilities": { "vision": true, "prompt_caching": true, "stream": true, "image_output": true }, "modalities": { "input": [ "image" ], "output": [] }, "released_at": "2022-04-06", "family": "dall-e", "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/dall-e-3", "model_name": "dall-e-3", "display_name": "dall-e-3", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+portkey+llmdb", "charges": { "image_input": { "unit": "per_image", "price": "0.04" }, "image_output": { "unit": "per_image", "price": "0.04" }, "image_output_1024px": { "unit": "per_image", "price": "0.04" }, "image_output_1024x1792": { "unit": "per_image", "price": "0.08" }, "image_output_1792x1024": { "unit": "per_image", "price": "0.08" }, "image_output_hd": { "unit": "per_image", "price": "0.08" }, "image_output_1024px_hd": { "unit": "per_image", "price": "0.08" }, "image_output_1024x1792_hd": { "unit": "per_image", "price": "0.12" }, "image_output_1792x1024_hd": { "unit": "per_image", "price": "0.12" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "image_input": "litellm", "image_output": "portkey", "image_output_1024px": "portkey", "image_output_1024x1792": "portkey", "image_output_1792x1024": "portkey", "image_output_hd": "portkey", "image_output_1024px_hd": "portkey", "image_output_1024x1792_hd": "portkey", "image_output_1792x1024_hd": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "cross_checked" } } ], "deprecated": true, "model_type": "image_generation", "deprecation_date": "2026-05-12", "capabilities": { "vision": true, "function_calling": true, "pdf_input": true, "stream": true, "image_output": true }, "modalities": { "input": [ "image" ], "output": [] }, "released_at": "2023-10-01", "family": "dall-e", "status": "deprecated", "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "max_input_tokens": 800, "max_output_tokens": 0, "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/dall-e-3" ], "intro_i18n": { "zh-CN": "DALL·E 3", "zh-TW": "DALL·E 3", "ja-JP": "DALL·E 3", "ru-RU": "DALL·E 3" }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/davinci", "model_name": "davinci", "display_name": "davinci", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "20" }, "completion": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "davinci" } ] }, { "slug": "openai/davinci-002", "model_name": "davinci-002", "display_name": "davinci-002", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey+llmdb", "charge_sources": { "prompt": "portkey", "completion": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "capabilities": { "prompt_caching": true }, "released_at": "2023-08-21", "knowledge_cutoff": "2021-09", "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "davinci-002" } ] }, { "slug": "openai/ft:gpt-3.5-turbo", "model_name": "ft:gpt-3.5-turbo", "display_name": "ft:gpt-3.5-turbo", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 16385, "max_output_tokens": 4096, "model_type": "text_generation", "deprecation_date": "2026-10-23", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] } }, { "slug": "openai/ft:gpt-3.5-turbo-", "model_name": "ft:gpt-3.5-turbo-", "display_name": "ft:gpt-3.5-turbo-", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "GPT-3.5 Turbo fine tuned.", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "ft:gpt-3.5-turbo-" } ] }, { "slug": "openai/ft:gpt-3.5-turbo-0125", "model_name": "ft:gpt-3.5-turbo-0125", "display_name": "ft:gpt-3.5-turbo-0125", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 16385, "max_output_tokens": 4096, "model_type": "text_generation", "deprecation_date": "2026-10-23", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] } }, { "slug": "openai/ft:gpt-3.5-turbo-0613", "model_name": "ft:gpt-3.5-turbo-0613", "display_name": "ft:gpt-3.5-turbo-0613", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 4096, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] } }, { "slug": "openai/ft:gpt-3.5-turbo-1106", "model_name": "ft:gpt-3.5-turbo-1106", "display_name": "ft:gpt-3.5-turbo-1106", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 16385, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] } }, { "slug": "openai/ft:gpt-4-0613", "model_name": "ft:gpt-4-0613", "display_name": "ft:gpt-4-0613", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "30" }, "completion": { "unit": "per_M_tokens", "price": "60" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "OpenAI needs to add pricing for this ft model, will be updated when added by OpenAI. Defaulting to base model pricing", "max_input_tokens": 8192, "max_output_tokens": 4096, "model_type": "text_generation", "deprecation_date": "2026-10-23", "capabilities": { "function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] } }, { "slug": "openai/ft:gpt-4.1-2025-04-14", "model_name": "ft:gpt-4.1-2025-04-14", "display_name": "ft:gpt-4.1-2025-04-14", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.75" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" }, "verification_status": "cross_checked" }, "provider_model_id": "ft:gpt-4.1" } ], "max_input_tokens": 1047576, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "ft:gpt-4.1" ] }, { "slug": "openai/ft:gpt-4.1-mini-2025-04-14", "model_name": "ft:gpt-4.1-mini-2025-04-14", "display_name": "ft:gpt-4.1-mini-2025-04-14", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.8" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" }, "verification_status": "cross_checked" }, "provider_model_id": "ft:gpt-4.1-mini" } ], "max_input_tokens": 1047576, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "ft:gpt-4.1-mini" ] }, { "slug": "openai/ft:gpt-4.1-nano-2025-04-14", "model_name": "ft:gpt-4.1-nano-2025-04-14", "display_name": "ft:gpt-4.1-nano-2025-04-14", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.8" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "portkey" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 1047576, "max_output_tokens": 32768, "model_type": "text_generation", "deprecation_date": "2026-10-23", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] } }, { "slug": "openai/ft:gpt-4o-2024-11-20", "model_name": "ft:gpt-4o-2024-11-20", "display_name": "ft:gpt-4o-2024-11-20", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3.75" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "1.875" }, "cache_write": { "unit": "per_M_tokens", "price": "1.875" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "cache_write": "litellm", "file_search_call": "portkey", "web_search": "portkey" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "1.875" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "cache_write from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "1.875" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "cache_write from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "ft:gpt-4o-2024-08-06" } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true }, "intro": "GPT-4o fine tuned.", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "ft:gpt-4o", "ft:gpt-4o-2024-08-06" ], "price_history": [ { "date": "2026-07-03", "kind": "capability", "note": "vision: false→true" } ] }, { "slug": "openai/ft:gpt-4o-mini-2024-07-18", "model_name": "ft:gpt-4o-mini-2024-07-18", "display_name": "ft:gpt-4o-mini-2024-07-18", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "1.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" }, "verification_status": "cross_checked" }, "provider_model_id": "ft:gpt-4o-mini" } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true }, "intro": "GPT-4o Mini fine tuned.", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "ft:gpt-4o-mini" ] }, { "slug": "openai/ft:o4-mini-2025-04-16", "model_name": "ft:o4-mini-2025-04-16", "display_name": "ft:o4-mini-2025-04-16", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "16" }, "cache_read": { "unit": "per_M_tokens", "price": "1" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 200000, "max_output_tokens": 100000, "model_type": "deep_thinking", "deprecation_date": "2026-10-23", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] } }, { "slug": "openai/gpt-3.5-0301", "model_name": "gpt-3.5-0301", "display_name": "gpt-3.5-0301", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "pydantic-prices+portkey", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "web_search": "portkey", "file_search_call": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gpt-3.5-0301" } ] }, { "slug": "openai/gpt-3.5-turbo", "model_name": "gpt-3.5-turbo", "display_name": "GPT-3.5-turbo", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.25" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2023-03-01", "knowledge_cutoff": "2021-09", "max_input_tokens": 16385, "max_output_tokens": 4096, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt", "status": "deprecated", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "stream": true }, "model_type": "text_generation", "deprecation_date": "2026-10-23", "parameters": { "unsupported": [ "temperature" ] }, "benchmarks": { "intelligence_index": null, "coding_index": 10.7, "agentic_index": null }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-3.5-turbo" ], "intro_i18n": { "zh-CN": "GPT-3.5 Turbo 用于文本生成与理解；当前指向 gpt-3.5-turbo-0125。", "zh-TW": "GPT 3.5 Turbo 用於文字生成與理解，目前指向 gpt-3.5-turbo-0125。", "ja-JP": "GPT-3.5 Turbo はテキスト生成と理解のためのモデルで、現在は gpt-3.5-turbo-0125 を指しています。", "ru-RU": "GPT 3.5 Turbo для генерации и понимания текста; в настоящее время указывает на gpt-3.5-turbo-0125." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-3.5-turbo-0125", "model_name": "gpt-3.5-turbo-0125", "display_name": "gpt-3.5-turbo-0125", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.5" }, "completion": { "unit": "per_M_tokens", "price": "1.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 16385, "max_output_tokens": 4096, "model_type": "text_generation", "deprecation_date": "2026-10-23", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "parallel_function_calling": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2024-01-25", "knowledge_cutoff": "2021-09", "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "deprecated": true, "family": "gpt", "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-3.5-turbo-0125" ], "intro_i18n": { "zh-CN": "GPT-3.5 Turbo 用于文本生成与理解；当前指向 gpt-3.5-turbo-0125。", "zh-TW": "GPT 3.5 Turbo 用於文字生成與理解，目前指向 gpt-3.5-turbo-0125。", "ja-JP": "GPT-3.5 Turbo はテキスト生成と理解のためのモデルで、現在は gpt-3.5-turbo-0125 を指しています。", "ru-RU": "GPT 3.5 Turbo для генерации и понимания текста; в настоящее время указывает на gpt-3.5-turbo-0125." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" } ] }, { "slug": "openai/gpt-3.5-turbo-0301", "model_name": "gpt-3.5-turbo-0301", "display_name": "GPT-3.5 Turbo 0301", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "prompt_caching": true }, "released_at": "2023-03-01", "knowledge_cutoff": "2021-08", "max_input_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GPT-3.5 Turbo 0301" } ] }, { "slug": "openai/gpt-3.5-turbo-0613", "model_name": "gpt-3.5-turbo-0613", "display_name": "GPT-3.5 Turbo (older v0613)", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "pydantic-prices+portkey", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "web_search": "portkey", "file_search_call": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 16385, "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "stream": true }, "max_output_tokens": 4096, "model_type": "text_generation", "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2024-01-25", "knowledge_cutoff": "2021-09", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-3.5-turbo-0613" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GPT-3.5 Turbo 0613" } ] }, { "slug": "openai/gpt-3.5-turbo-1106", "model_name": "gpt-3.5-turbo-1106", "display_name": "gpt-3.5-turbo-1106", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 16385, "max_output_tokens": 4096, "model_type": "text_generation", "deprecation_date": "2026-09-28", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "parallel_function_calling": true }, "released_at": "2023-11-06", "knowledge_cutoff": "2021-09", "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt", "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-3.5-turbo-1106" ], "intro_i18n": { "zh-CN": "GPT-3.5 Turbo 用于文本生成与理解；当前指向 gpt-3.5-turbo-0125。", "zh-TW": "GPT 3.5 Turbo 用於文字生成與理解，目前指向 gpt-3.5-turbo-0125。", "ja-JP": "GPT-3.5 Turbo はテキスト生成と理解のためのモデルで、現在は gpt-3.5-turbo-0125 を指しています。", "ru-RU": "GPT 3.5 Turbo для генерации и понимания текста; в настоящее время указывает на gpt-3.5-turbo-0125." }, "price_history": [ { "date": "2026-07-25", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" } ] }, { "slug": "openai/gpt-3.5-turbo-16k", "model_name": "gpt-3.5-turbo-16k", "display_name": "gpt-3.5-turbo-16k", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "4" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 16385, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "stream": true }, "intro": "This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost. Training data: up to Sep 2021.", "released_at": "2023-08-28", "knowledge_cutoff": "2021-09", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-3.5-turbo-16k" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-3.5-turbo-16k-0613", "model_name": "gpt-3.5-turbo-16k-0613", "display_name": "gpt-3.5-turbo-16k-0613", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "4" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gpt-3.5-turbo-16k-0613" } ] }, { "slug": "openai/gpt-3.5-turbo-instruct", "model_name": "gpt-3.5-turbo-instruct", "display_name": "GPT-3.5 Turbo Instruct", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "cross_checked" } } ], "intro": "GPT-3.5 Turbo offers a balance between cost and performance.", "max_input_tokens": 16385, "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "stream": true, "structured_output": true, "pdf_input": true }, "max_output_tokens": 4096, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "knowledge_cutoff": "2021-09", "released_at": "2023-08-24", "family": "gpt", "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-3.5-turbo-instruct" ], "intro_i18n": { "zh-CN": "GPT-3.5 Turbo 优化用于指令跟随的文本生成与理解任务。", "zh-TW": "GPT 3.5 Turbo 用於文字生成與理解任務，針對指令遵循進行最佳化。", "ja-JP": "GPT-3.5 Turbo は、指示に従うタスクに最適化されたテキスト生成・理解モデルです。", "ru-RU": "GPT 3.5 Turbo для задач генерации и понимания текста, оптимизирован для выполнения инструкций." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "GPT-3.5 Turbo Instruct" } ] }, { "slug": "openai/gpt-3.5-turbo-instruct-0914", "model_name": "gpt-3.5-turbo-instruct-0914", "display_name": "gpt-3.5-turbo-instruct-0914", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.5" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "cross_checked" } } ], "capabilities": { "prompt_caching": true }, "released_at": "2026-08-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "gpt-3.5-turbo-instruct-0914" } ] }, { "slug": "openai/gpt-4", "model_name": "gpt-4", "display_name": "GPT-4", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "30" }, "completion": { "unit": "per_M_tokens", "price": "60" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "cross_checked" } } ], "intro": "GPT model for general reasoning, writing, coding, and tool-assisted tasks", "released_at": "2023-11-06", "knowledge_cutoff": "2023-11", "max_input_tokens": 8192, "max_output_tokens": 8192, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt", "status": "deprecated", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "stream": true }, "model_type": "text_generation", "deprecation_date": "2026-10-23", "benchmarks": { "intelligence_index": null, "coding_index": 13.1, "agentic_index": null }, "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_completion_tokens", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-4" ], "intro_i18n": { "zh-CN": "GPT-4 提供更大的上下文窗口，适用于信息整合与数据分析等任务。", "zh-TW": "GPT-4 提供更大的上下文視窗，能處理更長的輸入，適合廣泛資訊整合與資料分析。", "ja-JP": "GPT-4 はより大きなコンテキストウィンドウを提供し、長文入力に対応。広範な情報統合やデータ分析に適しています。", "ru-RU": "GPT-4 предоставляет расширенное контекстное окно для обработки длинных входных данных, что делает его подходящим для комплексного анализа информации и синтеза данных." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-4-0125-preview", "model_name": "gpt-4-0125-preview", "display_name": "gpt-4-0125-preview", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 128000, "max_output_tokens": 4096, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-03-26", "capabilities": { "function_calling": true, "prompt_caching": true, "parallel_function_calling": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2023-12", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4-0125-Preview" ], "intro_i18n": { "zh-CN": "最新的 GPT-4 Turbo 模型支持视觉功能。视觉请求可以使用 JSON 模式和函数调用。GPT-4 Turbo 是增强版，平衡了准确性和效率，适用于具有成本效益的多模态任务和实时交互。", "zh-TW": "最新的 GPT-4 Turbo 模型包含視覺功能。視覺請求可使用 JSON 模式和函數調用。GPT-4 Turbo 是一個增強版，平衡了準確性和效率，適用於成本效益高的多模態任務和即時交互。", "ja-JP": "最新のGPT-4 Turboモデルにはビジョンが含まれています。ビジョンリクエストはJSONモードと関数呼び出しを使用できます。GPT-4 Turboは、コスト効率の高いマルチモーダルタスクとリアルタイムインタラクションのために、精度と効率のバランスを取った強化版です。", "ru-RU": "Последняя модель GPT-4 Turbo включает поддержку зрения. Запросы с использованием зрения могут использовать режим JSON и вызов функций. GPT-4 Turbo — это улучшенная версия, которая балансирует точность и эффективность для экономичных мультимодальных задач и взаимодействий в реальном времени." } }, { "slug": "openai/gpt-4-0314", "model_name": "gpt-4-0314", "display_name": "gpt-4-0314", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "30" }, "completion": { "unit": "per_M_tokens", "price": "60" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey", "charge_sources": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 8192, "max_output_tokens": 4096, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-03-26", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2023-05-28", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-4-0314" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/gpt-4-0613", "model_name": "gpt-4-0613", "display_name": "gpt-4-0613", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "30" }, "completion": { "unit": "per_M_tokens", "price": "60" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 8192, "max_output_tokens": 4096, "model_type": "text_generation", "deprecation_date": "2026-10-23", "capabilities": { "function_calling": true, "prompt_caching": true }, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2023-06-13", "knowledge_cutoff": "2021-09", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-4-0613" ], "intro_i18n": { "zh-CN": "GPT-4 提供更大的上下文窗口，适用于处理更长的输入，适合信息整合与数据分析。", "zh-TW": "GPT-4 提供更大的上下文視窗，能處理更長的輸入，適合廣泛資訊整合與資料分析。", "ja-JP": "GPT-4 はより大きなコンテキストウィンドウを提供し、長文入力に対応。広範な情報統合やデータ分析に適しています。", "ru-RU": "GPT-4 предоставляет расширенное контекстное окно для обработки длинных входных данных, что делает его подходящим для комплексного анализа информации и синтеза данных." } }, { "slug": "openai/gpt-4-1106-preview", "model_name": "gpt-4-1106-preview", "display_name": "gpt-4-1106-preview", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 128000, "max_output_tokens": 4096, "model_type": "text_generation", "deprecation_date": "2026-10-23", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "parallel_function_calling": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2023-11-06", "knowledge_cutoff": "2023-04", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4-1106-Preview", "openai/gpt-4-1106-preview" ], "intro_i18n": { "zh-CN": "最新的 GPT-4 Turbo 模型支持视觉功能。视觉请求可以使用 JSON 模式和函数调用。GPT-4 Turbo 是增强版，平衡了准确性和效率，适用于具有成本效益的多模态任务和实时交互。", "zh-TW": "最新的 GPT-4 Turbo 模型包含視覺功能。視覺請求可使用 JSON 模式和函數調用。GPT-4 Turbo 是一個增強版，平衡了準確性和效率，適用於成本效益高的多模態任務和即時交互。", "ja-JP": "最新のGPT-4 Turboモデルにはビジョンが含まれています。ビジョンリクエストはJSONモードと関数呼び出しを使用できます。GPT-4 Turboは、コスト効率の高いマルチモーダルタスクとリアルタイムインタラクションのために、精度と効率のバランスを取った強化版です。", "ru-RU": "Последняя модель GPT-4 Turbo включает поддержку зрения. Запросы с использованием зрения могут использовать режим JSON и вызов функций. GPT-4 Turbo — это улучшенная версия, которая балансирует точность и эффективность для экономичных мультимодальных задач и взаимодействий в реальном времени." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/gpt-4-1106-vision-preview", "model_name": "gpt-4-1106-vision-preview", "display_name": "gpt-4-1106-vision-preview", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "vision_understanding", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gpt-4-1106-vision-preview" } ] }, { "slug": "openai/gpt-4-32k", "model_name": "gpt-4-32k", "display_name": "GPT-4 32K", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices+truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "60" }, "completion": { "unit": "per_M_tokens", "price": "120" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "pydantic-prices+portkey", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "web_search": "portkey", "file_search_call": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "GPT-4 is the latest and most advanced model in the GPT series, demonstrating sophisticated capabilities in complex reasoning, theory of mind, and narrative understanding.", "max_input_tokens": 32000, "capabilities": { "prompt_caching": true, "function_calling": true, "stream": true }, "max_output_tokens": 4096, "model_type": "text_generation", "released_at": "2023-03-14", "knowledge_cutoff": "2023-11", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-4-32k" ], "intro_i18n": { "zh-CN": "GPT-4 提供更大的上下文窗口，适用于需要广泛信息整合与数据分析的场景。", "zh-TW": "GPT-4 提供更大的上下文視窗，能處理更長的輸入，適合需要廣泛資訊整合與資料分析的場景。", "ja-JP": "GPT-4 はより大きなコンテキストウィンドウを提供し、長文入力に対応。広範な情報統合やデータ分析に適しています。", "ru-RU": "GPT-4 предоставляет расширенное контекстное окно для обработки длинных входных данных, что делает его подходящим для интеграции информации и анализа данных в сложных сценариях." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GPT-4 32K" } ] }, { "slug": "openai/gpt-4-32k-0314", "model_name": "gpt-4-32k-0314", "display_name": "gpt-4-32k-0314", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "60" }, "completion": { "unit": "per_M_tokens", "price": "120" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "prompt_caching": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gpt-4-32k-0314" } ] }, { "slug": "openai/gpt-4-32k-0613", "model_name": "gpt-4-32k-0613", "display_name": "GPT-4 32K 0613", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "60" }, "completion": { "unit": "per_M_tokens", "price": "120" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "capabilities": { "function_calling": true, "prompt_caching": true }, "max_input_tokens": 32768, "max_output_tokens": 4096, "model_type": "text_generation", "knowledge_cutoff": "2021-09", "released_at": "2026-08-14", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "intro_i18n": { "zh-CN": "GPT-4 提供更大的上下文窗口，适用于需要广泛信息整合与数据分析的场景。", "zh-TW": "GPT-4 提供更大的上下文視窗，能處理更長的輸入，適合需要廣泛資訊整合與資料分析的場景。", "ja-JP": "GPT-4 はより大きなコンテキストウィンドウを提供し、長文入力に対応。広範な情報統合やデータ分析に適しています。", "ru-RU": "GPT-4 предоставляет расширенное контекстное окно для обработки длинных входных данных, что делает его подходящим для интеграции информации и анализа данных в сложных сценариях." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "GPT-4 32K 0613" } ] }, { "slug": "openai/gpt-4-turbo", "model_name": "gpt-4-turbo", "display_name": "GPT-4 Turbo", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gpt-4-turbo-2024-04-09", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2023-11-06", "knowledge_cutoff": "2023-12", "max_input_tokens": 128000, "max_output_tokens": 4096, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt", "status": "deprecated", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "stream": true }, "model_type": "vision_understanding", "deprecation_date": "2026-10-23", "parameters": { "unsupported": [ "temperature" ] }, "benchmarks": { "intelligence_index": null, "coding_index": 21.5, "agentic_index": null }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4-turbo-2024-04-09", "openai/gpt-4-turbo", "openai/gpt-4-turbo-2024-04-09" ], "intro_i18n": { "zh-CN": "最新的 GPT-4 Turbo 增加了视觉能力。视觉请求支持 JSON 模式与函数调用。该模型在实时应用中兼顾准确性与效率，性价比高。", "zh-TW": "最新 GPT-4 Turbo 加入視覺功能。視覺請求支援 JSON 模式與函數呼叫。這是一款具成本效益的多模態模型，兼顧準確性與效率，適用於即時應用。", "ja-JP": "最新の GPT-4 Turbo は視覚機能を追加。ビジュアルリクエストは JSON モードと関数呼び出しに対応。リアルタイムアプリケーション向けに精度と効率のバランスを取ったコスト効率の高いマルチモーダルモデルです。", "ru-RU": "Последняя версия GPT-4 Turbo теперь поддерживает обработку изображений. Визуальные запросы поддерживают режим JSON и вызов функций. Это экономичный мультимодальный ИИ, сочетающий точность и эффективность для приложений в реальном времени." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-4-turbo-preview", "model_name": "gpt-4-turbo-preview", "display_name": "gpt-4-turbo-preview", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 128000, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "stream": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2024-01-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt", "knowledge_cutoff": "2023-12", "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-4-turbo-preview" ], "intro_i18n": { "zh-CN": "最新的 GPT-4 Turbo 模型支持视觉功能。视觉请求可以使用 JSON 模式和函数调用。GPT-4 Turbo 是增强版，平衡了准确性和效率，适用于具有成本效益的多模态任务和实时交互。", "zh-TW": "最新的 GPT-4 Turbo 模型包含視覺功能。視覺請求可使用 JSON 模式和函數調用。GPT-4 Turbo 是一個增強版，平衡了準確性和效率，適用於成本效益高的多模態任務和即時交互。", "ja-JP": "最新のGPT-4 Turboモデルにはビジョンが含まれています。ビジョンリクエストはJSONモードと関数呼び出しを使用できます。GPT-4 Turboは、コスト効率の高いマルチモーダルタスクとリアルタイムインタラクションのために、精度と効率のバランスを取った強化版です。", "ru-RU": "Последняя модель GPT-4 Turbo включает поддержку зрения. Запросы с использованием зрения могут использовать режим JSON и вызов функций. GPT-4 Turbo — это улучшенная версия, которая балансирует точность и эффективность для экономичных мультимодальных задач и взаимодействий в реальном времени." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/gpt-4-vision-preview", "model_name": "gpt-4-vision-preview", "display_name": "gpt-4-vision-preview", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "30" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "intro": "GPT-4 Vision is a model that offers a balance between cost and performance.", "max_input_tokens": 128000, "capabilities": { "vision": true }, "max_output_tokens": 4096, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "intro_i18n": { "zh-CN": "GPT-4 Vision 预览版，专为图像分析与处理任务设计。", "zh-TW": "GPT-4 Vision 預覽版，專為圖像分析與處理任務設計。", "ja-JP": "GPT-4 Vision プレビューは、画像解析および処理タスク向けに設計されたモデルです。", "ru-RU": "Предварительная версия GPT-4 Vision, предназначенная для анализа и обработки изображений." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gpt-4-vision-preview" } ] }, { "slug": "openai/gpt-4.1-2025-04-14", "model_name": "gpt-4.1-2025-04-14", "display_name": "gpt-4.1-2025-04-14", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "8" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gpt-4.1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1.75", "completion": "1.75", "cache_read": "1.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "25" } } } ], "intro": "Long-lived GPT workhorse for coding, instruction following, and production apps", "released_at": "2025-04-14", "knowledge_cutoff": "2024-04", "max_input_tokens": 1047576, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_p" ] }, "deprecated": true, "status": "deprecated", "deprecation_date": "2027-04-14", "aliases": [ "azure/gpt-4.1", "azure/openai-responses/gpt-4.1", "gpt-4-1", "gpt-4.1", "openai-responses/gpt-4.1", "openai/gpt-4.1", "openai/gpt-4.1-2025-04-14" ], "intro_i18n": { "zh-CN": "GPT-4.1 是我们面向复杂任务与跨领域问题解决的旗舰模型。", "zh-TW": "GPT-4.1 是我們的旗艦模型，適用於複雜任務與跨領域問題解決。", "ja-JP": "GPT-4.1 は複雑なタスクや分野横断的な問題解決に対応するフラッグシップモデルです。", "ru-RU": "GPT-4.1 — наша флагманская модель для решения сложных задач и междисциплинарных проблем." }, "price_history": [ { "date": "2026-07-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/gpt-4.1-mini-2025-04-14", "model_name": "gpt-4.1-mini-2025-04-14", "display_name": "gpt-4.1-mini-2025-04-14", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "1.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.1" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gpt-4.1-mini", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1.75", "completion": "1.75", "cache_read": "1.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "5" } } } ], "intro": "Affordable GPT-4.1 lane for fast coding help and structured extraction", "released_at": "2025-04-14", "knowledge_cutoff": "2024-04", "max_input_tokens": 1047576, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt-mini", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_p" ] }, "deprecated": true, "status": "deprecated", "deprecation_date": "2027-04-14", "benchmarks": { "intelligence_index": 14.8, "coding_index": 20.2, "agentic_index": 1.8 }, "aliases": [ "gpt-4-1-mini", "gpt-4.1-mini", "openai-responses/gpt-4.1-mini", "openai/gpt-4.1-mini", "openai/gpt-4.1-mini-2025-04-14" ], "intro_i18n": { "zh-CN": "GPT-4.1 mini 在智能、速度与成本之间实现平衡，适用于多种场景。", "zh-TW": "GPT-4.1 mini 在智慧、速度與成本之間取得平衡，適用於多種應用場景。", "ja-JP": "GPT-4.1 mini は知能、速度、コストのバランスが取れたモデルで、多様なユースケースに適しています。", "ru-RU": "GPT-4.1 mini сочетает интеллект, скорость и экономичность, что делает его привлекательным для множества сценариев использования." }, "price_history": [ { "date": "2026-07-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-4.1-nano-2025-04-14", "model_name": "gpt-4.1-nano-2025-04-14", "display_name": "gpt-4.1-nano-2025-04-14", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.025" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.025" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.025" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.025" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.03" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-4.1-nano", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "1.5" } } } ], "intro": "Tiny GPT-4.1 option for classification, routing, and very high-volume tasks", "released_at": "2025-04-14", "knowledge_cutoff": "2024-04", "max_input_tokens": 1047576, "max_output_tokens": 32768, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt-nano", "status": "deprecated", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "web_search": true, "stream": true }, "model_type": "vision_understanding", "deprecation_date": "2026-10-23", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_p" ] }, "benchmarks": { "intelligence_index": 9.6, "coding_index": 11.1, "agentic_index": 1.2 }, "aliases": [ "azure/gpt-4.1-nano", "azure/openai-responses/gpt-4.1-nano", "gpt-4-1-nano", "gpt-4.1-nano", "openai-responses/gpt-4.1-nano", "openai/gpt-4.1-nano", "openai/gpt-4.1-nano-2025-04-14" ], "intro_i18n": { "zh-CN": "GPT-4.1 nano 是最快且最具性价比的 GPT-4.1 模型。", "zh-TW": "GPT-4.1 nano 是 GPT-4.1 系列中最快且最具成本效益的模型。", "ja-JP": "GPT-4.1 nano は GPT-4.1 モデルの中で最も高速かつコスト効率の高いモデルです。", "ru-RU": "GPT-4.1 nano — самая быстрая и экономичная модель в линейке GPT-4.1." }, "price_history": [ { "date": "2026-07-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-4.5", "model_name": "gpt-4.5", "display_name": "GPT-4.5", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "75" }, "completion": { "unit": "per_M_tokens", "price": "150" }, "cache_read": { "unit": "per_M_tokens", "price": "37.5" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www", "cache_read": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GPT-4.5" } ] }, { "slug": "openai/gpt-4.5-preview-2025-02-27", "model_name": "gpt-4.5-preview-2025-02-27", "display_name": "GPT 4.5 Preview", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "75" }, "completion": { "unit": "per_M_tokens", "price": "150" }, "cache_read": { "unit": "per_M_tokens", "price": "37.5" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "file_search_call": "portkey", "cache_write": "portkey" }, "verification_status": "cross_checked" }, "provider_model_id": "gpt-4.5-preview" } ], "intro": "GPT-4.5 (Preview) is a research preview of OpenAI's latest language model, designed to advance capabilities in reasoning, creativity, and multi-turn conversation. It builds on previous iterations with improvements in world knowledge, contextual coherence, and the ability to follow user intent more effectively.", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "parallel_function_calling": true }, "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "text_generation", "released_at": "2025-02-27", "knowledge_cutoff": "2023-10", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4.5-preview", "openai/gpt-4.5-preview" ], "intro_i18n": { "zh-CN": "GPT-4.5-preview 是最新的通用模型，具备更深的世界知识与更强的意图理解能力，擅长创意任务与智能体规划。知识截止时间为 2023 年 10 月。", "zh-TW": "GPT-4.5-preview 是最新的通用模型，具備深厚的世界知識與更佳的意圖理解能力，擅長創意任務與智能代理規劃。知識截止時間為 2023 年 10 月。", "ja-JP": "GPT-4.5-preview は最新の汎用モデルで、深い世界知識と意図理解を備え、創造的なタスクやエージェント計画に強みを持ちます。知識のカットオフは 2023年10月です。", "ru-RU": "GPT-4.5-preview — последняя универсальная модель с глубокими знаниями о мире и улучшенным пониманием намерений. Отлично справляется с творческими задачами и планированием агентов. Актуальность знаний — октябрь 2023 года." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GPT 4.5 Preview" } ] }, { "slug": "openai/gpt-4o", "model_name": "gpt-4o", "display_name": "GPT-4o", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "1.25" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "models-dev", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from models-dev conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "models-dev", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15" }, "message": "completion from models-dev conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6" }, "message": "prompt from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "18" }, "message": "completion from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15" }, "message": "completion from portkey conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "batch prompt from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "7.5" }, "message": "batch completion from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "portkey", "selected_source": "portkey", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "4.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8.75" }, "message": "priority prompt from portkey conflicts with portkey; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "portkey", "selected_source": "portkey", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "17" }, "discarded_charge": { "unit": "per_M_tokens", "price": "26.25" }, "message": "priority completion from portkey conflicts with portkey; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-4o-2024-05-13", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1.7", "completion": "1.7", "cache_read": "1.7" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "25" } } } ], "intro": "Omni-era GPT for multimodal chat, practical coding, and general assistants", "released_at": "2024-05-13", "knowledge_cutoff": "2023-09", "max_input_tokens": 128000, "max_output_tokens": 16384, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "web_search": true, "stream": true }, "deprecated": true, "status": "deprecated", "model_type": "vision_understanding", "deprecation_date": "2026-10-23", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_p" ] }, "benchmarks": { "intelligence_index": null, "coding_index": 24.2, "agentic_index": null }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4o-2024-05-13", "gpt-4o-2024-08-06", "gpt-4o-2024-11-20", "gpt-4o:extended", "openai/gpt-4o", "openai/gpt-4o-2024-05-13", "openai/gpt-4o-2024-08-06", "openai/gpt-4o-2024-11-20", "openai/gpt-4o:extended" ], "intro_i18n": { "zh-CN": "ChatGPT-4o 是一款实时更新的动态模型，结合强大的理解与生成能力，适用于客户支持、教育与技术支持等大规模应用场景。", "zh-TW": "ChatGPT-4o 是一款即時更新的動態模型，結合強大的理解與生成能力，適用於客服、教育與技術支援等大規模應用場景。", "ja-JP": "ChatGPT-4o はリアルタイムで更新される動的モデルで、カスタマーサポート、教育、技術支援などの大規模ユースケースにおいて高い理解力と生成力を発揮します。", "ru-RU": "ChatGPT-4o — это динамическая модель с обновлением в реальном времени, сочетающая глубокое понимание и генерацию текста для масштабных сценариев, таких как поддержка клиентов, образование и техническая помощь." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-4o-audio-preview", "model_name": "gpt-4o-audio-preview", "display_name": "gpt-4o-audio-preview", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "audio_input": { "unit": "per_M_tokens", "price": "40" }, "audio_output": { "unit": "per_M_tokens", "price": "80" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "audio_output": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "40" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "audio_input from pydantic-prices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "40" }, "discarded_charge": { "unit": "per_M_tokens", "price": "100" }, "message": "audio_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_output", "selected_charge": { "unit": "per_M_tokens", "price": "80" }, "discarded_charge": { "unit": "per_M_tokens", "price": "200" }, "message": "audio_output from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "40" }, "discarded_charge": { "unit": "per_M_tokens", "price": "100" }, "message": "audio_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_output", "selected_charge": { "unit": "per_M_tokens", "price": "80" }, "discarded_charge": { "unit": "per_M_tokens", "price": "200" }, "message": "audio_output from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-4o-audio-preview-2024-12-17" } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "omni", "deprecation_date": "2027-01-20", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "pdf_input": true, "parallel_function_calling": true, "stream": true }, "intro": "Audio model for gpt-4o", "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ] }, "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "released_at": "2025-08-15", "aliases": [ "gpt-4o-audio-preview-2024-10-01", "gpt-4o-audio-preview-2024-12-17", "gpt-4o-audio-preview-2025-06-03", "openai/gpt-4o-audio-preview" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-4o-latest", "model_name": "gpt-4o-latest", "display_name": "gpt-4o-latest", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "1.25" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.25", "completion": "0.333333" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.85", "completion": "1.133333", "cache_read": "1.7" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gpt-4o-latest" } ] }, { "slug": "openai/gpt-4o-mini", "model_name": "gpt-4o-mini", "display_name": "GPT-4o mini", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "web_search": { "unit": "per_k_calls", "price": "27.5" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "litellm", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "27.5" }, "discarded_charge": { "unit": "per_k_calls", "price": "10" }, "message": "web_search from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "27.5" }, "discarded_charge": { "unit": "per_k_calls", "price": "10" }, "message": "web_search from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "27.5" }, "discarded_charge": { "unit": "per_k_calls", "price": "10" }, "message": "web_search from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "27.5" }, "discarded_charge": { "unit": "per_k_calls", "price": "10" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.08" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "27.5" }, "discarded_charge": { "unit": "per_k_calls", "price": "10" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.08" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-4o-mini-2024-07-18", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "0.363636", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "0.363636", "file_search_call": "1", "prompt": "1.666667", "completion": "1.666667", "cache_read": "1.666667" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "finetune_charges": { "train": { "unit": "per_M_tokens", "price": "3" } } } ], "intro": "Small omni GPT for cheap multimodal assistance and production-scale traffic", "released_at": "2024-07-18", "knowledge_cutoff": "2023-09", "max_input_tokens": 128000, "max_output_tokens": 16384, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt-mini", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "web_search": true, "stream": true }, "model_type": "vision_understanding", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_p" ] }, "deprecated": true, "status": "deprecated", "deprecation_date": "2027-04-14", "benchmarks": { "intelligence_index": null, "coding_index": 11.4, "agentic_index": 1 }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4o-mini-2024-07-18", "openai/gpt-4o-mini", "openai/gpt-4o-mini-2024-07-18" ], "intro_i18n": { "zh-CN": "GPT-4o mini 是 OpenAI 在 GPT-4 Omni 之后推出的最新模型，支持文本+图像输入与文本输出。作为最先进的小型模型，其价格远低于前沿模型，比 GPT-3.5 Turbo 便宜 60% 以上，同时保持顶级智能水平（MMLU 达 82%）。", "zh-TW": "GPT-4o mini 是 OpenAI 在 GPT-4 Omni 之後推出的最新模型，支援文字+圖片輸入與文字輸出。作為最先進的小型模型，其價格遠低於最新前沿模型，比 GPT-3.5 Turbo 便宜超過 60%，同時保有頂尖智慧（82% MMLU）。", "ja-JP": "GPT-4o mini は GPT-4 Omni の後継となる最新モデルで、テキスト＋画像入力とテキスト出力に対応。最先端の小型モデルであり、最近の先端モデルより大幅に安価（GPT-3.5 Turbo の 60%以上安）ながら、トップクラスの知能（MMLU 82%）を維持しています。", "ru-RU": "GPT-4o mini — новейшая модель OpenAI после GPT-4 Omni, поддерживающая ввод текста и изображений с текстовым выводом. Это самая продвинутая компактная модель, значительно дешевле современных передовых моделей и более чем на 60% дешевле GPT-3.5 Turbo, при этом сохраняет высокий уровень интеллекта (82% MMLU)." }, "price_history": [ { "date": "2026-07-03", "kind": "price", "provider": "openai", "charge": "web_search", "old": "10", "new": "27.5" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-4o-mini-2024-07-18.ft-", "model_name": "gpt-4o-mini-2024-07-18.ft-", "display_name": "gpt-4o-mini-2024-07-18.ft-", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "1.2" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "GPT-4o Mini fine tuned.", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gpt-4o-mini-2024-07-18.ft-" } ] }, { "slug": "openai/gpt-4o-mini-audio-preview", "model_name": "gpt-4o-mini-audio-preview", "display_name": "gpt-4o-mini-audio-preview", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" }, "audio_input": { "unit": "per_M_tokens", "price": "10" }, "audio_output": { "unit": "per_M_tokens", "price": "20" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "audio_output": "litellm", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.15" }, "message": "audio_input from pydantic-prices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20" }, "message": "audio_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_output", "selected_charge": { "unit": "per_M_tokens", "price": "20" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10" }, "message": "audio_output from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-4o-mini-audio-preview-2024-12-17" } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "omni", "deprecation_date": "2027-01-20", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "pdf_input": true, "parallel_function_calling": true }, "intro": "Audio model for gpt-4o mini", "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "released_at": "2026-08-14", "aliases": [ "gpt-4o-mini-audio-preview-2024-12-17" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "openai/gpt-4o-mini-realtime-preview", "model_name": "gpt-4o-mini-realtime-preview", "display_name": "GPT-4o Mini Realtime", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "pydantic-prices+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" }, "audio_input": { "unit": "per_M_tokens", "price": "10" }, "audio_output": { "unit": "per_M_tokens", "price": "20" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "3" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "audio_input": "pydantic-prices", "audio_output": "pydantic-prices", "cache_write": "portkey", "audio_cache_read": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "cache_read from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "100" }, "message": "audio_input from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "audio_output", "selected_charge": { "unit": "per_M_tokens", "price": "20" }, "discarded_charge": { "unit": "per_M_tokens", "price": "200" }, "message": "audio_output from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "cache_read from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "100" }, "message": "audio_input from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "audio_output", "selected_charge": { "unit": "per_M_tokens", "price": "20" }, "discarded_charge": { "unit": "per_M_tokens", "price": "200" }, "message": "audio_output from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "portkey", "charge": "audio_cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "audio_cache_read from lobehub-modelbank conflicts with portkey; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-4o-mini-realtime-preview-2024-12-17" } ], "capabilities": { "function_calling": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "parallel_function_calling": true }, "released_at": "2024-12-17", "max_input_tokens": 128000, "max_output_tokens": 4096, "model_type": "realtime_omni", "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4o-mini-realtime-preview-2024-12-17" ], "intro_i18n": { "zh-CN": "GPT-4o-mini 实时变体，支持音频与文本的实时输入输出。", "zh-TW": "GPT-4o-mini 即時變體，支援音訊與文字的即時輸入/輸出。", "ja-JP": "GPT-4o-mini リアルタイムバリアントは、音声とテキストのリアルタイム入出力に対応しています。", "ru-RU": "Вариант GPT-4o-mini с поддержкой аудио и текста в режиме реального времени." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "openai/gpt-4o-mini-search-preview", "model_name": "gpt-4o-mini-search-preview", "display_name": "gpt-4o-mini-search-preview", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.15" }, "completion": { "unit": "per_M_tokens", "price": "0.6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "web_search": { "unit": "per_k_calls", "price": "27.5" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "litellm", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_request", "price": "0.025" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "27.5" }, "discarded_charge": { "unit": "per_k_calls", "price": "10" }, "message": "web_search from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "27.5" }, "discarded_charge": { "unit": "per_k_calls", "price": "10" }, "message": "web_search from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "27.5" }, "discarded_charge": { "unit": "per_k_calls", "price": "10" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "27.5" }, "discarded_charge": { "unit": "per_k_calls", "price": "10" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-4o-mini-search-preview-2025-03-11" } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "text_generation", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true }, "deprecated": true, "deprecation_date": "2026-07-23", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2025-03-07", "knowledge_cutoff": "2023-10", "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "family": "gpt-mini", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4o-mini-search-preview-2025-03-11", "openai/gpt-4o-mini-search-preview", "openai/gpt-4o-mini-search-preview-2025-03-11" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-4o-mini-transcribe", "model_name": "gpt-4o-mini-transcribe", "display_name": "gpt-4o-mini-transcribe", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "5" }, "audio_input": { "unit": "per_M_tokens", "price": "1.25" }, "audio_output": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "audio_output": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "audio_input from pydantic-prices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3000" }, "message": "audio_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "audio_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "audio_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "audio_input from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-4o-mini-transcribe-2025-03-20" } ], "max_input_tokens": 16000, "max_output_tokens": 2000, "model_type": "speech_recognition", "capabilities": { "function_calling": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true }, "deprecation_date": "2027-01-20", "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "deprecated": true, "released_at": "2025-03-15", "knowledge_cutoff": "2024-06", "intro": "Speech transcription model for accurate audio-to-text and captioning workflows", "family": "o-mini", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4o-mini-transcribe-2025-03-20", "gpt-4o-mini-transcribe-2025-12-15", "openai/gpt-4o-mini-transcribe" ], "intro_i18n": { "zh-CN": "GPT-4o Mini 转录模型是一款语音转文本模型，使用 GPT-4o 进行音频转录，在词错误率、语言识别与准确性方面优于原始 Whisper 模型。", "zh-TW": "GPT-4o Mini Transcribe 是一款語音轉文字模型，使用 GPT-4o 進行音訊轉錄，提升詞錯率、語言識別與準確性，優於原始 Whisper 模型。", "ja-JP": "GPT-4o Mini Transcribe は音声をテキストに変換するモデルで、元の Whisper モデルよりも単語誤認率、言語識別、精度が向上しています。", "ru-RU": "GPT-4o Mini Transcribe — это модель преобразования речи в текст, которая транскрибирует аудио с помощью GPT-4o, улучшая точность распознавания слов, определение языка и общую точность по сравнению с оригинальной моделью Whisper." }, "price_history": [ { "date": "2026-07-29", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-28", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-28", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-27", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "openai/gpt-4o-mini-tts", "model_name": "gpt-4o-mini-tts", "display_name": "GPT-4o Mini TTS", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "audio_output": { "unit": "per_M_tokens", "price": "12" }, "audio_input": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "audio_output": "pydantic-prices", "audio_input": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "12" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "12" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "12" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "completion from portkey conflicts with pydantic-prices; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-4o-mini-tts-2025-03-20" } ], "capabilities": { "audio_output": true, "pdf_input": true, "audio_input": true, "prompt_caching": true, "function_calling": true, "structured_output": true }, "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "model_type": "speech_synthesis", "released_at": "2025-03-19", "max_input_tokens": 2000, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4o-mini-tts-2025-03-20", "gpt-4o-mini-tts-2025-12-15", "openai/gpt-4o-mini-tts", "openai/gpt-4o-mini-tts-2025-03-20", "openai/gpt-4o-mini-tts-2025-12-15" ], "intro_i18n": { "zh-CN": "GPT-4o mini TTS 是一款基于 GPT-4o mini 的文本转语音模型，可将文本转换为自然语音，最大输入为 2000 个 token。", "zh-TW": "GPT-4o mini TTS 是一款基於 GPT-4o mini 的文字轉語音模型，將文字轉換為自然語音，最多支援 2000 個 token 輸入。", "ja-JP": "GPT-4o mini TTS は GPT-4o mini をベースにしたテキスト読み上げモデルで、最大 2000 トークンのテキストを自然な音声に変換します。", "ru-RU": "GPT-4o mini TTS — это модель преобразования текста в речь, основанная на GPT-4o mini, преобразующая текст в естественно звучащую речь с максимальным входом до 2000 токенов." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GPT-4o Mini TTS" } ] }, { "slug": "openai/gpt-4o-realtime-preview", "model_name": "gpt-4o-realtime-preview", "display_name": "GPT-4o Realtime 241217", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "pydantic-prices+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "20" }, "cache_read": { "unit": "per_M_tokens", "price": "2.5" }, "audio_input": { "unit": "per_M_tokens", "price": "40" }, "audio_output": { "unit": "per_M_tokens", "price": "80" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "audio_input": "pydantic-prices", "audio_output": "pydantic-prices", "cache_write": "portkey", "audio_cache_read": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "40" }, "discarded_charge": { "unit": "per_M_tokens", "price": "100" }, "message": "audio_input from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "audio_output", "selected_charge": { "unit": "per_M_tokens", "price": "80" }, "discarded_charge": { "unit": "per_M_tokens", "price": "200" }, "message": "audio_output from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "portkey", "charge": "audio_cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20" }, "message": "audio_cache_read from portkey conflicts with portkey; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "pydantic-prices", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "40" }, "discarded_charge": { "unit": "per_M_tokens", "price": "100" }, "message": "audio_input from lobehub-modelbank conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "pydantic-prices", "charge": "audio_output", "selected_charge": { "unit": "per_M_tokens", "price": "80" }, "discarded_charge": { "unit": "per_M_tokens", "price": "200" }, "message": "audio_output from lobehub-modelbank conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "portkey", "charge": "audio_cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20" }, "message": "audio_cache_read from lobehub-modelbank conflicts with portkey; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-4o-realtime-preview-2024-10-01" } ], "capabilities": { "function_calling": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "parallel_function_calling": true }, "released_at": "2024-12-17", "max_input_tokens": 16000, "max_output_tokens": 4096, "model_type": "realtime_omni", "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4o-realtime-preview-2024-10-01", "gpt-4o-realtime-preview-2024-12-17", "gpt-4o-realtime-preview-2025-06-03" ], "intro_i18n": { "zh-CN": "GPT-4o 实时变体，支持音频与文本的实时输入输出。", "zh-TW": "GPT-4o 即時變體，支援音訊與文字的即時輸入/輸出。", "ja-JP": "GPT-4o リアルタイムバリアントは、音声とテキストのリアルタイム入出力に対応しています。", "ru-RU": "Вариант GPT-4o с поддержкой аудио и текста в режиме реального времени." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-19", "kind": "limit", "old": "128000", "new": "16000", "note": "max_input_tokens" } ] }, { "slug": "openai/gpt-4o-search-preview", "model_name": "gpt-4o-search-preview", "display_name": "gpt-4o-search-preview", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "1.25" }, "web_search": { "unit": "per_k_calls", "price": "35" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "litellm", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_request", "price": "0.025" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_request", "price": "0.025" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "35" }, "discarded_charge": { "unit": "per_k_calls", "price": "25" }, "message": "web_search from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "35" }, "discarded_charge": { "unit": "per_k_calls", "price": "25" }, "message": "web_search from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "35" }, "discarded_charge": { "unit": "per_k_calls", "price": "10" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "35" }, "discarded_charge": { "unit": "per_k_calls", "price": "10" }, "message": "web_search from llmdb conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-4o-search-preview-2025-03-11" } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "text_generation", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true }, "deprecated": true, "deprecation_date": "2026-07-23", "intro": "GPT-4o Search Previewis a specialized model for web search in Chat Completions. It is trained to understand and execute web search queries.", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2026-02-24", "knowledge_cutoff": "2023-10", "family": "gpt", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4o-search-preview-2025-03-11", "openai/gpt-4o-search-preview", "openai/gpt-4o-search-preview-2025-03-11" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-4o-transcribe", "model_name": "gpt-4o-transcribe", "display_name": "gpt-4o-transcribe", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "audio_input": { "unit": "per_M_tokens", "price": "2.5" }, "audio_output": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "audio_output": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6" }, "message": "audio_input from pydantic-prices conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6000" }, "message": "audio_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6" }, "message": "audio_input from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 16000, "max_output_tokens": 2000, "model_type": "speech_recognition", "capabilities": { "function_calling": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true }, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "released_at": "2025-03-15", "knowledge_cutoff": "2024-06", "intro": "Speech transcription model for accurate audio-to-text and captioning workflows", "family": "gpt", "deprecation_date": "2026-10-15", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4o-transcribe-2025-03-20", "openai/gpt-4o-transcribe" ], "intro_i18n": { "zh-CN": "GPT-4o 转录模型是一款语音转文本模型，使用 GPT-4o 进行音频转录，在词错误率、语言识别与准确性方面优于原始 Whisper 模型。", "zh-TW": "GPT-4o Transcribe 是一款語音轉文字模型，使用 GPT-4o 進行音訊轉錄，提升詞錯率、語言識別與準確性，優於原始 Whisper 模型。", "ja-JP": "GPT-4o Transcribe は音声をテキストに変換するモデルで、元の Whisper モデルよりも単語誤認率、言語識別、精度が向上しています。", "ru-RU": "GPT-4o Transcribe — это модель преобразования речи в текст, которая транскрибирует аудио с помощью GPT-4o, улучшая точность распознавания слов, определение языка и общую точность по сравнению с оригинальной моделью Whisper." }, "price_history": [ { "date": "2026-07-28", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-28", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-27", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "openai/gpt-4o-transcribe-diarize", "model_name": "gpt-4o-transcribe-diarize", "display_name": "gpt-4o-transcribe-diarize", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "audio_input": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6" }, "message": "audio_input from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 16000, "max_output_tokens": 2000, "model_type": "speech_recognition", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true }, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "released_at": "2025-06-24", "knowledge_cutoff": "2024-06", "deprecation_date": "2027-04-15", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-4o-transcribe-diarize-2025-10-15", "openai/gpt-4o-transcribe-diarize" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-15", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-15", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-15", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "openai/gpt-5", "model_name": "gpt-5", "display_name": "GPT-5", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "computeprices", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from computeprices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "computeprices", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "30" }, "message": "completion from computeprices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "computeprices", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.625" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "batch prompt from computeprices conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "computeprices", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15" }, "message": "batch completion from computeprices conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-5-2025-08-07", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows", "released_at": "2025-08-07", "knowledge_cutoff": "2024-09", "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "deprecation_date": "2026-12-11", "deprecated": true, "benchmarks": { "intelligence_index": 35.3, "coding_index": 37.8, "agentic_index": 26.5 }, "reasoning_config": { "mandatory": true }, "aliases": [ "azure/gpt-5", "gpt-5-2025-08-07", "openai-responses/gpt-5", "openai/gpt-5", "openai/gpt-5-2025-08-07", "pa/gpt-5", "pa/gpt-5-2025-08-07" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5 —— 旗舰模型，具备先进推理与多模态能力。", "zh-TW": "OpenAI GPT-5 —— 旗艦模型，具備先進推理與多模態輸入能力。", "ja-JP": "GPT-5 by OpenAI — 高度な推論とマルチモーダル入力を備えたフラッグシップモデル。", "ru-RU": "GPT-5 от OpenAI — флагманская модель с продвинутыми возможностями рассуждения и мультимодальным вводом." }, "price_history": [ { "date": "2026-07-03", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/gpt-5-chat", "model_name": "gpt-5-chat", "display_name": "gpt-5-chat", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true, "image_output": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "released_at": "2025-08-07", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt-codex", "parameters": { "unsupported": [ "temperature" ] }, "docs_url": "https://azure.microsoft.com/en-us/blog/gpt-5-in-azure-ai-foundry-the-future-of-ai-apps-and-agents-starts-here/", "deprecated": true, "deprecation_date": "2026-06-29", "knowledge_cutoff": "2024-09", "aliases": [ "gpt-5-chat-2025-08-07", "gpt-5-chat-2025-08-15", "gpt-5-chat-2025-10-03", "openai/gpt-5-chat" ], "intro_i18n": { "zh-CN": "GPT-5 Chat 是一款预览模型，专为对话场景优化。支持文本与图像输入，仅输出文本，适用于聊天机器人与对话式 AI 应用。", "zh-TW": "GPT-5 Chat 是一款預覽模型，針對對話場景進行最佳化。支援文字與圖片輸入，僅輸出文字，適用於聊天機器人與對話式 AI 應用。", "ja-JP": "GPT-5 Chat は会話シナリオに最適化されたプレビューモデルで、テキストと画像の入力に対応し、テキスト出力を行います。チャットボットや会話型 AI アプリケーションに適しています。", "ru-RU": "GPT-5 Chat — предварительная модель, оптимизированная для разговорных сценариев. Поддерживает ввод текста и изображений, выводит только текст и подходит для чат-ботов и разговорного ИИ." }, "price_history": [ { "date": "2026-07-03", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/gpt-5-chat-latest", "model_name": "gpt-5-chat-latest", "display_name": "gpt-5-chat-latest", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+helicone-registry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "litellm+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-07-23", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "GPT-5 Chat Latest is a continuously updated version of GPT-5 optimized for conversational interactions. It receives regular updates with the latest improvements in dialogue management, safety, and helpfulness. Features a 128K context window and 16K max output tokens, making it ideal for focused conversations. Knowledge cutoff: September 30, 2024.", "knowledge_cutoff": "2024-09", "parameters": { "supported": [ "max_completion_tokens", "response_format", "seed", "stop", "tool_choice", "tools", "verbosity" ], "unsupported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "n", "presence_penalty", "temperature", "top_logprobs", "top_p" ] }, "released_at": "2025-08-07", "family": "gpt-codex", "aliases": [ "openai/gpt-5-chat-latest", "pa/gpt-5-chat-latest" ], "intro_i18n": { "zh-CN": "GPT-5 是 CometAPI 最新的旗舰模型，专注于跨领域编码和代理任务，在准确性、速度、推理能力、上下文感知、结构化思维和问题解决方面有重大提升。", "zh-TW": "GPT-5 是 CometAPI 最新的旗艦模型，專為跨領域編碼和代理任務而設計，在準確性、速度、推理、上下文感知、結構化思維和問題解決方面取得了重大進展。", "ja-JP": "GPT-5は、CometAPIの最新旗艦モデルで、クロスドメインのコーディングとエージェントタスクにおいて、精度、速度、推論、コンテキスト認識、構造的思考、問題解決能力において大幅な向上を実現しています。", "ru-RU": "GPT-5 — это последняя флагманская модель CometAPI для междисциплинарного кодирования и задач агентов, с существенными улучшениями в точности, скорости, рассуждении, осведомленности о контексте, структурированном мышлении и решении задач." }, "price_history": [ { "date": "2026-07-25", "kind": "limit", "old": "400000", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-07-25", "kind": "limit", "old": "128000", "new": "16384", "note": "max_output_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5-codex", "model_name": "gpt-5-codex", "display_name": "gpt-5-codex", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+helicone-registry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "litellm+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-07-23", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "Specialized model for code generation and analysis", "knowledge_cutoff": "2025-01", "parameters": { "supported": [ "max_completion_tokens", "response_format", "seed", "stop", "tool_choice", "tools" ], "unsupported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "temperature", "top_logprobs", "top_p", "verbosity" ] }, "released_at": "2025-09-15", "family": "gpt-codex", "aliases": [ "gpt-5-codex-2025-09-15", "openai-responses/gpt-5-codex", "openai/gpt-5-codex", "pa/gpt-5-codex" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5 Codex —— 具备工具调用支持的代码专项模型。", "zh-TW": "OpenAI GPT-5 Codex —— 專為程式設計優化，並支援工具使用。", "ja-JP": "GPT-5 Codex by OpenAI — ツール使用をサポートするコーディング特化型バリアント。", "ru-RU": "GPT-5 Codex от OpenAI — специализированная модель для программирования с поддержкой инструментов." }, "price_history": [ { "date": "2026-07-25", "kind": "limit", "old": "400000", "new": "272000", "note": "max_input_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5-image", "model_name": "gpt-5-image", "display_name": "GPT-5 Image", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "1.25" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "stream": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2025-10-14", "knowledge_cutoff": "2024-10", "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "image", "text" ] }, "family": "gpt", "model_type": "image_generation", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-5-image" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GPT-5 Image" } ] }, { "slug": "openai/gpt-5-image-mini", "model_name": "gpt-5-image-mini", "display_name": "GPT-5 Image Mini", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "stream": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2025-10-16", "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "pdf", "image", "text" ], "output": [ "image", "text" ] }, "family": "gpt", "model_type": "image_generation", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-5-image-mini" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "OpenAI: GPT-5 Image Mini" } ] }, { "slug": "openai/gpt-5-mini", "model_name": "gpt-5-mini", "display_name": "GPT-5 Mini", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gpt-5-mini-2025-08-07", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1.8", "completion": "1.8", "cache_read": "1.8" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Small GPT-5 for responsive agents, coding help, and everyday automation", "released_at": "2025-08-07", "knowledge_cutoff": "2024-05", "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt-mini", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "deprecation_date": "2026-12-11", "deprecated": true, "benchmarks": { "intelligence_index": 25.8, "coding_index": 15.6, "agentic_index": 19.6 }, "reasoning_config": { "mandatory": true }, "aliases": [ "azure/gpt-5-mini", "gpt-5-mini-2025-08-07", "openai-responses/gpt-5-mini", "openai/gpt-5-mini", "openai/gpt-5-mini-2025-08-07", "pa/gpt-5-mini", "pa/gpt-5-mini-2025-08-07" ], "intro_i18n": { "zh-CN": "GPT-5 的快速、低成本变体，适用于定义明确的任务，在保持质量的同时提供更快响应。", "zh-TW": "GPT-5 的快速且具成本效益的變體，適用於明確任務，回應更快且維持品質。", "ja-JP": "明確に定義されたタスク向けに高速かつコスト効率の高い GPT-5 バリアントで、品質を維持しながら迅速な応答を提供します。", "ru-RU": "Быстрый и экономичный вариант GPT-5 для четко определенных задач, обеспечивающий быстрые ответы при сохранении качества." }, "price_history": [ { "date": "2026-07-09", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-03", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/gpt-5-nano", "model_name": "gpt-5-nano", "display_name": "GPT-5 Nano", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.05" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.005" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "cache_write": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "cache_write": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gpt-5-nano-2025-08-07", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs", "released_at": "2025-08-07", "knowledge_cutoff": "2024-05", "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt-nano", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "deprecation_date": "2026-12-11", "deprecated": true, "reasoning_config": { "mandatory": true }, "aliases": [ "azure/gpt-5-nano", "gpt-5-nano-2025-08-07", "openai-responses/gpt-5-nano", "openai/gpt-5-nano", "openai/gpt-5-nano-2025-08-07", "pa/gpt-5-nano", "pa/gpt-5-nano-2025-08-07" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5 Nano —— 轻量级高性价比模型。", "zh-TW": "OpenAI GPT-5 Nano —— 輕量、省成本模型。", "ja-JP": "GPT-5 Nano by OpenAI — 軽量でコスト効率の良いモデル。", "ru-RU": "GPT-5 Nano от OpenAI — лёгкая и экономичная модель." }, "price_history": [ { "date": "2026-07-09", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5-pro", "model_name": "gpt-5-pro", "display_name": "GPT-5 Pro", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "120" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.005" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_read": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_read": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "service_tier_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "7.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15" }, "message": "batch prompt from truefoundry conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "truefoundry", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "60" }, "discarded_charge": { "unit": "per_M_tokens", "price": "120" }, "message": "batch completion from truefoundry conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-5-pro-2025-10-06", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning", "released_at": "2025-10-06", "knowledge_cutoff": "2024-09", "max_input_tokens": 400000, "max_output_tokens": 272000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt-pro", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "deprecation_date": "2026-12-11", "deprecated": true, "docs_url": "https://learn.microsoft.com/en-us/azure/ai-foundry/foundry-models/concepts/models-sold-directly-by-azure?pivots=azure-openai&tabs=global-standard-aoai%2Cstandard-chat-completions%2Cglobal-standard#gpt-5", "reasoning_config": { "mandatory": true }, "aliases": [ "gpt-5-pro-2025-10-01", "gpt-5-pro-2025-10-06", "openai-responses/gpt-5-pro", "openai/gpt-5-pro", "openai/gpt-5-pro-2025-10-01", "openai/gpt-5-pro-2025-10-06", "pa/gpt-5-pro", "pa/gpt-5-pro-2025-10-01" ], "intro_i18n": { "zh-CN": "GPT-5 Pro 使用更多计算资源以实现更深入的思考，持续提供更优质的答案。", "zh-TW": "GPT-5 Pro 使用更多運算資源以進行更深入思考，穩定提供更優質的答案。", "ja-JP": "GPT-5 Pro はより多くの計算資源を使用して深く思考し、常に優れた回答を提供するモデルです。", "ru-RU": "GPT-5 Pro использует больше вычислительных ресурсов для более глубокого анализа и стабильно выдает более качественные ответы." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5-search-api", "model_name": "gpt-5-search-api", "display_name": "gpt-5-search-api", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_request", "price": "0.01" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-5-search-api-2025-10-14" } ], "max_input_tokens": 272000, "max_output_tokens": 128000, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-5-search-api-2025-10-14", "openai/gpt-5-search-api", "openai/gpt-5-search-api-2025-10-14" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" } ] }, { "slug": "openai/gpt-5.1-2025-11-13", "model_name": "gpt-5.1-2025-11-13", "display_name": "gpt-5.1-2025-11-13", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.125" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.13" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-5.1", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Sharper GPT-5 generation for coding, product work, and tool-assisted tasks", "released_at": "2025-11-13", "knowledge_cutoff": "2024-09", "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "deprecation_date": "2027-05-15", "benchmarks": { "intelligence_index": 37.5, "coding_index": 49.4, "agentic_index": 21.6 }, "reasoning_config": { "mandatory": false }, "aliases": [ "azure/gpt-5.1", "gpt-5-1", "gpt-5.1", "openai-responses/gpt-5.1", "openai/gpt-5.1", "openai/gpt-5.1-2025-11-13", "pa/gpt-5.1-2025-11-13" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.1 —— 推理准确度进一步提升的改进版 GPT-5。", "zh-TW": "OpenAI GPT-5.1 —— 在推理準確性上進一步提升。", "ja-JP": "GPT-5.1 by OpenAI — 推論精度が向上した改良版GPT-5。", "ru-RU": "GPT-5.1 от OpenAI — улучшенная версия GPT-5 с повышенной точностью рассуждений." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "2.13", "new": "18.3" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.27", "new": "2.29" }, { "date": "2026-08-14", "kind": "price", "provider": "cloudflare-ai-gateway", "charge": "cache_read", "old": "0.13", "new": "0.125" }, { "date": "2026-08-13", "kind": "price", "provider": "fastrouter", "charge": "cache_read", "old": "0.125", "new": "0.13" }, { "date": "2026-08-11", "kind": "price", "provider": "fastrouter", "charge": "cache_read", "old": "0.13", "new": "0.125" }, { "date": "2026-08-08", "kind": "price", "provider": "fastrouter", "charge": "cache_read", "old": "0.125", "new": "0.13" }, { "date": "2026-08-07", "kind": "price", "provider": "fastrouter", "charge": "cache_read", "old": "0.13", "new": "0.125" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "cache_read", "old": "0.14", "new": "0.156" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "completion", "old": "9.838", "new": "10.96" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "prompt", "old": "1.234", "new": "1.375" }, { "date": "2026-08-05", "kind": "price", "provider": "fastrouter", "charge": "cache_read", "old": "0.125", "new": "0.13" }, { "date": "2026-08-02", "kind": "price", "provider": "fastrouter", "charge": "cache_read", "old": "0.13", "new": "0.125" }, { "date": "2026-08-01", "kind": "price", "provider": "fastrouter", "charge": "cache_read", "old": "0.125", "new": "0.13" }, { "date": "2026-07-27", "kind": "price", "provider": "fastrouter", "charge": "cache_read", "old": "0.13", "new": "0.125" }, { "date": "2026-07-25", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.06", "new": "0.03" }, { "date": "2026-07-25", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "4.14", "new": "2.13" }, { "date": "2026-07-25", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.51", "new": "0.27" }, { "date": "2026-07-25", "kind": "price", "provider": "fastrouter", "charge": "cache_read", "old": "0.125", "new": "0.13" }, { "date": "2026-07-22", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "2.13", "new": "4.14" }, { "date": "2026-07-22", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.27", "new": "0.51" } ] }, { "slug": "openai/gpt-5.1-chat-latest", "model_name": "gpt-5.1-chat-latest", "display_name": "gpt-5.1-chat-latest", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+helicone-registry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "litellm+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-07-23", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true, "image_output": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "GPT-5.1 Chat is a continuously updated version of GPT-5.1 optimized for conversational interactions. It receives regular updates with the latest improvements in dialogue management, safety, and helpfulness. Features a 128K context window and 16K max output tokens, making it ideal for focused conversations.", "knowledge_cutoff": "2025-01", "parameters": { "supported": [ "max_completion_tokens", "response_format", "seed", "stop", "tool_choice", "tools", "verbosity" ], "unsupported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "n", "presence_penalty", "temperature", "top_logprobs", "top_p" ] }, "released_at": "2025-11-13", "family": "gpt-codex", "aliases": [ "gpt-5-1-chat-latest", "openai/gpt-5.1-chat-latest" ], "intro_i18n": { "zh-CN": "GPT-5.1 Chat：GPT-5.1 的 ChatGPT 变体，专为对话场景打造。", "zh-TW": "GPT-5.1 Chat：GPT-5.1 的 ChatGPT 變體，專為對話場景打造。", "ja-JP": "GPT-5.1 Chat：GPT-5.1 のチャット向けバリアントで、会話シナリオに最適化されています。", "ru-RU": "GPT-5.1 Chat: вариант GPT-5.1, предназначенный для сценариев общения." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5.1-codex", "model_name": "gpt-5.1-codex", "display_name": "gpt-5.1-codex", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+helicone-registry+portkey+llmdb+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "litellm+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-07-23", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true, "image_output": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "Specialized model for code generation and analysis, based on GPT-5.1", "knowledge_cutoff": "2025-01", "parameters": { "supported": [ "max_completion_tokens", "response_format", "seed", "stop", "tool_choice", "tools" ], "unsupported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "temperature", "top_logprobs", "top_p", "verbosity" ] }, "released_at": "2025-11-13", "family": "gpt-codex", "reasoning_config": { "mandatory": true }, "aliases": [ "gpt-5.1-codex-2025-11-13", "openai-responses/gpt-5.1-codex", "openai/gpt-5.1-codex" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.1 Codex —— 加强工具调用的代码专项模型。", "zh-TW": "OpenAI GPT-5.1 Codex —— 以程式能力為重點並增強工具使用。", "ja-JP": "GPT-5.1 Codex by OpenAI — ツール使用が強化されたコーディング特化型バリアント。", "ru-RU": "GPT-5.1 Codex от OpenAI — модель, ориентированная на программирование, с расширенной поддержкой инструментов." }, "price_history": [ { "date": "2026-07-25", "kind": "limit", "old": "400000", "new": "272000", "note": "max_input_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5.1-codex-max", "model_name": "gpt-5.1-codex-max", "display_name": "gpt-5.1-codex-max", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "0.125" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-07-23", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2025-11-13", "knowledge_cutoff": "2024-09", "family": "gpt-codex", "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "parameters": { "unsupported": [ "temperature" ] }, "docs_url": "https://openrouter.ai/openai/gpt-5.1-codex-max", "reasoning_config": { "mandatory": true }, "aliases": [ "gpt-5.1-codex-max-2025-12-04", "openai/gpt-5.1-codex-max" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.1 Codex Max —— 最高性能的 Codex 变体。", "zh-TW": "OpenAI GPT-5.1 Codex Max —— Codex 系列最高能力版本。", "ja-JP": "GPT-5.1 Codex Max by OpenAI — 最大能力のCodexバリアント。", "ru-RU": "GPT-5.1 Codex Max от OpenAI — максимально мощная версия Codex." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-08-06", "kind": "capability", "note": "image_output: true→false" }, { "date": "2026-07-25", "kind": "limit", "old": "400000", "new": "272000", "note": "max_input_tokens" }, { "date": "2026-07-09", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5.1-codex-mini", "model_name": "gpt-5.1-codex-mini", "display_name": "gpt-5.1-codex-mini", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.025" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-07-23", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true, "image_output": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "Compact specialized model for code generation and analysis, based on GPT-5.1", "knowledge_cutoff": "2025-01", "parameters": { "supported": [ "max_completion_tokens", "response_format", "seed", "stop", "tool_choice", "tools" ], "unsupported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "temperature", "top_logprobs", "top_p", "verbosity" ] }, "released_at": "2025-11-13", "family": "gpt-codex", "reasoning_config": { "mandatory": false }, "aliases": [ "gpt-5.1-codex-mini-2025-11-13", "openai/gpt-5.1-codex-mini" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.1 Codex Mini —— 小型但强大的编码模型。", "zh-TW": "OpenAI GPT-5.1 Codex Mini —— 輕量型程式模型，能力依然強大。", "ja-JP": "GPT-5.1 Codex Mini by OpenAI — コンパクトなコーディングモデルで強力な能力を備えています。", "ru-RU": "GPT-5.1 Codex Mini от OpenAI — компактная, но производительная модель для программирования." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-25", "kind": "limit", "old": "400000", "new": "272000", "note": "max_input_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5.2-2025-12-11", "model_name": "gpt-5.2-2025-12-11", "display_name": "gpt-5.2-2025-12-11", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.75" }, "completion": { "unit": "per_M_tokens", "price": "14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.175" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gpt-5.2", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Reliable GPT generation for broad coding, writing, and tool-assisted product work", "released_at": "2025-12-11", "knowledge_cutoff": "2025-08", "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "deprecation_date": "2027-06-08", "reasoning_config": { "mandatory": false }, "aliases": [ "gpt-5-2", "gpt-5.2", "openai-responses/gpt-5.2", "openai/gpt-5.2", "openai/gpt-5.2-2025-12-11", "pa/gpt-5.2" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.2 —— 推理与多模态处理能力全面升级。", "zh-TW": "OpenAI GPT-5.2 —— 升級版推理與多模態處理能力。", "ja-JP": "GPT-5.2 by OpenAI — 推論とマルチモーダル処理がアップグレードされたモデル。", "ru-RU": "GPT-5.2 от OpenAI — улучшенная модель с расширенными возможностями рассуждения и мультимодальной обработки." }, "price_history": [ { "date": "2026-07-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-03", "kind": "limit", "old": "272000", "new": "400000", "note": "max_input_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "openai/gpt-5.2-chat-2026-02-10", "model_name": "gpt-5.2-chat-2026-02-10", "display_name": "GPT-5.2 Chat", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "1.75" }, "completion": { "unit": "per_M_tokens", "price": "14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.175" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.2-chat-2025-12-11", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "web_search": true, "stream": true }, "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "released_at": "2025-12-10", "knowledge_cutoff": "2025-08", "max_input_tokens": 128000, "max_output_tokens": 32000, "modalities": { "input": [ "pdf", "image", "text" ], "output": [ "text" ] }, "family": "gpt-codex", "parameters": { "unsupported": [ "temperature" ] }, "model_type": "vision_understanding", "deprecated": true, "deprecation_date": "2026-06-29", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-5.2-chat", "gpt-5.2-chat-2025-12-11", "openai/gpt-5.2-chat" ], "intro_i18n": { "zh-CN": "GPT-5.2 Chat 是 ChatGPT 的变体，用于体验最新的对话改进。", "zh-TW": "GPT-5.2 Chat 是 ChatGPT 的變體，用於體驗最新的對話改進。", "ja-JP": "GPT-5.2 Chatは、最新の会話機能を体験できるChatGPTバリアントです。", "ru-RU": "GPT-5.2 Chat — вариант ChatGPT для знакомства с последними улучшениями в диалогах." }, "price_history": [ { "date": "2026-08-12", "kind": "delisted", "note": "deprecated" }, { "date": "2026-08-10", "kind": "delisted", "note": "deprecated" }, { "date": "2026-08-10", "kind": "limit", "old": "16384", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "GPT-5.2 Chat" } ] }, { "slug": "openai/gpt-5.2-chat-latest", "model_name": "gpt-5.2-chat-latest", "display_name": "GPT-5.2 Chat", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.75" }, "completion": { "unit": "per_M_tokens", "price": "14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.175" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "released_at": "2025-12-11", "knowledge_cutoff": "2025-08", "max_input_tokens": 128000, "max_output_tokens": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt-codex", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-08-10", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-5.2-chat-latest", "pa/gpt-5.2-chat-latest" ], "intro_i18n": { "zh-CN": "GPT-5.2 Chat 是 ChatGPT 的最新对话版本，带来最新的对话体验改进。", "zh-TW": "GPT-5.2 Chat 是 ChatGPT 的最新對話版本，帶來最新的對話體驗改進。", "ja-JP": "GPT-5.2 Chatは、最新の会話機能を備えたChatGPTバリアント（chat-latest）です。", "ru-RU": "GPT-5.2 Chat — это вариант ChatGPT (chat-latest) с последними улучшениями в области диалогов." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5.2-codex", "model_name": "gpt-5.2-codex", "display_name": "gpt-5.2-codex", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.75" }, "completion": { "unit": "per_M_tokens", "price": "14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.175" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 272000, "max_output_tokens": 128000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-07-23", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2025-12-11", "knowledge_cutoff": "2025-08", "family": "gpt-codex", "intro": "Code-specialist GPT for repository edits, reviews, and long-running software agents", "parameters": { "unsupported": [ "temperature" ] }, "reasoning_config": { "mandatory": true }, "aliases": [ "gpt-5.2-codex-2026-01-14", "openai-responses/gpt-5.2-codex", "openai/gpt-5.2-codex" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.2 Codex —— 工具调用准确度更高的代码专项模型。", "zh-TW": "OpenAI GPT-5.2 Codex —— 專注程式能力並提升工具調用準確度。", "ja-JP": "GPT-5.2 Codex by OpenAI — ツール呼び出し精度が向上したコーディング特化型モデル。", "ru-RU": "GPT-5.2 Codex от OpenAI — специализированная модель программирования с повышенной точностью вызовов инструментов." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-08-06", "kind": "capability", "note": "image_output: true→false" }, { "date": "2026-07-25", "kind": "limit", "old": "400000", "new": "272000", "note": "max_input_tokens" }, { "date": "2026-07-09", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5.2-pro-2025-12-11", "model_name": "gpt-5.2-pro-2025-12-11", "display_name": "gpt-5.2-pro-2025-12-11", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "21" }, "completion": { "unit": "per_M_tokens", "price": "168" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gpt-5.2-pro", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows", "released_at": "2025-12-11", "knowledge_cutoff": "2025-08", "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt-pro", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "reasoning_config": { "mandatory": true }, "aliases": [ "gpt-5-2-pro", "gpt-5.2-pro", "openai/gpt-5.2-pro", "openai/gpt-5.2-pro-2025-12-11", "pa/gpt-5.2-pro" ], "intro_i18n": { "zh-CN": "GPT-5.2 Pro：更智能、更精准的 GPT-5.2 变体（仅限 Responses API），适用于复杂问题和多轮推理。", "zh-TW": "GPT-5.2 Pro：更智慧、更精確的 GPT-5.2 變體（僅限 Responses API），適用於高難度問題與多輪長推理。", "ja-JP": "GPT-5.2 Proは、より賢く精密なGPT-5.2バリアント（Responses API専用）であり、難解な問題や長い多段階推論に適しています。", "ru-RU": "GPT-5.2 pro: более умный и точный вариант GPT-5.2 (только через Responses API), подходит для сложных задач и многошагового рассуждения." }, "price_history": [ { "date": "2026-07-03", "kind": "limit", "old": "272000", "new": "400000", "note": "max_input_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/gpt-5.3", "model_name": "gpt-5.3", "display_name": "gpt-5.3", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.75" }, "completion": { "unit": "per_M_tokens", "price": "14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.175" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "GPT-5.3 Instant model used in ChatGPT", "max_input_tokens": 128000, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gpt-5.3" } ] }, { "slug": "openai/gpt-5.3-chat-latest", "model_name": "gpt-5.3-chat-latest", "display_name": "GPT-5.3 Chat", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+truefoundry+portkey+lobehub-modelbank+pricetoken+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.75" }, "completion": { "unit": "per_M_tokens", "price": "14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.175" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Chat-tuned GPT model for conversational assistance, writing, and tool workflows", "released_at": "2026-03-03", "knowledge_cutoff": "2025-08", "max_input_tokens": 128000, "max_output_tokens": 16384, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-08-10", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-5.3-chat-latest" ], "intro_i18n": { "zh-CN": "GPT-5.3 Chat 是最新的 ChatGPT 模型，改进了对话体验。", "zh-TW": "GPT-5.3 Chat 是最新的 ChatGPT 模型，提供改進的對話體驗。", "ja-JP": "GPT-5.3 ChatはChatGPTで使用される最新のChatGPTモデルで、会話体験が向上しています。", "ru-RU": "GPT-5.3 Chat — это последняя модель ChatGPT, используемая в ChatGPT, с улучшенным опытом общения." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5.3-codex", "model_name": "gpt-5.3-codex", "display_name": "GPT-5.3 Codex", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+pricetoken+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.75" }, "completion": { "unit": "per_M_tokens", "price": "14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.175" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "released_at": "2026-02-05", "knowledge_cutoff": "2025-08", "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt-codex", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "deprecation_date": "2027-08-24", "reasoning_config": { "mandatory": false }, "aliases": [ "gpt-5-3-codex", "gpt-5.3-codex-2026-02-20", "gpt-5.3-codex-2026-02-24", "openai-responses/gpt-5.3-codex", "openai/gpt-5.3-codex" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.3 Codex —— 新一代 Codex，具备更强代码理解能力。", "zh-TW": "OpenAI GPT-5.3 Codex —— 最新 Codex，具備更強的程式理解能力。", "ja-JP": "GPT-5.3 Codex by OpenAI — コード理解が強化された最新のCodexモデル。", "ru-RU": "GPT-5.3 Codex от OpenAI — последняя версия Codex с улучшенным пониманием кода." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-09", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-5.3-codex-spark", "model_name": "gpt-5.3-codex-spark", "display_name": "GPT-5.3 Codex Spark", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.75" }, "completion": { "unit": "per_M_tokens", "price": "14" }, "cache_read": { "unit": "per_M_tokens", "price": "0.175" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "cross_checked" } } ], "intro": "Coding-optimized GPT model for repository edits, reviews, and agentic software work", "released_at": "2026-02-05", "knowledge_cutoff": "2025-08", "max_input_tokens": 128000, "max_output_tokens": 32000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt-codex-spark", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-5.3-codex-spark" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.3 Codex Spark —— 速度优化的小型编码模型。", "zh-TW": "OpenAI GPT-5.3 Codex Spark —— 高速優化的輕量型程式模型。", "ja-JP": "GPT-5.3 Codex Spark by OpenAI — スピードに最適化されたコンパクトなコーディングモデル。", "ru-RU": "GPT-5.3 Codex Spark от OpenAI — компактная модель программирования, оптимизированная для скорости." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/gpt-5.4-2026-03-05", "model_name": "gpt-5.4-2026-03-05", "display_name": "gpt-5.4-2026-03-05", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.25" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "pydantic-prices", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "pydantic-prices introduced a ≥272000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "truefoundry introduced a ≥272000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "truefoundry introduced a ≥272000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "helicone-registry", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "helicone-registry introduced a ≥272000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "helicone-registry", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "helicone-registry introduced a ≥272000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-5.4", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1", "cache_read": "0.52" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.75" }, "completion": { "unit": "per_M_tokens", "price": "16.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4", "region": "ae", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.75" }, "completion": { "unit": "per_M_tokens", "price": "16.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4", "region": "au", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.75" }, "completion": { "unit": "per_M_tokens", "price": "16.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4", "region": "ca", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.75" }, "completion": { "unit": "per_M_tokens", "price": "16.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4", "region": "eu", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.75" }, "completion": { "unit": "per_M_tokens", "price": "16.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4", "region": "gb", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.75" }, "completion": { "unit": "per_M_tokens", "price": "16.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4", "region": "in", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.75" }, "completion": { "unit": "per_M_tokens", "price": "16.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4", "region": "jp", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.75" }, "completion": { "unit": "per_M_tokens", "price": "16.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4", "region": "kr", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.75" }, "completion": { "unit": "per_M_tokens", "price": "16.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4", "region": "sg", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.75" }, "completion": { "unit": "per_M_tokens", "price": "16.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4", "region": "us", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.52" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] } ], "intro": "Agent-ready GPT for coding and computer-use workflows at a lower cost", "released_at": "2026-03-05", "knowledge_cutoff": "2025-08", "max_input_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "parallel_function_calling": true, "web_search": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "docs_url": "https://ai.azure.com/catalog/models/gpt-5.4", "deprecation_date": "2027-09-02", "benchmarks": { "intelligence_index": 53.1, "coding_index": 71.1, "agentic_index": 44.2 }, "reasoning_config": { "mandatory": false }, "aliases": [ "azure/gpt-5.4", "ex/gpt-5.4", "gpt-5-4", "gpt-5.4", "gpt-5.4:free", "openai-responses/gpt-5.4", "openai.gpt-5.4", "openai.gpt-5.4-2026-03-05", "openai/gpt-5.4", "openai/gpt-5.4-2026-03-05", "pa/gpt-5.4", "pa/gpt-5.4-2026-03-05" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.4 —— 新一代模型，支持百万级上下文与多模态输入。", "zh-TW": "OpenAI GPT-5.4 —— 次世代模型，具備百萬級上下文與多模態輸入能力。", "ja-JP": "GPT-5.4 by OpenAI — 1M+コンテキストウィンドウとマルチモーダル入力を備えた次世代モデル。", "ru-RU": "GPT-5.4 от OpenAI — модель следующего поколения с контекстом более 1M и мультимодальным вводом." }, "price_history": [ { "date": "2026-07-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/gpt-5.4-272k", "model_name": "gpt-5.4-272k", "display_name": "GPT-5.4", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "22.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www", "cache_read": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GPT-5.4" } ] }, { "slug": "openai/gpt-5.4-image-2", "model_name": "gpt-5.4-image-2", "display_name": "GPT-5.4 Image 2", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "8" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "GPT-5.4 Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multimodal workflows across reasoning, coding, and image generation.", "capabilities": { "vision": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true }, "released_at": "2026-04-21", "max_input_tokens": 272000, "max_output_tokens": 128000, "modalities": { "input": [ "image", "text", "pdf" ], "output": [ "image", "text" ] }, "family": "gpt", "parameters": { "unsupported": [ "temperature" ] }, "model_type": "image_generation", "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-5.4-image-2" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "OpenAI: GPT-5.4 Image 2" } ] }, { "slug": "openai/gpt-5.4-mini-2026-03-17", "model_name": "gpt-5.4-mini-2026-03-17", "display_name": "gpt-5.4-mini-2026-03-17", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+computeprices+portkey+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.75" }, "completion": { "unit": "per_M_tokens", "price": "4.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gpt-5.4-mini", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.825" }, "completion": { "unit": "per_M_tokens", "price": "4.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0825" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-mini", "region": "ae", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.825" }, "completion": { "unit": "per_M_tokens", "price": "4.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0825" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-mini", "region": "au", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.825" }, "completion": { "unit": "per_M_tokens", "price": "4.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0825" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-mini", "region": "ca", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.825" }, "completion": { "unit": "per_M_tokens", "price": "4.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0825" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-mini", "region": "eu", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.825" }, "completion": { "unit": "per_M_tokens", "price": "4.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0825" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-mini", "region": "gb", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.825" }, "completion": { "unit": "per_M_tokens", "price": "4.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0825" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-mini", "region": "in", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.825" }, "completion": { "unit": "per_M_tokens", "price": "4.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0825" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-mini", "region": "jp", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.825" }, "completion": { "unit": "per_M_tokens", "price": "4.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0825" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-mini", "region": "kr", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.825" }, "completion": { "unit": "per_M_tokens", "price": "4.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0825" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-mini", "region": "sg", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.825" }, "completion": { "unit": "per_M_tokens", "price": "4.95" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0825" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-mini", "region": "us", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Strong small GPT for coding subagents, quick tool use, and high-volume work", "released_at": "2026-03-17", "knowledge_cutoff": "2025-08", "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt-mini", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "docs_url": "https://ai.azure.com/catalog/models/gpt-5.4-mini", "deprecation_date": "2027-09-21", "benchmarks": { "intelligence_index": 40.9, "coding_index": 56.1, "agentic_index": 31.5 }, "reasoning_config": { "mandatory": false }, "aliases": [ "azure/gpt-5.4-mini", "gpt-5-4-mini", "gpt-5.4-mini", "openai-responses/gpt-5.4-mini", "openai/gpt-5.4-mini", "openai/gpt-5.4-mini-2026-03-17" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.4 Mini —— 性能与成本的高效平衡。", "zh-TW": "OpenAI GPT-5.4 Mini —— 在成本與效能間取得高效平衡。", "ja-JP": "GPT-5.4 Mini by OpenAI — コストと性能のバランスが取れた効率的なモデル。", "ru-RU": "GPT-5.4 Mini от OpenAI — эффективная модель, сочетающая стоимость и производительность." }, "price_history": [ { "date": "2026-07-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-03", "kind": "limit", "old": "1050000", "new": "400000", "note": "max_input_tokens" } ] }, { "slug": "openai/gpt-5.4-nano-2026-03-17", "model_name": "gpt-5.4-nano-2026-03-17", "display_name": "gpt-5.4-nano-2026-03-17", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "1.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.02" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gpt-5.4-nano", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-nano", "region": "ae", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-nano", "region": "au", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-nano", "region": "ca", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-nano", "region": "eu", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-nano", "region": "gb", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-nano", "region": "in", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-nano", "region": "jp", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-nano", "region": "kr", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-nano", "region": "sg", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.375" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-nano", "region": "us", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation", "released_at": "2026-03-17", "knowledge_cutoff": "2025-08", "max_input_tokens": 400000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt-nano", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "docs_url": "https://ai.azure.com/catalog/models/gpt-5.4-nano", "deprecation_date": "2027-09-21", "benchmarks": { "intelligence_index": 39.7, "coding_index": 56.1, "agentic_index": 29.7 }, "reasoning_config": { "mandatory": false }, "aliases": [ "gpt-5-4-nano", "gpt-5.4-nano", "openai-responses/gpt-5.4-nano", "openai/gpt-5.4-nano", "openai/gpt-5.4-nano-2026-03-17" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.4 Nano —— 超轻量模型，适用于高吞吐任务。", "zh-TW": "OpenAI GPT-5.4 Nano —— 超輕量模型，適合高吞吐量任務。", "ja-JP": "GPT-5.4 Nano by OpenAI — 高スループットタスク向けの超軽量モデル。", "ru-RU": "GPT-5.4 Nano от OpenAI — сверхлёгкая модель для высокоскоростных задач." }, "price_history": [ { "date": "2026-07-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-03", "kind": "limit", "old": "1050000", "new": "400000", "note": "max_input_tokens" } ] }, { "slug": "openai/gpt-5.4-pro-2026-03-05", "model_name": "gpt-5.4-pro-2026-03-05", "display_name": "gpt-5.4-pro-2026-03-05", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "30" }, "completion": { "unit": "per_M_tokens", "price": "180" }, "cache_read": { "unit": "per_M_tokens", "price": "3" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "pydantic-prices", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "pydantic-prices introduced a ≥272000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "truefoundry introduced a ≥272000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "truefoundry introduced a ≥272000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-5.4-pro", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-pro", "region": "ae", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-pro", "region": "au", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-pro", "region": "ca", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-pro", "region": "eu", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-pro", "region": "gb", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-pro", "region": "in", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-pro", "region": "jp", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-pro", "region": "kr", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-pro", "region": "sg", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.4-pro", "region": "us", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "More exact GPT-5.4 tier for demanding professional reasoning and agent tasks", "released_at": "2026-03-05", "knowledge_cutoff": "2025-08", "max_input_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "gpt-pro", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "docs_url": "https://ai.azure.com/catalog/models/gpt-5.4-pro", "deprecation_date": "2027-09-07", "reasoning_config": { "mandatory": true }, "aliases": [ "gpt-5-4-pro", "gpt-5.4-pro", "openai-responses/gpt-5.4-pro", "openai/gpt-5.4-pro", "openai/gpt-5.4-pro-2026-03-05" ], "intro_i18n": { "zh-CN": "OpenAI 的 GPT-5.4 Pro —— 具备最大上下文与推理能力的高端模型。", "zh-TW": "OpenAI GPT-5.4 Pro —— 最強模型，提供最大上下文與推理能力。", "ja-JP": "GPT-5.4 Pro by OpenAI — 最大コンテキストと推論能力を備えた最も能力の高いモデル。", "ru-RU": "GPT-5.4 Pro от OpenAI — самая мощная модель с максимальным контекстом и рассуждениями." }, "price_history": [ { "date": "2026-07-03", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" } ] }, { "slug": "openai/gpt-5.4-pro-272k", "model_name": "gpt-5.4-pro-272k", "display_name": "GPT-5.4 Pro", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "60" }, "completion": { "unit": "per_M_tokens", "price": "270" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GPT-5.4 Pro" } ] }, { "slug": "openai/gpt-5.5-2026-04-23", "model_name": "gpt-5.5-2026-04-23", "display_name": "gpt-5.5-2026-04-23", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "truefoundry introduced a ≥272000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "truefoundry introduced a ≥272000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-5.5", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "cache_read": "1", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2.5", "completion": "2.5", "cache_read": "2.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5", "region": "ae", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2.5", "completion": "2.5", "cache_read": "2.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5", "region": "au", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2.5", "completion": "2.5", "cache_read": "2.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5", "region": "ca", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2.5", "completion": "2.5", "cache_read": "2.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5", "region": "eu", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2.5", "completion": "2.5", "cache_read": "2.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5", "region": "gb", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2.5", "completion": "2.5", "cache_read": "2.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5", "region": "in", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2.5", "completion": "2.5", "cache_read": "2.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5", "region": "jp", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2.5", "completion": "2.5", "cache_read": "2.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5", "region": "kr", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2.5", "completion": "2.5", "cache_read": "2.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5", "region": "sg", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2.5", "completion": "2.5", "cache_read": "2.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5", "region": "us", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2.5", "completion": "2.5", "cache_read": "2.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] } ], "intro": "Default frontier GPT for coding, computer use, research, and knowledge work", "released_at": "2026-04-23", "knowledge_cutoff": "2025-12", "max_input_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "docs_url": "https://ai.azure.com/catalog/models/gpt-5.5", "benchmarks": { "intelligence_index": 56.3, "coding_index": 74.9, "agentic_index": 47.4 }, "reasoning_config": { "mandatory": false }, "aliases": [ "gpt-5-5", "gpt-5.5", "gpt-5.5-2026-04-24", "gpt-5.5:free", "openai-responses/gpt-5.5", "openai.gpt-5.5", "openai.gpt-5.5-2026-04-23", "openai/gpt-5.5", "openai/gpt-5.5-2026-04-23" ], "intro_i18n": { "zh-CN": "GPT-5.5 是 OpenAI 的上一代前沿模型，适用于复杂的专业工作。", "zh-TW": "GPT-5.5 是 OpenAI 的上一代前沿模型，適用於複雜的專業工作。", "ja-JP": "GPT-5.5はOpenAIの前世代の最先端モデルで、複雑な専門的作業に対応します。", "ru-RU": "GPT-5.5 — предыдущая передовая модель OpenAI для сложной профессиональной работы." }, "price_history": [ { "date": "2026-07-03", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "openai/gpt-5.5-272k", "model_name": "gpt-5.5-272k", "display_name": "GPT-5.5", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "45" }, "cache_read": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www", "cache_read": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GPT-5.5" } ] }, { "slug": "openai/gpt-5.5-pro-2026-04-23", "model_name": "gpt-5.5-pro-2026-04-23", "display_name": "gpt-5.5-pro-2026-04-23", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "30" }, "completion": { "unit": "per_M_tokens", "price": "180" }, "cache_read": { "unit": "per_M_tokens", "price": "3" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+litellm+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gpt-5.5-pro", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." }, { "code": "unresolved_track_combination", "service_tier": "flex", "source": "portkey", "message": "flex pricing and context tiers are both published, but no exact combined flex + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5-pro", "region": "ae", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." }, { "code": "unresolved_track_combination", "service_tier": "flex", "source": "portkey", "message": "flex pricing and context tiers are both published, but no exact combined flex + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5-pro", "region": "au", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." }, { "code": "unresolved_track_combination", "service_tier": "flex", "source": "portkey", "message": "flex pricing and context tiers are both published, but no exact combined flex + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5-pro", "region": "ca", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." }, { "code": "unresolved_track_combination", "service_tier": "flex", "source": "portkey", "message": "flex pricing and context tiers are both published, but no exact combined flex + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5-pro", "region": "eu", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." }, { "code": "unresolved_track_combination", "service_tier": "flex", "source": "portkey", "message": "flex pricing and context tiers are both published, but no exact combined flex + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5-pro", "region": "gb", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." }, { "code": "unresolved_track_combination", "service_tier": "flex", "source": "portkey", "message": "flex pricing and context tiers are both published, but no exact combined flex + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5-pro", "region": "in", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." }, { "code": "unresolved_track_combination", "service_tier": "flex", "source": "portkey", "message": "flex pricing and context tiers are both published, but no exact combined flex + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5-pro", "region": "jp", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." }, { "code": "unresolved_track_combination", "service_tier": "flex", "source": "portkey", "message": "flex pricing and context tiers are both published, but no exact combined flex + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5-pro", "region": "kr", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." }, { "code": "unresolved_track_combination", "service_tier": "flex", "source": "portkey", "message": "flex pricing and context tiers are both published, but no exact combined flex + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5-pro", "region": "sg", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." }, { "code": "unresolved_track_combination", "service_tier": "flex", "source": "portkey", "message": "flex pricing and context tiers are both published, but no exact combined flex + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "33" }, "completion": { "unit": "per_M_tokens", "price": "198" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.5-pro", "region": "us", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "portkey", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." }, { "code": "unresolved_track_combination", "service_tier": "flex", "source": "portkey", "message": "flex pricing and context tiers are both published, but no exact combined flex + context prices were provided." } ] } ], "intro": "Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding", "released_at": "2026-04-23", "knowledge_cutoff": "2025-12", "max_input_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt-pro", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "reasoning_config": { "mandatory": true }, "aliases": [ "gpt-5-5-pro", "gpt-5.5-pro", "openai-responses/gpt-5.5-pro", "openai/gpt-5.5-pro", "openai/gpt-5.5-pro-2026-04-23" ], "intro_i18n": { "zh-CN": "GPT-5.5 Pro 通过更高计算投入实现更深入思考，并持续输出更可靠的答案。", "zh-TW": "GPT-5.5 Pro 使用更多算力進行更深入的思考，提供始終如一的高品質回答。", "ja-JP": "GPT-5.5 Proは、より多くの計算を使用して、より深く考え、一貫して優れた回答を提供します。", "ru-RU": "GPT-5.5 Pro использует больше вычислительных ресурсов для более глубоких рассуждений и consistently better answers." }, "price_history": [ { "date": "2026-07-03", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" } ] }, { "slug": "openai/gpt-5.5-pro-272k", "model_name": "gpt-5.5-pro-272k", "display_name": "GPT-5.5 Pro", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "60" }, "completion": { "unit": "per_M_tokens", "price": "270" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-30", "kind": "listed", "note": "GPT-5.5 Pro" } ] }, { "slug": "openai/gpt-5.6", "model_name": "gpt-5.6", "display_name": "GPT-5.6", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "cache_write": { "unit": "per_M_tokens", "price": "6.25" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "gpt-5.6-2026-07-09", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-2026-07-09", "region": "ae", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-2026-07-09", "region": "au", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-2026-07-09", "region": "ca", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-2026-07-09", "region": "eu", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-2026-07-09", "region": "gb", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-2026-07-09", "region": "in", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-2026-07-09", "region": "jp", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-2026-07-09", "region": "kr", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-2026-07-09", "region": "sg", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-2026-07-09", "region": "us", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] } ], "intro": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "released_at": "2026-07-09", "knowledge_cutoff": "2026-02", "max_input_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt-sol", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-5.6-2026-07-09", "openai/gpt-5.6" ], "price_history": [ { "date": "2026-07-09", "kind": "listed", "note": "GPT-5.6" } ] }, { "slug": "openai/gpt-5.6-luna", "model_name": "gpt-5.6-luna", "display_name": "GPT-5.6 Luna", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory+override", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "1.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.02" }, "cache_write": { "unit": "per_M_tokens", "price": "0.25" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Fast mode", "source": "override", "charge_sources": { "prompt": "override", "completion": "override", "cache_read": "override", "cache_write": "override" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "prompt from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6" }, "message": "completion from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.02" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "cache_read from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "0.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.25" }, "message": "cache_write from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "pydantic-prices", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "pydantic-prices introduced a ≥272000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "truefoundry introduced a ≥272000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-5.6-luna-2026-07-09", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Fast mode", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^(priority|fast)$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" }, "cache_write": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-luna-2026-07-09", "region": "ae", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" }, "cache_write": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-luna-2026-07-09", "region": "au", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" }, "cache_write": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-luna-2026-07-09", "region": "ca", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" }, "cache_write": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-luna-2026-07-09", "region": "eu", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" }, "cache_write": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-luna-2026-07-09", "region": "gb", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" }, "cache_write": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-luna-2026-07-09", "region": "in", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" }, "cache_write": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-luna-2026-07-09", "region": "jp", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" }, "cache_write": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-luna-2026-07-09", "region": "kr", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" }, "cache_write": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-luna-2026-07-09", "region": "sg", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "0.22" }, "completion": { "unit": "per_M_tokens", "price": "1.32" }, "cache_read": { "unit": "per_M_tokens", "price": "0.022" }, "cache_write": { "unit": "per_M_tokens", "price": "0.275" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-luna-2026-07-09", "region": "us", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] } ], "intro": "Cost-efficient GPT-5.6 model for fast, high-volume workloads", "released_at": "2026-07-09", "knowledge_cutoff": "2026-02", "max_input_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt-luna", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "status": "beta", "deprecation_date": "2028-01-11", "benchmarks": { "intelligence_index": 52.3, "coding_index": 71.4, "agentic_index": 46.9 }, "reasoning_config": { "mandatory": false }, "aliases": [ "gpt-5-6-luna", "gpt-5.6-luna-2026-07-09", "openai-responses/gpt-5.6-luna", "openai.gpt-5.6-luna", "openai/gpt-5.6-luna", "codex-auto-review", "openai/codex-auto-review" ], "intro_i18n": { "zh-CN": "GPT-5.6 Luna 专为成本敏感型、高负载工作量优化，是 GPT-5.6 系列中价格最低的模型。", "zh-TW": "GPT-5.6 Luna 專為成本敏感、高流量工作負載而優化，是 GPT-5.6 系列中價格最低的選擇。", "ja-JP": "GPT-5.6 Lunaは、GPT-5.6ファミリーの中で最も低価格で、コストに敏感な大量ワークロードに最適化されています。", "ru-RU": "GPT-5.6 Luna оптимизирован для экономичных, высокообъемных рабочих нагрузок с самой низкой ценой в семействе GPT-5.6." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.09", "new": "0.08" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "4.6", "new": "54.9" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.85", "new": "9.15" }, { "date": "2026-08-14", "kind": "price", "provider": "cloudflare-ai-gateway", "charge": "cache_read", "old": "0.1", "new": "0.02" }, { "date": "2026-08-14", "kind": "price", "provider": "cloudflare-ai-gateway", "charge": "completion", "old": "6", "new": "1.2" }, { "date": "2026-08-14", "kind": "price", "provider": "cloudflare-ai-gateway", "charge": "prompt", "old": "1", "new": "0.2" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "web_search", "old": "5", "new": "10" }, { "date": "2026-08-12", "kind": "price", "provider": "azure", "charge": "cache_read", "old": "0.1", "new": "0.02" }, { "date": "2026-08-12", "kind": "price", "provider": "azure", "charge": "cache_write", "old": "1.25", "new": "0.25" }, { "date": "2026-08-12", "kind": "price", "provider": "azure", "charge": "completion", "old": "6", "new": "1.2" }, { "date": "2026-08-12", "kind": "price", "provider": "azure", "charge": "prompt", "old": "1", "new": "0.2" }, { "date": "2026-08-12", "kind": "price", "provider": "jiekou", "charge": "completion", "old": "6", "new": "1.2" }, { "date": "2026-08-12", "kind": "price", "provider": "jiekou", "charge": "prompt", "old": "1", "new": "0.2" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_eu", "charge": "cache_read", "old": "0.11", "new": "0.022" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_eu", "charge": "completion", "old": "6.6", "new": "1.32" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_eu", "charge": "prompt", "old": "1.1", "new": "0.22" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_us", "charge": "cache_read", "old": "0.11", "new": "0.022" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_us", "charge": "completion", "old": "6.6", "new": "1.32" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_us", "charge": "prompt", "old": "1.1", "new": "0.22" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "cache_write", "old": "0.85", "new": "1.11" } ] }, { "slug": "openai/gpt-5.6-luna-272k", "model_name": "gpt-5.6-luna-272k", "display_name": "GPT-5.6 Luna", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "1.8" }, "cache_read": { "unit": "per_M_tokens", "price": "0.04" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www", "cache_read": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-30", "kind": "listed", "note": "GPT-5.6 Luna" } ] }, { "slug": "openai/gpt-5.6-sol", "model_name": "gpt-5.6-sol", "display_name": "GPT-5.6 Sol", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory+override", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "cache_write": { "unit": "per_M_tokens", "price": "6.25" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Fast mode", "source": "override", "charge_sources": { "prompt": "override", "completion": "override", "cache_read": "override", "cache_write": "override" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "pydantic-prices", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "pydantic-prices introduced a ≥272000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "truefoundry introduced a ≥272000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-5.6-sol-2026-07-09", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Fast mode", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^(priority|fast)$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-sol-2026-07-09", "region": "ae", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-sol-2026-07-09", "region": "au", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-sol-2026-07-09", "region": "ca", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-sol-2026-07-09", "region": "eu", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-sol-2026-07-09", "region": "gb", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-sol-2026-07-09", "region": "in", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-sol-2026-07-09", "region": "jp", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-sol-2026-07-09", "region": "kr", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-sol-2026-07-09", "region": "sg", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "5.5" }, "completion": { "unit": "per_M_tokens", "price": "33" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "cache_write": { "unit": "per_M_tokens", "price": "6.875" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-sol-2026-07-09", "region": "us", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] } ], "intro": "Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows", "released_at": "2026-07-09", "knowledge_cutoff": "2026-02", "max_input_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt-sol", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "status": "beta", "deprecation_date": "2028-01-11", "benchmarks": { "intelligence_index": 60.9, "coding_index": 77.4, "agentic_index": 57.8 }, "reasoning_config": { "mandatory": false }, "aliases": [ "gpt-5-6-sol", "gpt-5.6-sol-2026-07-09", "openai-responses/gpt-5.6-sol", "openai.gpt-5.6-sol", "openai/gpt-5.6-sol", "stealth/gpt-5.6-sol" ], "intro_i18n": { "zh-CN": "GPT-5.6 Sol 是 OpenAI 最新的旗舰模型，也是最强大的模型，是 GPT 系列中编程和代理工作的首选。", "zh-TW": "GPT-5.6 Sol 是 OpenAI 最新的旗艦模型，也是最強大的模型，在 GPT 系列中是編程和代理工作的首選。", "ja-JP": "GPT-5.6 SolはOpenAIの最新の主力モデルで、コーディングやエージェント作業においてGPTファミリーの中で最も優れた選択肢です。", "ru-RU": "GPT-5.6 Sol — новейшая флагманская и самая мощная модель OpenAI, лучший выбор в семействе GPT для кодирования и агентной работы." }, "price_history": [ { "date": "2026-08-06", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "openai/gpt-5.6-sol-272k", "model_name": "gpt-5.6-sol-272k", "display_name": "GPT-5.6 Sol", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "45" }, "cache_read": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www", "cache_read": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-30", "kind": "listed", "note": "GPT-5.6 Sol" } ] }, { "slug": "openai/gpt-5.6-terra", "model_name": "gpt-5.6-terra", "display_name": "GPT-5.6 Terra", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank+llm-prices-www+ai-model-directory+override", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "cache_write": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "cache_read": "portkey", "cache_write": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Fast mode", "source": "override", "charge_sources": { "prompt": "override", "completion": "override", "cache_read": "override", "cache_write": "override" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "web_search": "portkey", "file_search_call": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "prompt from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "12" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15" }, "message": "completion from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.25" }, "message": "cache_read from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pydantic-prices", "selected_source": "models-dev", "charge": "cache_write", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3.125" }, "message": "cache_write from pydantic-prices conflicts with models-dev; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "pydantic-prices", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "pydantic-prices introduced a ≥272000 tier outside the models-dev schedule; it was discarded." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 272000, "inclusive": true, "message": "truefoundry introduced a ≥272000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-5.6-terra-2026-07-09", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Fast mode", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^(priority|fast)$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.2" }, "completion": { "unit": "per_M_tokens", "price": "13.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.22" }, "cache_write": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-terra-2026-07-09", "region": "ae", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.2" }, "completion": { "unit": "per_M_tokens", "price": "13.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.22" }, "cache_write": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-terra-2026-07-09", "region": "au", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.2" }, "completion": { "unit": "per_M_tokens", "price": "13.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.22" }, "cache_write": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-terra-2026-07-09", "region": "ca", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.2" }, "completion": { "unit": "per_M_tokens", "price": "13.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.22" }, "cache_write": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-terra-2026-07-09", "region": "eu", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.2" }, "completion": { "unit": "per_M_tokens", "price": "13.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.22" }, "cache_write": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-terra-2026-07-09", "region": "gb", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.2" }, "completion": { "unit": "per_M_tokens", "price": "13.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.22" }, "cache_write": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-terra-2026-07-09", "region": "in", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.2" }, "completion": { "unit": "per_M_tokens", "price": "13.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.22" }, "cache_write": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-terra-2026-07-09", "region": "jp", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.2" }, "completion": { "unit": "per_M_tokens", "price": "13.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.22" }, "cache_write": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-terra-2026-07-09", "region": "kr", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.2" }, "completion": { "unit": "per_M_tokens", "price": "13.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.22" }, "cache_write": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-terra-2026-07-09", "region": "sg", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] }, { "provider": "openai", "official": true, "source": "portkey", "charges": { "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "2.2" }, "completion": { "unit": "per_M_tokens", "price": "13.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.22" }, "cache_write": { "unit": "per_M_tokens", "price": "2.75" } }, "provenance": { "base_charges": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" }, "tracks": [ { "label": "Batch AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex AND Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Context >272K", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey" } } ], "verification_status": "aggregator_only" }, "provider_model_id": "gpt-5.6-terra-2026-07-09", "region": "us", "tracks": [ { "label": "Batch AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "2", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex AND Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1", "completion": "0.75", "cache_read": "1", "cache_write": "1" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" }, { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5", "cache_write": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Context >272K", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "2", "completion": "1.5", "cache_read": "2", "cache_write": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "priority", "source": "portkey", "message": "priority pricing and context tiers are both published, but no exact combined priority + context prices were provided." } ] } ], "intro": "Balanced GPT-5.6 model for capable, cost-efficient everyday work", "released_at": "2026-07-09", "knowledge_cutoff": "2026-02", "max_input_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt-terra", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "status": "beta", "deprecation_date": "2028-01-11", "benchmarks": { "intelligence_index": 56.6, "coding_index": 76.7, "agentic_index": 50.2 }, "reasoning_config": { "mandatory": false }, "aliases": [ "gpt-5-6-terra", "gpt-5.6-terra-2026-07-09", "openai-responses/gpt-5.6-terra", "openai.gpt-5.6-terra", "openai/gpt-5.6-terra" ], "intro_i18n": { "zh-CN": "GPT-5.6 Terra 在智能与成本之间实现平衡，适用于日常专业工作，其性能可与 GPT-5.5 竞争，但价格约为其一半。", "zh-TW": "GPT-5.6 Terra 在智慧與成本之間取得平衡，適用於日常專業工作，其性能可與 GPT-5.5 媲美，但價格約為其一半。", "ja-JP": "GPT-5.6 Terraは、日常的なプロフェッショナル作業のために知能とコストのバランスを取り、GPT-5.5と競合しながら約半分の価格を実現しています。", "ru-RU": "GPT-5.6 Terra сочетает интеллект и экономичность для повседневной профессиональной работы, конкурируя с GPT-5.5 примерно за половину цены." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "11.5", "new": "54.9" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "2.1", "new": "9.15" }, { "date": "2026-08-14", "kind": "price", "provider": "cloudflare-ai-gateway", "charge": "cache_read", "old": "0.25", "new": "0.2" }, { "date": "2026-08-14", "kind": "price", "provider": "cloudflare-ai-gateway", "charge": "completion", "old": "15", "new": "12" }, { "date": "2026-08-14", "kind": "price", "provider": "cloudflare-ai-gateway", "charge": "prompt", "old": "2.5", "new": "2" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "web_search", "old": "5", "new": "10" }, { "date": "2026-08-12", "kind": "price", "provider": "azure", "charge": "cache_read", "old": "0.25", "new": "0.2" }, { "date": "2026-08-12", "kind": "price", "provider": "azure", "charge": "cache_write", "old": "3.125", "new": "2.5" }, { "date": "2026-08-12", "kind": "price", "provider": "azure", "charge": "completion", "old": "15", "new": "12" }, { "date": "2026-08-12", "kind": "price", "provider": "azure", "charge": "prompt", "old": "2.5", "new": "2" }, { "date": "2026-08-12", "kind": "price", "provider": "jiekou", "charge": "completion", "old": "15", "new": "12" }, { "date": "2026-08-12", "kind": "price", "provider": "jiekou", "charge": "prompt", "old": "2.5", "new": "2" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_eu", "charge": "cache_read", "old": "0.275", "new": "0.22" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_eu", "charge": "completion", "old": "16.5", "new": "13.2" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_eu", "charge": "prompt", "old": "2.75", "new": "2.2" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_us", "charge": "cache_read", "old": "0.275", "new": "0.22" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_us", "charge": "completion", "old": "16.5", "new": "13.2" }, { "date": "2026-08-10", "kind": "price", "provider": "azure@datazone_us", "charge": "prompt", "old": "2.75", "new": "2.2" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.35", "new": "0.21" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "cache_write", "old": "2.8", "new": "2.64" } ] }, { "slug": "openai/gpt-5.6-terra-272k", "model_name": "gpt-5.6-terra-272k", "display_name": "GPT-5.6 Terra", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "18" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www", "cache_read": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-30", "kind": "listed", "note": "GPT-5.6 Terra" } ] }, { "slug": "openai/gpt-audio", "model_name": "gpt-audio", "display_name": "gpt-audio", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "audio_input": { "unit": "per_M_tokens", "price": "32" }, "audio_output": { "unit": "per_M_tokens", "price": "64" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "audio_output": "litellm", "cache_write": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "32" }, "discarded_charge": { "unit": "per_M_tokens", "price": "40" }, "message": "audio_input from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "audio_output", "selected_charge": { "unit": "per_M_tokens", "price": "64" }, "discarded_charge": { "unit": "per_M_tokens", "price": "80" }, "message": "audio_output from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "32" }, "message": "prompt from ai-model-directory conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "64" }, "message": "completion from ai-model-directory conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-audio-2025-08-28" } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "omni", "deprecation_date": "2027-01-20", "capabilities": { "function_calling": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "intro": "The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural-sounding voices and maintains better voice consistency.", "deprecated": true, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ] }, "released_at": "2025-08-28", "knowledge_cutoff": "2023-10", "family": "gpt", "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "aliases": [ "gpt-audio-2025-08-28", "openai/gpt-audio" ], "intro_i18n": { "zh-CN": "GPT Audio 是支持音频输入/输出的通用对话模型，可通过 Chat Completions API 使用。", "zh-TW": "GPT Audio 是一款通用聊天模型，支援音訊輸入/輸出，並整合於 Chat Completions API 中。", "ja-JP": "GPT Audio は、音声の入出力に対応した汎用チャットモデルで、Chat Completions API に対応しています。", "ru-RU": "GPT Audio — универсальная модель общения с поддержкой ввода и вывода аудио, доступная через API завершения чата." }, "price_history": [ { "date": "2026-08-01", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "openai/gpt-audio-1.5", "model_name": "gpt-audio-1.5", "display_name": "gpt-audio-1.5", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+portkey+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.5" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "audio_input": { "unit": "per_M_tokens", "price": "32" }, "audio_output": { "unit": "per_M_tokens", "price": "64" }, "cache_read": { "unit": "per_M_tokens", "price": "0" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "audio_output": "litellm", "cache_read": "portkey", "cache_write": "portkey" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "32" }, "message": "prompt from ai-model-directory conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "64" }, "message": "completion from ai-model-directory conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "omni", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ] }, "released_at": "2026-02-20", "knowledge_cutoff": "2024-09", "deprecation_date": "2027-08-24", "aliases": [ "gpt-audio-1.5-2026-02-23" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-29", "kind": "capability", "note": "prompt_caching: true→false" }, { "date": "2026-07-15", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-15", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "openai/gpt-audio-mini", "model_name": "gpt-audio-mini", "display_name": "gpt-audio-mini", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.4" }, "audio_input": { "unit": "per_M_tokens", "price": "10" }, "audio_output": { "unit": "per_M_tokens", "price": "20" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.06" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "audio_input": "litellm", "audio_output": "litellm", "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "cache_write": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "audio_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_output", "selected_charge": { "unit": "per_M_tokens", "price": "20" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "audio_output from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-audio-mini-2025-10-06" } ], "max_input_tokens": 128000, "max_output_tokens": 16384, "model_type": "omni", "deprecation_date": "2027-01-20", "capabilities": { "function_calling": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "deprecated": true, "intro": "A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency.", "modalities": { "input": [ "text", "audio" ], "output": [ "text", "audio" ] }, "released_at": "2025-10-03", "knowledge_cutoff": "2023-10", "family": "o-mini", "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "aliases": [ "gpt-audio-mini-2025-10-06", "gpt-audio-mini-2025-12-15", "openai/gpt-audio-mini" ], "price_history": [ { "date": "2026-07-03", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" } ] }, { "slug": "openai/gpt-chat-latest", "model_name": "gpt-chat-latest", "display_name": "GPT Chat Latest", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT.", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true }, "released_at": "2026-05-03", "max_input_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "gpt", "parameters": { "unsupported": [ "temperature" ] }, "knowledge_cutoff": "2025-12", "status": "beta", "model_type": "vision_understanding", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-chat-latest-2026-05-05", "gpt-chat-latest-2026-05-28", "openai/gpt-chat-latest" ], "price_history": [ { "date": "2026-08-03", "kind": "limit", "old": "400000", "new": "1050000", "note": "max_input_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "128000", "new": "400000", "note": "max_input_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "16384", "new": "128000", "note": "max_output_tokens" }, { "date": "2026-07-13", "kind": "limit", "old": "400000", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-07-13", "kind": "limit", "old": "128000", "new": "16384", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "OpenAI: GPT Chat Latest" } ] }, { "slug": "openai/gpt-image-1", "model_name": "gpt-image-1", "display_name": "gpt-image-1", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "cache_read": { "unit": "per_M_tokens", "price": "1.25" }, "image_input": { "unit": "per_image", "price": "0.167" }, "completion": { "unit": "per_M_tokens", "price": "12.5" }, "image_output": { "unit": "per_image", "price": "0.167" }, "image_output_1024px": { "unit": "per_image", "price": "0.167" }, "image_output_1024x1536": { "unit": "per_image", "price": "0.25" }, "image_output_1536x1024": { "unit": "per_image", "price": "0.25" }, "image_output_hd": { "unit": "per_image", "price": "0.167" }, "image_output_1024px_hd": { "unit": "per_image", "price": "0.167" }, "image_output_1024x1536_hd": { "unit": "per_image", "price": "0.25" }, "image_output_1536x1024_hd": { "unit": "per_image", "price": "0.25" }, "image_output_medium": { "unit": "per_image", "price": "0.042" }, "image_output_1024px_medium": { "unit": "per_image", "price": "0.042" }, "image_output_1024x1536_medium": { "unit": "per_image", "price": "0.063" }, "image_output_1536x1024_medium": { "unit": "per_image", "price": "0.063" }, "image_output_low": { "unit": "per_image", "price": "0.011" }, "image_output_1024px_low": { "unit": "per_image", "price": "0.011" }, "image_output_1024x1536_low": { "unit": "per_image", "price": "0.016" }, "image_output_1536x1024_low": { "unit": "per_image", "price": "0.016" }, "image_output_tokens": { "unit": "per_M_tokens", "price": "40" }, "image_cache_read": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "cache_read": "litellm", "image_input": "litellm", "completion": "helicone-registry", "image_output": "portkey", "image_output_1024px": "portkey", "image_output_1024x1536": "portkey", "image_output_1536x1024": "portkey", "image_output_hd": "portkey", "image_output_1024px_hd": "portkey", "image_output_1024x1536_hd": "portkey", "image_output_1536x1024_hd": "portkey", "image_output_medium": "portkey", "image_output_1024px_medium": "portkey", "image_output_1024x1536_medium": "portkey", "image_output_1536x1024_medium": "portkey", "image_output_low": "portkey", "image_output_1024px_low": "portkey", "image_output_1024x1536_low": "portkey", "image_output_1536x1024_low": "portkey", "image_output_tokens": "portkey", "image_cache_read": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.167" }, "discarded_charge": { "unit": "per_image", "price": "0.25" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.167" }, "discarded_charge": { "unit": "per_image", "price": "0.25" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.167" }, "discarded_charge": { "unit": "per_image", "price": "0.011" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.167" }, "discarded_charge": { "unit": "per_image", "price": "0.016" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.167" }, "discarded_charge": { "unit": "per_image", "price": "0.016" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.167" }, "discarded_charge": { "unit": "per_image", "price": "0.042" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.167" }, "discarded_charge": { "unit": "per_image", "price": "0.063" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.167" }, "discarded_charge": { "unit": "per_image", "price": "0.063" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6.25" }, "message": "prompt from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.167" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10" }, "message": "image_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.167" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10" }, "message": "image_input from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "portkey", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.167" }, "discarded_charge": { "unit": "per_M_tokens", "price": "40" }, "message": "image_output from lobehub-modelbank conflicts with portkey; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10" }, "message": "prompt from llm-prices-www conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "helicone-registry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "12.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "40" }, "message": "completion from llm-prices-www conflicts with helicone-registry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10" }, "message": "prompt from ai-model-directory conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "helicone-registry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "12.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "40" }, "message": "completion from ai-model-directory conflicts with helicone-registry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "cache_read from ai-model-directory conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "OpenAI image model for production generation, edits, and brand-safe visual workflows", "released_at": "2025-04-24", "max_input_tokens": 0, "max_output_tokens": 0, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "family": "gpt-image", "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "image_generation", "deprecation_date": "2026-10-23", "knowledge_cutoff": "2025-04", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-image-1-2025-04-15", "openai/gpt-image-1" ], "intro_i18n": { "zh-CN": "ChatGPT 原生多模态图像生成模型。", "zh-TW": "ChatGPT 原生多模態圖像生成模型。", "ja-JP": "ChatGPT にネイティブ対応したマルチモーダル画像生成モデルです。", "ru-RU": "Нативная мультимодальная модель генерации изображений ChatGPT." }, "price_history": [ { "date": "2026-08-07", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-image-1-mini", "model_name": "gpt-image-1-mini", "display_name": "gpt-image-1-mini", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "image_input": { "unit": "per_image", "price": "0.005" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "image_cache_read": { "unit": "per_M_tokens", "price": "0.25" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" }, "image_output": { "unit": "per_M_tokens", "price": "8" } }, "provenance": { "base_charges": { "prompt": "litellm", "cache_read": "litellm", "image_input": "litellm", "completion": "portkey", "image_cache_read": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb", "image_output": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+portkey+llmdb+lobehub-modelbank", "charge_sources": { "prompt": "litellm", "cache_read": "litellm", "image_input": "litellm", "completion": "portkey", "image_cache_read": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb", "image_output": "lobehub-modelbank" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.005" }, "discarded_charge": { "unit": "per_image", "price": "0.006" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.005" }, "discarded_charge": { "unit": "per_image", "price": "0.006" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.005" }, "discarded_charge": { "unit": "per_image", "price": "0.011" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.005" }, "discarded_charge": { "unit": "per_image", "price": "0.015" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.005" }, "discarded_charge": { "unit": "per_image", "price": "0.015" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.005" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "image_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.005" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "image_input from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "portkey", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8" }, "message": "completion from llm-prices-www conflicts with portkey; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "prompt from ai-model-directory conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "portkey", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8" }, "message": "completion from ai-model-directory conflicts with portkey; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.25" }, "message": "cache_read from ai-model-directory conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2025-09-26", "max_input_tokens": 0, "max_output_tokens": 0, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "family": "gpt-image", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "image_generation", "deprecation_date": "2026-12-01", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-image-1-mini-2025-10-06", "openai/gpt-image-1-mini" ], "intro_i18n": { "zh-CN": "GPT Image 1 的低成本变体，原生支持文本与图像输入，以及图像输出。", "zh-TW": "GPT Image 1 的低成本變體，原生支援文字與圖片輸入，並輸出圖片。", "ja-JP": "低コストな GPT Image 1 バリアントで、テキストと画像の入力および画像出力に対応しています。", "ru-RU": "Бюджетный вариант GPT Image 1 с нативной поддержкой ввода текста и изображений и генерацией изображений." }, "price_history": [ { "date": "2026-08-07", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-image-1.5-2025-12-16", "model_name": "gpt-image-1.5-2025-12-16", "display_name": "gpt-image-1.5-2025-12-16", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "1.25" }, "image_input": { "unit": "per_image", "price": "0.009" }, "image_output": { "unit": "per_image", "price": "0.009" }, "image_output_1024px": { "unit": "per_image", "price": "0.133" }, "image_output_1024x1536": { "unit": "per_image", "price": "0.2" }, "image_output_1536x1024": { "unit": "per_image", "price": "0.2" }, "image_output_hd": { "unit": "per_image", "price": "0.133" }, "image_output_1024px_hd": { "unit": "per_image", "price": "0.133" }, "image_output_1024x1536_hd": { "unit": "per_image", "price": "0.2" }, "image_output_1536x1024_hd": { "unit": "per_image", "price": "0.2" }, "image_output_medium": { "unit": "per_image", "price": "0.034" }, "image_output_1024px_medium": { "unit": "per_image", "price": "0.034" }, "image_output_1024x1536_medium": { "unit": "per_image", "price": "0.05" }, "image_output_1536x1024_medium": { "unit": "per_image", "price": "0.05" }, "image_output_low": { "unit": "per_image", "price": "0.009" }, "image_output_1024px_low": { "unit": "per_image", "price": "0.009" }, "image_output_1024x1536_low": { "unit": "per_image", "price": "0.013" }, "image_output_1536x1024_low": { "unit": "per_image", "price": "0.013" }, "image_output_tokens": { "unit": "per_M_tokens", "price": "32" }, "image_cache_read": { "unit": "per_M_tokens", "price": "2" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "image_input": "litellm", "image_output": "truefoundry", "image_output_1024px": "portkey", "image_output_1024x1536": "portkey", "image_output_1536x1024": "portkey", "image_output_hd": "portkey", "image_output_1024px_hd": "portkey", "image_output_1024x1536_hd": "portkey", "image_output_1536x1024_hd": "portkey", "image_output_medium": "portkey", "image_output_1024px_medium": "portkey", "image_output_1024x1536_medium": "portkey", "image_output_1536x1024_medium": "portkey", "image_output_low": "portkey", "image_output_1024px_low": "portkey", "image_output_1024x1536_low": "portkey", "image_output_1536x1024_low": "portkey", "image_output_tokens": "portkey", "image_cache_read": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+truefoundry+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "image_input": "litellm", "image_output": "truefoundry", "image_output_1024px": "portkey", "image_output_1024x1536": "portkey", "image_output_1536x1024": "portkey", "image_output_hd": "portkey", "image_output_1024px_hd": "portkey", "image_output_1024x1536_hd": "portkey", "image_output_1536x1024_hd": "portkey", "image_output_medium": "portkey", "image_output_1024px_medium": "portkey", "image_output_1024x1536_medium": "portkey", "image_output_1536x1024_medium": "portkey", "image_output_low": "portkey", "image_output_1024px_low": "portkey", "image_output_1024x1536_low": "portkey", "image_output_1536x1024_low": "portkey", "image_output_tokens": "portkey", "image_cache_read": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.034" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.05" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.05" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.133" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.2" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.2" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.034" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.05" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.05" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.133" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.2" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.2" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.013" }, "message": "image_input from litellm conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.133" }, "message": "image_output from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8" }, "message": "image_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_image", "price": "0.133" }, "message": "image_output from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8" }, "message": "image_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "litellm", "charge": "image_input", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8" }, "message": "image_input from lobehub-modelbank conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "truefoundry", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.009" }, "discarded_charge": { "unit": "per_M_tokens", "price": "32" }, "message": "image_output from lobehub-modelbank conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8" }, "message": "prompt from ai-model-directory conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "10" }, "discarded_charge": { "unit": "per_M_tokens", "price": "32" }, "message": "completion from ai-model-directory conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "cache_read from ai-model-directory conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-image-1.5", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2025-11-25", "max_input_tokens": 0, "max_output_tokens": 0, "modalities": { "input": [ "text", "image" ], "output": [ "text", "image" ] }, "family": "gpt-image", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "image_generation", "deprecation_date": "2026-12-01", "deprecated": true, "knowledge_cutoff": "2025-12", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-image-1.5", "openai/gpt-image-1.5" ], "intro_i18n": { "zh-CN": "GPT Image 1 的增强版本，生成速度提升 4 倍，编辑更精准，文本渲染效果更佳。", "zh-TW": "GPT Image 1 的增強版，生成速度提升 4 倍，編輯更精準，文字渲染效果更佳。", "ja-JP": "GPT Image 1 の強化版で、4倍の生成速度、より正確な編集、テキスト描画の改善を実現しています。", "ru-RU": "Улучшенная модель GPT Image 1 с генерацией в 4 раза быстрее, более точным редактированием и улучшенной визуализацией текста." }, "price_history": [ { "date": "2026-08-07", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-03", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-03", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-03", "kind": "limit", "new": "0", "note": "max_input_tokens" }, { "date": "2026-07-03", "kind": "limit", "new": "0", "note": "max_output_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/gpt-image-2", "model_name": "gpt-image-2", "display_name": "gpt-image-2", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "cache_read": { "unit": "per_M_tokens", "price": "1.25" }, "image_output": { "unit": "per_image", "price": "0.211" }, "image_output_1024px": { "unit": "per_image", "price": "0.211" }, "image_output_1024x1536": { "unit": "per_image", "price": "0.165" }, "image_output_1536x1024": { "unit": "per_image", "price": "0.165" }, "image_output_hd": { "unit": "per_image", "price": "0.211" }, "image_output_1024px_hd": { "unit": "per_image", "price": "0.211" }, "image_output_1024x1536_hd": { "unit": "per_image", "price": "0.165" }, "image_output_1536x1024_hd": { "unit": "per_image", "price": "0.165" }, "image_output_medium": { "unit": "per_image", "price": "0.053" }, "image_output_1024px_medium": { "unit": "per_image", "price": "0.053" }, "image_output_1024x1536_medium": { "unit": "per_image", "price": "0.041" }, "image_output_1536x1024_medium": { "unit": "per_image", "price": "0.041" }, "image_output_low": { "unit": "per_image", "price": "0.006" }, "image_output_1024px_low": { "unit": "per_image", "price": "0.006" }, "image_output_1024x1536_low": { "unit": "per_image", "price": "0.005" }, "image_output_1536x1024_low": { "unit": "per_image", "price": "0.005" }, "image_input": { "unit": "per_M_tokens", "price": "8" }, "image_output_tokens": { "unit": "per_M_tokens", "price": "30" }, "image_cache_read": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "image_output": "portkey", "image_output_1024px": "portkey", "image_output_1024x1536": "portkey", "image_output_1536x1024": "portkey", "image_output_hd": "portkey", "image_output_1024px_hd": "portkey", "image_output_1024x1536_hd": "portkey", "image_output_1536x1024_hd": "portkey", "image_output_medium": "portkey", "image_output_1024px_medium": "portkey", "image_output_1024x1536_medium": "portkey", "image_output_1536x1024_medium": "portkey", "image_output_low": "portkey", "image_output_1024px_low": "portkey", "image_output_1024x1536_low": "portkey", "image_output_1536x1024_low": "portkey", "image_input": "portkey", "image_output_tokens": "portkey", "image_cache_read": "portkey" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+portkey", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "image_output": "portkey", "image_output_1024px": "portkey", "image_output_1024x1536": "portkey", "image_output_1536x1024": "portkey", "image_output_hd": "portkey", "image_output_1024px_hd": "portkey", "image_output_1024x1536_hd": "portkey", "image_output_1536x1024_hd": "portkey", "image_output_medium": "portkey", "image_output_1024px_medium": "portkey", "image_output_1024x1536_medium": "portkey", "image_output_1536x1024_medium": "portkey", "image_output_low": "portkey", "image_output_1024px_low": "portkey", "image_output_1024x1536_low": "portkey", "image_output_1536x1024_low": "portkey", "image_input": "portkey", "image_output_tokens": "portkey", "image_cache_read": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "litellm", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10" }, "message": "completion from litellm conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "portkey", "charge": "image_output", "selected_charge": { "unit": "per_image", "price": "0.211" }, "discarded_charge": { "unit": "per_M_tokens", "price": "30" }, "message": "image_output from lobehub-modelbank conflicts with portkey; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-image-2-2026-04-21", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2026-04-21", "max_input_tokens": 0, "max_output_tokens": 0, "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "family": "gpt-image", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true }, "model_type": "image_generation", "deprecation_date": "2027-10-21", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-image-2-2026-04-21", "openai/gpt-image-2" ], "intro_i18n": { "zh-CN": "OpenAI 的下一代多模态图像模型，具备原生推理能力，支持最高 4K 分辨率、近乎完美的文字渲染及高保真多语言能力。", "zh-TW": "OpenAI 新一代多模態影像模型，具備原生推理能力、最高 4K 解析度、幾乎完美的文字呈現與高保真多語支援。", "ja-JP": "OpenAIの次世代マルチモーダル画像モデルで、ネイティブ推論、最大4K解像度、ほぼ完璧なテキストレンダリング、高忠実度の多言語サポートを提供します。", "ru-RU": "Следующее поколение мультимодальной модели генерации изображений от OpenAI с нативными возможностями рассуждения, разрешением до 4K, почти идеальным рендерингом текста и высококачественной многоязычной поддержкой." }, "price_history": [ { "date": "2026-07-09", "kind": "capability", "note": "audio_input: true→false" }, { "date": "2026-07-09", "kind": "capability", "note": "video_input: true→false" }, { "date": "2026-07-04", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-04", "kind": "capability", "note": "video_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" } ] }, { "slug": "openai/gpt-image-2-image", "model_name": "gpt-image-2-image", "display_name": "gpt-image-2 (image gen) image tokens", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "8" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "cache_read": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www", "cache_read": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gpt-image-2 (image gen) image tokens" } ] }, { "slug": "openai/gpt-image-2-text", "model_name": "gpt-image-2-text", "display_name": "gpt-image-2 (image gen) text tokens", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "cache_read": { "unit": "per_M_tokens", "price": "1.25" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www", "cache_read": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "image_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gpt-image-2 (image gen) text tokens" } ] }, { "slug": "openai/gpt-live-transcribe", "model_name": "gpt-live-transcribe", "display_name": "gpt-live-transcribe", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0002833333333333333" } }, "provenance": { "base_charges": { "audio_input": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://platform.openai.com/docs/models/gpt-live-transcribe", "model_type": "realtime_speech_recognition", "capabilities": { "audio_input": true }, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-29", "kind": "listed", "note": "gpt-live-transcribe" } ] }, { "slug": "openai/gpt-oss-120b", "model_name": "gpt-oss-120b", "display_name": "gpt-oss-120b", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.039" }, "completion": { "unit": "per_M_tokens", "price": "0.18" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases.", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "parallel_function_calling": true, "web_search": true, "stream": true }, "released_at": "2025-08-06", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt-oss", "knowledge_cutoff": "2025-08", "reasoning_config": { "mandatory": true, "budget_min": 128 }, "model_type": "deep_thinking", "docs_url": "https://openrouter.ai/openai/gpt-oss-120b", "deprecated": true, "benchmarks": { "intelligence_index": 24.1, "coding_index": 30.4, "agentic_index": 13.4 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_logprobs", "top_p" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "@cf/openai/gpt-oss-120b", "TEE/gpt-oss-120b", "accounts/fireworks/models/gpt-oss-120b", "anthropic/pioneer/openai/gpt-oss-120b", "cerebras/gpt-oss-120b", "deepinfra/openai/gpt-oss-120b", "fireworks/gpt-oss-120b", "groq/gpt-oss-120b", "groq/openai/gpt-oss-120b", "hf:openai/gpt-oss-120b", "lightning-ai/gpt-oss-120b", "nebius/openai/gpt-oss-120b", "openai.gpt-oss-120b", "openai/gpt-oss-120b", "openai/gpt-oss-120b:exacto", "openai/gpt-oss-120b:free", "workers-ai/@cf/openai/gpt-oss-120b" ], "intro_i18n": { "zh-CN": "需申请访问。GPT-OSS-120B 是 OpenAI 开源的大型语言模型，具备强大的文本生成能力。", "zh-TW": "需申請使用。GPT-OSS-120B 是 OpenAI 推出的開源大型語言模型，具備強大的文字生成能力。", "ja-JP": "申請が必要です。GPT-OSS-120B は、OpenAI によるオープンソースの大規模言語モデルで、強力なテキスト生成能力を備えています。", "ru-RU": "Требуется заявка на доступ. GPT-OSS-120B — это крупная open-source языковая модель от OpenAI с мощными возможностями генерации текста." }, "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "128000", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "4096", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "131072", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "32768", "new": "4096", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "131072", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "32768", "new": "4096", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "128000", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "4096", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "131072", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "32768", "new": "4096", "note": "max_output_tokens" } ] }, { "slug": "openai/GPT-OSS-20B", "model_name": "GPT-OSS-20B", "display_name": "gpt-oss-20b", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.029" }, "completion": { "unit": "per_M_tokens", "price": "0.14" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" }, "provider_model_id": "gpt-oss-20b" } ], "intro": "gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass.", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "parallel_function_calling": true, "web_search": true, "stream": true }, "released_at": "2025-08-06", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt-oss", "knowledge_cutoff": "2024-10", "model_type": "deep_thinking", "docs_url": "https://openrouter.ai/openai/gpt-oss-20b", "deprecated": true, "benchmarks": { "intelligence_index": 15.2, "coding_index": 20.7, "agentic_index": 3.1 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "@cf/openai/gpt-oss-20b", "TEE/gpt-oss-20b", "accounts/fireworks/models/gpt-oss-20b", "anthropic/pioneer/openai/gpt-oss-20b", "deepinfra/openai/gpt-oss-20b", "fireworks/gpt-oss-20b", "gpt-oss-20b", "groq/gpt-oss-20b", "groq/openai/gpt-oss-20b", "lightning-ai/gpt-oss-20b", "openai.gpt-oss-20b", "openai/chat-completion/models/gpt-oss-20b", "openai/gpt-oss-20b", "openai/gpt-oss-20b:free", "workers-ai/@cf/openai/gpt-oss-20b" ], "intro_i18n": { "zh-CN": "需申请访问。GPT-OSS-20B 是 OpenAI 开源的中型语言模型，具备高效的文本生成能力。", "zh-TW": "需申請使用。GPT-OSS-20B 是 OpenAI 推出的中型開源語言模型，具備高效的文字生成能力。", "ja-JP": "申請が必要です。GPT-OSS-20B は、OpenAI による中規模のオープンソース言語モデルで、効率的なテキスト生成が可能です。", "ru-RU": "Требуется заявка на доступ. GPT-OSS-20B — это средняя open-source языковая модель от OpenAI с эффективной генерацией текста." }, "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "128000", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "4096", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "131072", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "32768", "new": "4096", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "131072", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "32768", "new": "4096", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "128000", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "4096", "new": "32768", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "131072", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "32768", "new": "4096", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "128000", "new": "131072", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "4096", "new": "32768", "note": "max_output_tokens" } ] }, { "slug": "openai/gpt-oss-safeguard-20b", "model_name": "gpt-oss-safeguard-20b", "display_name": "GPT OSS Safeguard 20B", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.075" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.037" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks.", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "web_search": true, "stream": true }, "released_at": "2026-02-23", "max_input_tokens": 128000, "max_output_tokens": 16384, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "gpt-oss", "knowledge_cutoff": "2024-10", "status": "beta", "model_type": "safety_detection", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "accounts/fireworks/models/gpt-oss-safeguard-20b", "groq/openai/gpt-oss-safeguard-20b", "openai.gpt-oss-safeguard-20b", "openai/gpt-oss-safeguard-20b" ], "price_history": [ { "date": "2026-07-15", "kind": "limit", "old": "131072", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "65536", "new": "16384", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "gpt-oss-safeguard-20b" } ] }, { "slug": "openai/gpt-realtime", "model_name": "gpt-realtime", "display_name": "GPT Realtime", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "16" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "audio_input": { "unit": "per_M_tokens", "price": "32" }, "audio_output": { "unit": "per_M_tokens", "price": "64" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "0.5" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "64" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" }, "image_input": { "unit": "per_M_tokens", "price": "5" }, "image_cache_read": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "audio_input": "pydantic-prices", "audio_output": "pydantic-prices", "cache_read_input_audio": "truefoundry", "cache_write": "portkey", "audio_cache_read": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb", "image_input": "lobehub-modelbank", "image_cache_read": "lobehub-modelbank" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "16" }, "message": "cache_read from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "16" }, "message": "cache_read from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "portkey", "charge": "audio_cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "64" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.4" }, "message": "audio_cache_read from lobehub-modelbank conflicts with portkey; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "pydantic-prices", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from ai-model-directory conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "16" }, "discarded_charge": { "unit": "per_M_tokens", "price": "64" }, "message": "completion from ai-model-directory conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "pydantic-prices", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "cache_read from ai-model-directory conflicts with pydantic-prices; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-realtime-2025-08-28" } ], "capabilities": { "function_calling": true, "parallel_function_calling": true, "prompt_caching": true, "vision": true, "audio_input": true, "audio_output": true, "pdf_input": true, "structured_output": true }, "max_input_tokens": 32000, "max_output_tokens": 4096, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ] }, "model_type": "realtime_omni", "released_at": "2025-08-28", "knowledge_cutoff": "2023-10", "family": "GPT Realtime", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-realtime-2025-08-28", "openai/gpt-realtime" ], "intro_i18n": { "zh-CN": "通用实时模型，支持实时文本与音频输入/输出，并支持图像输入。", "zh-TW": "通用即時模型，支援即時文字與音訊輸入/輸出，並支援圖片輸入。", "ja-JP": "リアルタイムのテキスト・音声入出力、画像入力に対応した汎用リアルタイムモデルです。", "ru-RU": "Универсальная модель реального времени с поддержкой ввода/вывода текста и аудио, а также ввода изображений." }, "price_history": [ { "date": "2026-07-28", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-19", "kind": "price", "provider": "openai", "charge": "image_input", "old": "0.000005", "new": "5" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "openai/gpt-realtime-1.5-2026-02-23", "model_name": "gpt-realtime-1.5-2026-02-23", "display_name": "GPT-Realtime-1.5", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "truefoundry+portkey+ai-model-directory", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "audio_input": { "unit": "per_M_tokens", "price": "32" }, "prompt": { "unit": "per_M_tokens", "price": "4" }, "audio_output": { "unit": "per_M_tokens", "price": "64" }, "completion": { "unit": "per_M_tokens", "price": "16" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "image_input": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry", "cache_write": "portkey", "audio_cache_read": "portkey", "image_input": "portkey" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "16" }, "discarded_charge": { "unit": "per_M_tokens", "price": "64" }, "message": "completion from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "cache_read from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-realtime-1.5" } ], "max_input_tokens": 32000, "max_output_tokens": 4096, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ] }, "model_type": "realtime_omni", "capabilities": { "function_calling": true, "prompt_caching": true, "vision": true, "audio_input": true, "audio_output": true, "pdf_input": true, "parallel_function_calling": true }, "released_at": "2026-02-19", "knowledge_cutoff": "2024-09", "intro": "Speech generation model for controllable voice, narration, and audio delivery", "family": "gpt", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-realtime-1.5", "openai/gpt-realtime-1.5" ], "price_history": [ { "date": "2026-07-19", "kind": "listed", "note": "GPT-Realtime-1.5" } ] }, { "slug": "openai/gpt-realtime-2", "model_name": "gpt-realtime-2", "display_name": "GPT-Realtime-2", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "pydantic-prices+truefoundry+portkey+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "audio_input": { "unit": "per_M_tokens", "price": "32" }, "audio_output": { "unit": "per_M_tokens", "price": "64" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.4" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "image_input": { "unit": "per_M_tokens", "price": "5" }, "image_cache_read": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "audio_input": "pydantic-prices", "audio_output": "pydantic-prices", "cache_read_input_audio": "truefoundry", "cache_write": "portkey", "audio_cache_read": "portkey", "image_input": "portkey", "image_cache_read": "portkey" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "pydantic-prices", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from ai-model-directory conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "24" }, "discarded_charge": { "unit": "per_M_tokens", "price": "64" }, "message": "completion from ai-model-directory conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "pydantic-prices", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "cache_read from ai-model-directory conflicts with pydantic-prices; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "capabilities": { "function_calling": true, "prompt_caching": true, "reasoning": true, "vision": true, "audio_input": true, "audio_output": true, "pdf_input": true, "parallel_function_calling": true }, "max_input_tokens": 128000, "max_output_tokens": 32000, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ] }, "model_type": "realtime_omni", "released_at": "2026-05-05", "knowledge_cutoff": "2024-09", "intro": "Speech generation model for controllable voice, narration, and audio delivery", "family": "gpt", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-realtime-2-2026-05-06", "openai/gpt-realtime-2" ], "price_history": [ { "date": "2026-07-19", "kind": "limit", "old": "32000", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-07-19", "kind": "limit", "old": "4096", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-07-19", "kind": "price", "provider": "openai", "charge": "completion", "old": "16", "new": "24" }, { "date": "2026-07-19", "kind": "price", "provider": "openai", "charge": "image_input", "old": "0.000005", "new": "5" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "openai/gpt-realtime-2.1", "model_name": "gpt-realtime-2.1", "display_name": "GPT-Realtime-2.1", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "4" }, "completion": { "unit": "per_M_tokens", "price": "24" }, "cache_read": { "unit": "per_M_tokens", "price": "0.4" }, "audio_input": { "unit": "per_M_tokens", "price": "32" }, "audio_output": { "unit": "per_M_tokens", "price": "64" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.4" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "audio_input": "models-dev", "audio_output": "models-dev", "cache_read_input_audio": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from ai-model-directory conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "24" }, "discarded_charge": { "unit": "per_M_tokens", "price": "64" }, "message": "completion from ai-model-directory conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "cache_read from ai-model-directory conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior", "released_at": "2026-07-06", "knowledge_cutoff": "2024-09", "max_input_tokens": 128000, "max_output_tokens": 32000, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ] }, "family": "gpt", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "audio_output": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true }, "model_type": "realtime_omni", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-realtime-2.1-2026-07-07", "openai/gpt-realtime-2.1" ], "price_history": [ { "date": "2026-08-04", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-28", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-19", "kind": "capability", "note": "parallel_function_calling: true→false" }, { "date": "2026-07-09", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-07", "kind": "listed", "note": "GPT-Realtime-2.1" }, { "date": "2026-07-07", "kind": "price", "provider": "openai", "charge": "cache_read", "old": "0.5", "new": "0.4" }, { "date": "2026-07-07", "kind": "price", "provider": "openai", "charge": "completion", "old": "64", "new": "24" }, { "date": "2026-07-07", "kind": "price", "provider": "openai", "charge": "prompt", "old": "5", "new": "4" } ] }, { "slug": "openai/gpt-realtime-2.1-mini", "model_name": "gpt-realtime-2.1-mini", "display_name": "GPT-Realtime-2.1 mini", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.06" }, "audio_input": { "unit": "per_M_tokens", "price": "10" }, "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "audio_output": { "unit": "per_M_tokens", "price": "20" }, "completion": { "unit": "per_M_tokens", "price": "2.4" } }, "provenance": { "base_charges": { "cache_read_input_audio": "truefoundry", "cache_read": "truefoundry", "audio_input": "truefoundry", "prompt": "truefoundry", "audio_output": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.8" }, "message": "prompt from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "20" }, "message": "completion from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.06" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.08" }, "message": "cache_read from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 128000, "max_output_tokens": 32000, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ] }, "model_type": "realtime_omni", "capabilities": { "function_calling": true, "prompt_caching": true, "reasoning": true, "vision": true, "audio_input": true, "audio_output": true, "pdf_input": true, "structured_output": true }, "released_at": "2026-06-23", "knowledge_cutoff": "2024-09", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-28", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-19", "kind": "capability", "note": "parallel_function_calling: true→false" }, { "date": "2026-07-19", "kind": "limit", "old": "4096", "new": "32000", "note": "max_output_tokens" }, { "date": "2026-07-09", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-09", "kind": "limit", "new": "128000", "note": "max_input_tokens" }, { "date": "2026-07-09", "kind": "limit", "new": "4096", "note": "max_output_tokens" }, { "date": "2026-07-07", "kind": "listed", "note": "GPT-Realtime-2.1 mini" }, { "date": "2026-07-07", "kind": "price", "provider": "openai", "charge": "cache_read", "old": "0.08", "new": "0.06" }, { "date": "2026-07-07", "kind": "price", "provider": "openai", "charge": "completion", "old": "20", "new": "2.4" }, { "date": "2026-07-07", "kind": "price", "provider": "openai", "charge": "prompt", "old": "0.8", "new": "0.6" } ] }, { "slug": "openai/gpt-realtime-mini", "model_name": "gpt-realtime-mini", "display_name": "GPT-Realtime mini", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "pydantic-prices+truefoundry+portkey+llmdb+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.06" }, "audio_input": { "unit": "per_M_tokens", "price": "10" }, "audio_output": { "unit": "per_M_tokens", "price": "20" }, "cache_read_input_audio": { "unit": "per_M_tokens", "price": "0.3" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "audio_cache_read": { "unit": "per_M_tokens", "price": "0.08" }, "image_input": { "unit": "per_M_tokens", "price": "0.8" }, "image_cache_read": { "unit": "per_M_tokens", "price": "0.08" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "audio_input": "pydantic-prices", "audio_output": "pydantic-prices", "cache_read_input_audio": "truefoundry", "cache_write": "portkey", "audio_cache_read": "portkey", "image_input": "portkey", "image_cache_read": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "portkey", "charge": "audio_cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.08" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "audio_cache_read from portkey conflicts with portkey; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "portkey", "charge": "audio_cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.08" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "audio_cache_read from portkey conflicts with portkey; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "gpt-realtime-mini-2025-10-06" } ], "capabilities": { "function_calling": true, "prompt_caching": true, "vision": true, "audio_input": true, "audio_output": true, "pdf_input": true, "parallel_function_calling": true, "structured_output": true }, "max_input_tokens": 32000, "max_output_tokens": 4096, "modalities": { "input": [ "text", "audio", "image" ], "output": [ "text", "audio" ] }, "model_type": "realtime_omni", "deprecated": true, "released_at": "2025-10-03", "knowledge_cutoff": "2023-10", "intro": "Speech generation model for controllable voice, narration, and audio delivery", "family": "gpt", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "gpt-realtime-mini-2025-10-06", "gpt-realtime-mini-2025-12-15", "openai/gpt-realtime-mini" ], "price_history": [ { "date": "2026-07-28", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-19", "kind": "limit", "old": "128000", "new": "32000", "note": "max_input_tokens" }, { "date": "2026-07-19", "kind": "price", "provider": "openai", "charge": "image_input", "old": "0.0000008", "new": "0.8" }, { "date": "2026-07-03", "kind": "delisted", "note": "deprecated" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "openai/gpt-realtime-translate", "model_name": "gpt-realtime-translate", "display_name": "gpt-realtime-translate", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0005666666666666667" } }, "provenance": { "base_charges": { "audio_input": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 16000, "max_output_tokens": 2000, "modalities": { "input": [ "audio" ], "output": [ "audio", "text" ] }, "model_type": "realtime_speech_translation", "capabilities": { "audio_input": true, "audio_output": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "gpt-realtime-translate" } ] }, { "slug": "openai/gpt-realtime-whisper", "model_name": "gpt-realtime-whisper", "display_name": "gpt-realtime-whisper", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.0002833333333333333" } }, "provenance": { "base_charges": { "audio_input": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_second", "price": "0.0002833333333333333" }, "discarded_charge": { "unit": "per_second", "price": "0.0002833333" }, "message": "audio_input from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://platform.openai.com/docs/models/gpt-realtime-whisper", "model_type": "realtime_speech_recognition", "capabilities": { "audio_input": true }, "max_input_tokens": 16000, "max_output_tokens": 2000, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "intro": "Streaming speech-to-text model for low-latency transcript deltas from live audio", "released_at": "2026-05-07", "family": "whisper", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/gpt-realtime-whisper" ], "price_history": [ { "date": "2026-07-02", "kind": "limit", "new": "16000", "note": "max_input_tokens" }, { "date": "2026-07-02", "kind": "limit", "new": "2000", "note": "max_output_tokens" } ] }, { "slug": "openai/gpt-transcribe", "model_name": "gpt-transcribe", "display_name": "gpt-transcribe", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+truefoundry", "charges": { "audio_input": { "unit": "per_second", "price": "0.000075" } }, "provenance": { "base_charges": { "audio_input": "litellm" }, "verification_status": "cross_checked" } } ], "docs_url": "https://platform.openai.com/docs/models/gpt-transcribe", "model_type": "speech_recognition", "capabilities": { "audio_input": true }, "modalities": { "input": [ "audio", "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-29", "kind": "listed", "note": "gpt-transcribe" } ] }, { "slug": "openai/o1", "model_name": "o1", "display_name": "o1", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "60" }, "cache_read": { "unit": "per_M_tokens", "price": "7.5" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "file_search_call": "portkey", "cache_write": "portkey", "web_search": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "file_search_call": "portkey", "cache_write": "portkey", "web_search": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "o1-2024-12-17", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "O-series reasoning model for hard analysis, math, coding, and planning", "released_at": "2024-12-05", "knowledge_cutoff": "2023-09", "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecated": true, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "o", "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "deprecation_date": "2026-10-23", "benchmarks": { "intelligence_index": null, "coding_index": 39.7, "agentic_index": null }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "o1-2024-12-17", "openai/o1" ], "intro_i18n": { "zh-CN": "o1 是 OpenAI 推出的新型推理模型，支持文本+图像输入和文本输出，适用于需要广泛知识的复杂任务。具备 200K 上下文窗口，知识截止于 2023 年 10 月。", "zh-TW": "o1 是 OpenAI 的新一代推理模型，支援文字與圖像輸入、文字輸出，適用於需要廣泛知識的複雜任務。具備 200K 上下文視窗，知識截止於 2023 年 10 月。", "ja-JP": "o1はOpenAIの新しい推論モデルで、テキスト＋画像入力とテキスト出力に対応し、幅広い知識を必要とする複雑なタスクに適しています。200Kのコンテキストウィンドウと2023年10月の知識カットオフを持ちます。", "ru-RU": "o1 — новая модель рассуждения от OpenAI с вводом текст+изображение и текстовым выводом, подходящая для сложных задач, требующих обширных знаний. Имеет контекстное окно 200K и отсечку знаний на октябрь 2023 года." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/o1-mini", "model_name": "o1-mini", "display_name": "o1-mini", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices+truefoundry+portkey+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.1" }, "completion": { "unit": "per_M_tokens", "price": "4.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "file_search_call": "portkey", "cache_write": "portkey", "web_search": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "pydantic-prices+portkey", "charge_sources": { "prompt": "pydantic-prices", "completion": "pydantic-prices", "cache_read": "pydantic-prices", "file_search_call": "portkey", "cache_write": "portkey", "web_search": "portkey" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "pydantic-prices", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.55" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "cache_read from truefoundry conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "pydantic-prices", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "prompt from truefoundry conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from truefoundry conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "prompt from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "12" }, "message": "completion from portkey conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "pydantic-prices", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.55" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "cache_read from portkey conflicts with pydantic-prices; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "o1-mini-2024-09-12", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "O1 Mini is a model that offers a balance between cost and performance.", "max_input_tokens": 128000, "capabilities": { "prompt_caching": true, "vision": true, "pdf_input": true, "function_calling": true, "reasoning": true, "parallel_function_calling": true, "stream": true, "structured_output": true }, "max_output_tokens": 65536, "modalities": { "input": [ "image", "pdf" ], "output": [] }, "model_type": "deep_thinking", "released_at": "2025-01-01", "knowledge_cutoff": "2025-01", "family": "o-mini", "parameters": { "unsupported": [ "temperature" ] }, "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "o1-mini-2024-09-12", "openai/o1-mini", "openai/o1-mini-2024-09-12" ], "intro_i18n": { "zh-CN": "o1-mini 是一款快速、经济高效的推理模型，专为编码、数学和科学设计。支持 128K 上下文，知识截止日期为 2023 年 10 月。", "zh-TW": "o1-mini 是一款快速且具成本效益的推理模型，專為編程、數學和科學設計。擁有 128K 上下文及 2023 年 10 月的知識截止。", "ja-JP": "o1-miniは、コーディング、数学、科学向けに設計された高速でコスト効率の高い推論モデルです。128Kのコンテキストと2023年10月の知識カットオフを持ちます。", "ru-RU": "o1-mini — это быстрая, экономичная модель рассуждений, разработанная для программирования, математики и науки. Она имеет контекст 128K и отсечку знаний на октябрь 2023 года." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "o1-mini" } ] }, { "slug": "openai/o1-preview", "model_name": "o1-preview", "display_name": "o1 and o1-preview", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "portkey+llm-prices-www", "charges": { "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "60" }, "cache_read": { "unit": "per_M_tokens", "price": "7.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" } }, "provenance": { "base_charges": { "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey", "web_search": "portkey" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey", "charge_sources": { "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey", "cache_write": "portkey", "web_search": "portkey" } } ], "verification_status": "cross_checked" }, "provider_model_id": "o1-preview-2024-09-12", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "pdf_input": true, "parallel_function_calling": true, "stream": true }, "intro": "O-series reasoning model for hard analysis, math, coding, and planning", "released_at": "2024-01-01", "max_input_tokens": 128000, "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "o", "model_type": "deep_thinking", "knowledge_cutoff": "2023-09", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "o1-preview-2024-09-12", "openai/o1-preview" ], "intro_i18n": { "zh-CN": "o1 是 OpenAI 推出的新推理模型，适用于需要广泛知识的复杂任务。支持 128K 上下文，知识截止日期为 2023 年 10 月。", "zh-TW": "o1 是 OpenAI 的新推理模型，適用於需要廣泛知識的複雜任務。擁有 128K 上下文及 2023 年 10 月的知識截止。", "ja-JP": "o1は、広範な知識を必要とする複雑なタスク向けのOpenAIの新しい推論モデルです。128Kのコンテキストと2023年10月の知識カットオフを持ちます。", "ru-RU": "o1 — это новая модель рассуждений от OpenAI для сложных задач, требующих обширных знаний. Она имеет контекст 128K и отсечку знаний на октябрь 2023 года." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "o1 and o1-preview" } ] }, { "slug": "openai/o1-pro", "model_name": "o1-pro", "display_name": "o1-pro", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "150" }, "completion": { "unit": "per_M_tokens", "price": "600" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "file_search_call": "portkey", "web_search": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "file_search_call": "portkey", "web_search": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "o1-pro-2025-03-19", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "O-series reasoning model for hard analysis, math, coding, and planning", "released_at": "2025-03-19", "knowledge_cutoff": "2023-09", "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "o-pro", "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "parallel_function_calling": true, "stream": true }, "model_type": "deep_thinking", "deprecation_date": "2026-10-23", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "reasoning_config": { "mandatory": false }, "aliases": [ "o1-pro-2025-03-19", "openai/o1-pro" ], "intro_i18n": { "zh-CN": "o1 系列通过强化学习训练，具备先思考后作答的能力，能处理复杂推理任务。o1-pro 使用更多计算资源，提供更深入的思考和更高质量的回答。", "zh-TW": "o1 系列透過強化學習訓練，具備先思考再作答的能力，能處理複雜推理任務。o1-pro 使用更多運算資源以進行更深入思考，並穩定提供更高品質的回答。", "ja-JP": "o1シリーズは、回答前に思考するよう強化学習で訓練され、複雑な推論を処理できます。o1-proはより多くの計算資源を使用し、より深い思考と一貫して高品質な回答を提供します。", "ru-RU": "Серия o1 обучена с использованием обучения с подкреплением для предварительного обдумывания ответов и решения сложных задач. o1-pro использует больше вычислений для более глубокого мышления и стабильно высокого качества ответов." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/o3", "model_name": "o3", "display_name": "o3", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "8" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10" }, "message": "prompt from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "40" }, "message": "completion from llm-prices-www conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1" }, "message": "prompt from ai-model-directory conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "8" }, "discarded_charge": { "unit": "per_M_tokens", "price": "4" }, "message": "completion from ai-model-directory conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.25" }, "message": "cache_read from ai-model-directory conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "o3-2025-04-16", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1.75", "completion": "1.75", "cache_read": "1.75" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.5" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Deliberate o-series reasoner for hard math, coding, and multi-step analysis", "released_at": "2025-04-16", "knowledge_cutoff": "2024-05", "max_input_tokens": 200000, "max_output_tokens": 100000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "o", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses", "openai-compatible" ] }, "deprecation_date": "2026-12-11", "deprecated": true, "reasoning_config": { "mandatory": false }, "aliases": [ "o3-2025-04-16", "openai/o3" ], "intro_i18n": { "zh-CN": "o3 是 OpenAI 推出的新型推理模型，支持文本+图像输入和文本输出，适用于需要广泛知识的复杂任务。", "zh-TW": "o3 是 OpenAI 的新一代推理模型，支援文字與圖像輸入、文字輸出，適用於需要廣泛知識的複雜任務。", "ja-JP": "o3はOpenAIの新しい推論モデルで、テキスト＋画像入力とテキスト出力に対応し、幅広い知識を必要とする複雑なタスクに適しています。", "ru-RU": "o3 — новая модель рассуждения от OpenAI с вводом текст+изображение и текстовым выводом для сложных задач, требующих обширных знаний." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/o3-deep-research", "model_name": "o3-deep-research", "display_name": "o3-deep-research", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "10" }, "completion": { "unit": "per_M_tokens", "price": "40" }, "cache_read": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "o3-deep-research-2025-06-26", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-07-23", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "Research model for long-horizon investigation, synthesis, and analytical reports", "released_at": "2024-06-26", "knowledge_cutoff": "2024-05", "family": "o", "parameters": { "unsupported": [ "temperature" ] }, "aliases": [ "o3-deep-research-2025-06-26", "openai/o3-deep-research" ], "intro_i18n": { "zh-CN": "o3-deep-research 是我们最先进的深度研究模型，适用于复杂的多步研究。它可以通过 MCP 连接器搜索和综合网络信息并访问您的专属数据。", "zh-TW": "o3-deep-research 是我們最先進的深度研究模型，專為複雜的多步研究而設計。它可以通過 MCP 連接器搜索和綜合網絡信息並訪問您的數據。", "ja-JP": "o3-deep-researchは、複雑なマルチステップ研究向けの最先端の深層研究モデルです。ウェブ情報の検索と統合、MCPコネクタを介した独自データへのアクセスが可能です。", "ru-RU": "o3-deep-research — наша самая продвинутая модель для глубоких исследований, способная выполнять сложные многошаговые исследования. Она может искать и синтезировать информацию из интернета, а также получать доступ к вашим данным через MCP-коннекторы." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/o3-mini", "model_name": "o3-mini", "display_name": "o3-mini", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.1" }, "completion": { "unit": "per_M_tokens", "price": "4.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.55" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "o3-mini-2025-01-31", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Smaller o-series reasoner for economical coding, math, and planning tasks", "released_at": "2024-12-20", "knowledge_cutoff": "2024-05", "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "o-mini", "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "deprecation_date": "2026-10-23", "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "o3-mini-2025-01-31", "openai-responses/o3-mini", "openai/o3-mini" ], "intro_i18n": { "zh-CN": "o3-mini 是我们最新的小型推理模型，在保持与 o1-mini 相同成本和延迟的前提下，提供更高的智能表现。", "zh-TW": "o3-mini 是我們最新的小型推理模型，在維持與 o1-mini 相同成本與延遲的前提下，提供更高智慧表現。", "ja-JP": "o3-miniは、o1-miniと同等のコストとレイテンシで、より高い知能を提供する最新の小型推論モデルです。", "ru-RU": "o3-mini — наша последняя компактная модель рассуждения, обеспечивающая более высокий интеллект при тех же затратах и задержке, что и o1-mini." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/o3-pro", "model_name": "o3-pro", "display_name": "o3-pro", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "20" }, "completion": { "unit": "per_M_tokens", "price": "80" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "service_tier_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "20" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10" }, "message": "batch prompt from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "80" }, "discarded_charge": { "unit": "per_M_tokens", "price": "40" }, "message": "batch completion from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "20" }, "discarded_charge": { "unit": "per_M_tokens", "price": "10" }, "message": "batch prompt from portkey conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "service_tier_charge", "source": "portkey", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "80" }, "discarded_charge": { "unit": "per_M_tokens", "price": "40" }, "message": "batch completion from portkey conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "o3-pro-2025-06-10", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "1", "completion": "1", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "High-effort o3 tier for difficult technical reasoning and careful answers", "released_at": "2025-06-10", "knowledge_cutoff": "2024-05", "max_input_tokens": 200000, "max_output_tokens": 100000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "o-pro", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-responses" ] }, "deprecation_date": "2026-12-11", "deprecated": true, "reasoning_config": { "mandatory": false }, "aliases": [ "o3-pro-2025-06-10", "openai-responses/o3-pro", "openai/o3-pro", "openai/o3-pro-2025-06-10" ], "intro_i18n": { "zh-CN": "o3 Pro 是 OpenAI 推出的新一代推理模型，支持文本+图像输入和文本输出，适用于需要广泛知识的复杂任务。", "zh-TW": "o3 Pro 是 OpenAI 的新一代推理模型，支援文字與圖像輸入、文字輸出，適用於需要廣泛知識的複雜任務。", "ja-JP": "o3 Proは、OpenAIの新しい推論モデルで、テキスト＋画像入力とテキスト出力に対応し、幅広い知識を必要とする複雑なタスクに適しています。", "ru-RU": "o3 Pro — новая модель рассуждения от OpenAI с вводом текст+изображение и текстовым выводом для сложных задач, требующих обширных знаний." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/o4-mini", "model_name": "o4-mini", "display_name": "o4-mini", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+portkey+llmdb+lobehub-modelbank+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.1" }, "completion": { "unit": "per_M_tokens", "price": "4.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.275" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Priority", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Flex", "source": "portkey", "charge_sources": { "web_search": "portkey", "file_search_call": "portkey", "prompt": "portkey", "completion": "portkey", "cache_read": "portkey" } }, { "label": "Base pricing", "source": "models-dev+helicone-registry+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "web_search": "helicone-registry", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.275" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.28" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.275" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.28" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "o4-mini-2025-04-16", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Priority", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "1.818182", "completion": "1.818182", "cache_read": "1.818182" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^priority$" } ] }, { "label": "Flex", "factor": "1", "charge_factors": { "web_search": "1", "file_search_call": "1", "prompt": "0.5", "completion": "0.5", "cache_read": "0.501818" }, "triggers": [ { "kind": "body_matches", "field": "service_tier", "pattern": "^flex$" } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Fast o-series model for compact reasoning, coding, and tool use", "released_at": "2025-04-16", "knowledge_cutoff": "2024-05", "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "o-mini", "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "model_type": "deep_thinking", "deprecation_date": "2026-10-23", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "reasoning_config": { "mandatory": false }, "aliases": [ "o4-mini-2025-04-16", "openai-responses/o4-mini", "openai/o4-mini", "pa/o4-mini" ], "intro_i18n": { "zh-CN": "o4-mini 是 OpenAI 的推理模型，支持文本+图像输入和文本输出，适用于需要广泛知识的复杂任务，具备 200K 上下文窗口。", "zh-TW": "o4-mini 是 OpenAI 的推理模型，支援文字與圖像輸入、文字輸出，適用於需要廣泛知識的複雜任務，具備 200K 上下文視窗。", "ja-JP": "o4-miniは、OpenAIの推論モデルで、テキスト＋画像入力とテキスト出力に対応し、幅広い知識を必要とする複雑なタスクに適しており、200Kのコンテキストウィンドウを備えています。", "ru-RU": "o4-mini — модель рассуждения от OpenAI с вводом текст+изображение и текстовым выводом, подходящая для сложных задач, требующих обширных знаний, с контекстным окном 200K." }, "price_history": [ { "date": "2026-07-06", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/o4-mini-deep-research", "model_name": "o4-mini-deep-research", "display_name": "o4-mini-deep-research", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+pydantic-prices+truefoundry+portkey+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "8" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" } }, { "label": "Base pricing", "source": "litellm+portkey+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "portkey", "file_search_call": "portkey", "cache_write": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "o4-mini-deep-research-2025-06-26", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5", "web_search": "1", "file_search_call": "1" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 200000, "max_output_tokens": 100000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-07-23", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "Research model for long-horizon investigation, synthesis, and analytical reports", "released_at": "2024-06-26", "knowledge_cutoff": "2024-05", "family": "o-mini", "parameters": { "unsupported": [ "temperature" ] }, "aliases": [ "o4-mini-deep-research-2025-06-26", "openai/o4-mini-deep-research" ], "intro_i18n": { "zh-CN": "o4-mini-deep-research 是一个更快、更经济的深度研究模型，适用于复杂的多步研究。它可以通过 MCP 连接器搜索和综合网络信息并访问您的专属数据。", "zh-TW": "o4-mini-deep-research 是一款更快速、更經濟的深度研究模型，適用於複雜的多步研究。它可以通過 MCP 連接器搜索和綜合網絡信息並訪問您的數據。", "ja-JP": "o4-mini-deep-researchは、複雑なマルチステップ研究向けの高速で手頃な価格の深層研究モデルです。ウェブ情報の検索と統合、MCPコネクタを介した独自データへのアクセスが可能です。", "ru-RU": "o4-mini-deep-research — это более быстрая и доступная модель для глубоких исследований, способная выполнять сложные многошаговые исследования. Она может искать и синтезировать информацию из интернета, а также получать доступ к вашим данным через MCP-коннекторы." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "openai/omni-moderation-2024-09-26", "model_name": "omni-moderation-2024-09-26", "display_name": "omni-moderation-2024-09-26", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "cross_checked" } } ], "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "safety_detection", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "omni-moderation-2024-09-26" } ] }, { "slug": "openai/omni-moderation-latest", "model_name": "omni-moderation-latest", "display_name": "omni-moderation-latest", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "cross_checked" } } ], "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "safety_detection", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "omni-moderation-latest" } ] }, { "slug": "openai/omni-moderation-latest-intents", "model_name": "omni-moderation-latest-intents", "display_name": "omni-moderation-latest-intents", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "safety_detection", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "omni-moderation-latest-intents" } ] }, { "slug": "openai/ra-gpt-5.6-sol", "model_name": "ra-gpt-5.6-sol", "display_name": "ra-gpt-5.6-sol", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "truefoundry", "charges": { "cache_write": { "unit": "per_M_tokens", "price": "6.25" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" }, "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "30" } }, "provenance": { "base_charges": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥272,001", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "cache_write": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_write": "truefoundry", "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥272,001", "factor": "1", "charge_factors": { "cache_read": "2", "cache_write": "2", "prompt": "2", "completion": "1.5" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 272001, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1050000, "max_output_tokens": 128000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "parallel_function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-30", "kind": "listed", "note": "ra-gpt-5.6-sol" } ] }, { "slug": "openai/sora-2", "model_name": "sora-2", "display_name": "Sora 2", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "audio_output": { "unit": "per_second", "price": "0.1" }, "video_output_720x1280": { "unit": "per_second", "price": "0.1" }, "video_output_720p": { "unit": "per_second", "price": "0.1" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" }, "video_output": { "unit": "per_second", "price": "0.1" } }, "provenance": { "base_charges": { "audio_output": "truefoundry", "video_output_720x1280": "portkey", "video_output_720p": "portkey", "prompt": "portkey", "completion": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb", "video_output": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "video_output_720x1280": "portkey", "video_output_720p": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "truefoundry+portkey+llmdb+lobehub-modelbank", "charge_sources": { "audio_output": "truefoundry", "video_output_720x1280": "portkey", "video_output_720p": "portkey", "prompt": "portkey", "completion": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb", "video_output": "lobehub-modelbank" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "video_output_720x1280": "0.5", "video_output_720p": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "video", "audio" ] }, "model_type": "video_generation", "capabilities": { "vision": true, "audio_output": true, "function_calling": true, "pdf_input": true, "video_input": true }, "released_at": "2025-12-08", "intro": "Video model for prompt-guided generation, editing, and motion workflows", "max_input_tokens": 0, "max_output_tokens": 0, "family": "sora", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/sora-2", "sora-2-2025-10-06", "sora-2-2025-12-08" ], "intro_i18n": { "zh-CN": "Sora 2是我们新推出的强大媒体生成模型，生成与音频同步的视频。可从自然语言或图像创建细节丰富、动态的视频片段。", "zh-TW": "Sora 2是我們的新型強大媒體生成模型，生成與音頻同步的影像。能從自然語言或影像創建細緻且動態的片段。", "ja-JP": "Sora 2は、新しい強力なメディア生成モデルで、音声と同期したビデオを生成します。自然言語または画像からリッチで詳細な動的クリップを作成できます。", "ru-RU": "Sora 2 — наша новая мощная модель генерации медиа, создающая видео с синхронизированным звуком. Она может создавать детализированные, динамичные клипы из естественного языка или изображений." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Sora 2" } ] }, { "slug": "openai/sora-2-pro", "model_name": "sora-2-pro", "display_name": "Sora 2 Pro", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "portkey+llmdb+lobehub-modelbank", "charges": { "video_output_720x1280": { "unit": "per_second", "price": "0.3" }, "video_output_720p": { "unit": "per_second", "price": "0.3" }, "video_output_1024x1792": { "unit": "per_second", "price": "0.5" }, "video_output_1792x1024": { "unit": "per_second", "price": "0.5" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "video_output_1080x1920": { "unit": "per_second", "price": "0.7" }, "video_output_1080p": { "unit": "per_second", "price": "0.7" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" }, "video_output": { "unit": "per_second", "price": "0.5" } }, "provenance": { "base_charges": { "video_output_720x1280": "portkey", "video_output_720p": "portkey", "video_output_1024x1792": "portkey", "video_output_1792x1024": "portkey", "prompt": "portkey", "completion": "portkey", "video_output_1080x1920": "portkey", "video_output_1080p": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb", "video_output": "lobehub-modelbank" }, "tracks": [ { "label": "Batch", "source": "portkey", "charge_sources": { "video_output_720x1280": "portkey", "video_output_720p": "portkey", "video_output_1024x1792": "portkey", "video_output_1792x1024": "portkey", "video_output_1080x1920": "portkey", "video_output_1080p": "portkey", "prompt": "portkey", "completion": "portkey" } }, { "label": "Base pricing", "source": "portkey+llmdb+lobehub-modelbank", "charge_sources": { "video_output_720x1280": "portkey", "video_output_720p": "portkey", "video_output_1024x1792": "portkey", "video_output_1792x1024": "portkey", "prompt": "portkey", "completion": "portkey", "video_output_1080x1920": "portkey", "video_output_1080p": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb", "video_output": "lobehub-modelbank" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "video_output_720x1280": "0.5", "video_output_720p": "0.5", "video_output_1024x1792": "0.5", "video_output_1792x1024": "0.5", "video_output_1080x1920": "0.5", "video_output_1080p": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "capabilities": { "vision": true, "function_calling": true, "pdf_input": true }, "released_at": "2025-10-06", "model_type": "video_generation", "intro": "Video model for prompt-guided generation, editing, and motion workflows", "max_input_tokens": 0, "max_output_tokens": 0, "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "family": "sora", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/sora-2-pro" ], "intro_i18n": { "zh-CN": "Sora 2 Pro是我们最先进的媒体生成模型，生成与音频同步的视频。可从自然语言或图像创建细节丰富、动态的视频片段。", "zh-TW": "Sora 2 Pro是我們最先進的媒體生成模型，生成與音頻同步的影像。能從自然語言或影像創建細緻且動態的片段。", "ja-JP": "Sora 2 Proは、最先端の最も高度なメディア生成モデルで、音声と同期したビデオを生成します。自然言語または画像からリッチで詳細な動的クリップを作成できます。", "ru-RU": "Sora 2 Pro — наша передовая модель генерации медиа, создающая видео с синхронизированным звуком. Она может создавать детализированные, динамичные клипы из естественного языка или изображений." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Sora 2 Pro" } ] }, { "slug": "openai/text-davinci-002", "model_name": "text-davinci-002", "display_name": "text-davinci-002", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "20" }, "completion": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "text-davinci-002" } ] }, { "slug": "openai/text-davinci-003", "model_name": "text-davinci-003", "display_name": "GPT-3 Text Davinci 003", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "pydantic-prices+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "20" }, "completion": { "unit": "per_M_tokens", "price": "20" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GPT-3 Text Davinci 003" } ] }, { "slug": "openai/text-embedding-3-large", "model_name": "text-embedding-3-large", "display_name": "text-embedding-3-large", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.13" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.13" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.00013" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2024-01-25", "knowledge_cutoff": "2024-01", "max_input_tokens": 8191, "max_output_tokens": 3072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "text-embedding", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "stream": true }, "model_type": "text_embedding", "deprecation_date": "2028-02-09", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/text-embedding-3-large" ], "intro_i18n": { "zh-CN": "OpenAI 最强大的嵌入模型，适用于英文和非英文任务。", "zh-TW": "OpenAI 最強大的嵌入模型，適用於英文與非英文任務。", "ja-JP": "OpenAIの英語および非英語タスク向けで最も高性能な埋め込みモデルです。", "ru-RU": "Самая мощная модель встраивания от OpenAI для задач на английском и других языках." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/text-embedding-3-small", "model_name": "text-embedding-3-small", "display_name": "text-embedding-3-small", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.02" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "models-dev+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.02" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.00002" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2024-01-25", "knowledge_cutoff": "2024-01", "max_input_tokens": 8191, "max_output_tokens": 1536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "text-embedding", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "stream": true }, "model_type": "text_embedding", "deprecation_date": "2028-02-09", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/text-embedding-3-small" ], "intro_i18n": { "zh-CN": "OpenAI 提升性能的 ada 嵌入模型变体。", "zh-TW": "OpenAI 改良版、高效能的 ada 嵌入模型變體。", "ja-JP": "OpenAIの改良された高性能なada埋め込みモデルのバリアントです。", "ru-RU": "Улучшенный и более производительный вариант модели встраивания ada от OpenAI." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/text-embedding-ada-002", "model_name": "text-embedding-ada-002", "display_name": "text-embedding-ada-002", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+portkey+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "portkey" } }, { "label": "Base pricing", "source": "models-dev+portkey+llmdb", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "web_search": "portkey", "file_search_call": "portkey", "web_search_preview": "llmdb", "file_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.0001" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2022-12-15", "knowledge_cutoff": "2022-12", "max_input_tokens": 8192, "max_output_tokens": 1536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "text-embedding", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "stream": true }, "model_type": "text_embedding", "deprecation_date": "2028-02-09", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/text-embedding-ada-002" ], "intro_i18n": { "zh-CN": "OpenAI 的旧版文本嵌入模型。", "zh-TW": "OpenAI 的舊版文字嵌入模型。", "ja-JP": "OpenAIの旧世代テキスト埋め込みモデルです。", "ru-RU": "Устаревшая модель встраивания текста от OpenAI." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "openai/text-embedding-ada-002-v2", "model_name": "text-embedding-ada-002-v2", "display_name": "text-embedding-ada-002-v2", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "litellm+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "portkey", "file_search_call": "portkey" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 8191, "model_type": "text_embedding", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] } }, { "slug": "openai/text-moderation-004", "model_name": "text-moderation-004", "display_name": "text-moderation-004", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "portkey", "completion": "portkey", "web_search": "portkey", "file_search_call": "portkey" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "model_type": "safety_detection", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "text-moderation-004" } ] }, { "slug": "openai/text-moderation-007", "model_name": "text-moderation-007", "display_name": "text-moderation-007", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 0, "model_type": "safety_detection", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "text-moderation-007" } ] }, { "slug": "openai/text-moderation-latest", "model_name": "text-moderation-latest", "display_name": "text-moderation-latest", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" }, "verification_status": "cross_checked" } } ], "max_output_tokens": 0, "model_type": "safety_detection", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "text-moderation-latest" } ] }, { "slug": "openai/text-moderation-stable", "model_name": "text-moderation-stable", "display_name": "text-moderation-stable", "vendor": "openai", "pricing": [ { "provider": "openai", "official": true, "source": "truefoundry+portkey", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "file_search_call": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry", "web_search": "portkey", "file_search_call": "portkey" }, "verification_status": "cross_checked" } } ], "max_output_tokens": 0, "model_type": "safety_detection", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "text-moderation-stable" } ] }, { "slug": "openai/tts-1", "model_name": "tts-1", "display_name": "TTS-1", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "speech_input": { "unit": "per_M_characters", "price": "15" }, "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "portkey", "completion": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "portkey", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "15" }, "discarded_charge": { "unit": "per_M_characters", "price": "15" }, "message": "prompt from lobehub-modelbank conflicts with portkey; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "model_type": "speech_synthesis", "capabilities": { "audio_output": true, "pdf_input": true, "audio_input": true, "prompt_caching": true }, "intro": "Speech generation model for controllable voice, narration, and audio delivery", "released_at": "2023-11-06", "max_input_tokens": 0, "max_output_tokens": 0, "family": "o", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/tts-1" ], "intro_i18n": { "zh-CN": "最新文本转语音模型，优化实时速度。", "zh-TW": "最新的文字轉語音模型，優化即時速度。", "ja-JP": "リアルタイム速度に最適化された最新の音声合成モデルです。", "ru-RU": "Последняя модель синтеза речи, оптимизированная для скорости в реальном времени." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "TTS-1" } ] }, { "slug": "openai/tts-1-1106", "model_name": "tts-1-1106", "display_name": "tts-1-1106", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "truefoundry+portkey+llmdb", "charges": { "speech_input": { "unit": "per_M_characters", "price": "15" }, "prompt": { "unit": "per_M_tokens", "price": "15" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "portkey", "completion": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "aggregator_only" } } ], "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "model_type": "speech_synthesis", "capabilities": { "audio_output": true, "pdf_input": true, "audio_input": true, "prompt_caching": true }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/tts-1-1106" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "tts-1-1106" } ] }, { "slug": "openai/tts-1-hd", "model_name": "tts-1-hd", "display_name": "TTS-1 HD", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "speech_input": { "unit": "per_M_characters", "price": "30" }, "prompt": { "unit": "per_M_tokens", "price": "30" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "portkey", "completion": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "portkey", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "30" }, "discarded_charge": { "unit": "per_M_characters", "price": "30" }, "message": "prompt from lobehub-modelbank conflicts with portkey; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "model_type": "speech_synthesis", "capabilities": { "audio_output": true, "pdf_input": true, "audio_input": true, "prompt_caching": true }, "intro": "Speech generation model for controllable voice, narration, and audio delivery", "released_at": "2023-11-06", "max_input_tokens": 0, "max_output_tokens": 0, "family": "o", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/tts-1-hd" ], "intro_i18n": { "zh-CN": "最新文本转语音模型，优化音质表现。", "zh-TW": "最新的文字轉語音模型，優化音質表現。", "ja-JP": "高品質に最適化された最新の音声合成モデルです。", "ru-RU": "Последняя модель синтеза речи, оптимизированная для качества." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "TTS-1 HD" } ] }, { "slug": "openai/tts-1-hd-1106", "model_name": "tts-1-hd-1106", "display_name": "tts-1-hd-1106", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "truefoundry+portkey+llmdb", "charges": { "speech_input": { "unit": "per_M_characters", "price": "30" }, "prompt": { "unit": "per_M_tokens", "price": "30" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "speech_input": "truefoundry", "prompt": "portkey", "completion": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "verification_status": "aggregator_only" } } ], "modalities": { "input": [ "text" ], "output": [ "audio" ] }, "model_type": "speech_synthesis", "capabilities": { "audio_output": true, "pdf_input": true, "audio_input": true, "prompt_caching": true }, "released_at": "2026-08-14", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/tts-1-hd-1106" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "tts-1-hd-1106" } ] }, { "slug": "openai/whisper-1", "model_name": "whisper-1", "display_name": "whisper-1", "vendor": "openai", "pricing": [ { "provider": "openai", "provider_name": "OpenAI", "official": true, "source": "litellm+truefoundry+portkey+llmdb+lobehub-modelbank", "charges": { "audio_input": { "unit": "per_second", "price": "0.0001" }, "audio_output": { "unit": "per_second", "price": "0.0001" }, "prompt": { "unit": "per_M_tokens", "price": "6000" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "web_search_preview": { "unit": "per_k_calls", "price": "10" }, "file_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "audio_input": "litellm", "audio_output": "litellm", "prompt": "portkey", "completion": "portkey", "web_search": "llmdb", "web_search_preview": "llmdb", "file_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_input", "selected_charge": { "unit": "per_second", "price": "0.0001" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6000" }, "message": "audio_input from portkey conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "portkey", "selected_source": "litellm", "charge": "audio_output", "selected_charge": { "unit": "per_second", "price": "0.0001" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0" }, "message": "audio_output from portkey conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "model_type": "speech_recognition", "capabilities": { "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true }, "modalities": { "input": [ "audio" ], "output": [ "text" ] }, "intro": "Speech transcription model for accurate audio-to-text and captioning workflows", "released_at": "2022-09-21", "max_input_tokens": 0, "max_output_tokens": 0, "family": "whisper", "deprecation_date": "2026-12-15", "endpoints": { "inbound": [ "openai-compatible", "openai-responses", "anthropic-messages" ], "outbound": [ "openai-compatible", "openai-responses" ] }, "aliases": [ "openai/whisper-1" ], "intro_i18n": { "zh-CN": "通用语音识别模型，支持多语言 ASR、语音翻译和语言识别。", "zh-TW": "通用語音識別模型，支援多語言 ASR、語音翻譯與語言識別。", "ja-JP": "多言語ASR、音声翻訳、言語識別に対応した汎用音声認識モデルです。", "ru-RU": "Универсальная модель распознавания речи с поддержкой многоязычного ASR, перевода речи и определения языка." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "perplexity/codellama-34b-instruct", "model_name": "codellama-34b-instruct", "display_name": "codellama-34b-instruct", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.35" }, "completion": { "unit": "per_M_tokens", "price": "1.4" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 16384, "max_output_tokens": 16384, "model_type": "text_generation", "capabilities": {}, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "meta-llama/codellama-34b-instruct" ], "price_history": [ { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "perplexity/codellama-70b-instruct", "model_name": "codellama-70b-instruct", "display_name": "codellama-70b-instruct", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.7" }, "completion": { "unit": "per_M_tokens", "price": "2.8" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 16384, "max_output_tokens": 16384, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "perplexity/llama-2-70b-chat", "model_name": "llama-2-70b-chat", "display_name": "llama-2-70b-chat", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.7" }, "completion": { "unit": "per_M_tokens", "price": "2.8" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 4096, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": {}, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "meta-llama/llama-2-70b-chat" ], "price_history": [ { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "perplexity/llama-3.1-70b-instruct", "model_name": "llama-3.1-70b-instruct", "display_name": "llama-3.1-70b-instruct", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding", "released_at": "2024-07-16", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "knowledge_cutoff": "2023-12", "family": "llama", "status": "beta", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "hf:meta-llama/Llama-3.1-70B-Instruct", "meta-llama/Llama-3.1-70B-Instruct", "meta-llama/llama-3.1-70b-instruct", "meta/llama-3.1-70b-instruct" ], "intro_i18n": { "zh-CN": "Meta 最新的 Llama 3.1 系列，70B 指令微调版本，专为高质量对话优化。在行业评估中表现优异，超越领先闭源模型。（仅对企业认证用户开放）", "zh-TW": "Meta 最新的 Llama 3.1 系列，70B 指令微調版本，針對高品質對話進行優化。在業界評估中，表現優於多數封閉模型。（僅限企業驗證用戶使用）", "ja-JP": "Metaの最新Llama 3.1シリーズの70B命令調整バージョンで、高品質な対話に最適化されています。業界評価において、主要なクローズドモデルに対して優れた性能を示しています。（企業認証済みの組織のみ利用可能）", "ru-RU": "Последняя серия Meta Llama 3.1, вариант с 70 миллиардами параметров, обученный на инструкциях и оптимизированный для высококачественных диалогов. В отраслевых оценках показывает отличные результаты по сравнению с ведущими закрытыми моделями. (Доступна только для проверенных корпоративных клиентов.)" }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "perplexity/llama-3.1-8b-instruct", "model_name": "llama-3.1-8b-instruct", "display_name": "llama-3.1-8b-instruct", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "intro": "Open Llama instruction model for multilingual chat, reasoning, and coding", "released_at": "2025-01-01", "knowledge_cutoff": "2023-12", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "llama", "parameters": { "unsupported": [ "temperature" ] }, "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "@cf/meta/llama-3.1-8b-instruct", "hf:meta-llama/Llama-3.1-8B-Instruct", "meta-llama/Llama-3.1-8B-Instruct", "meta-llama/llama-3.1-8b-instruct", "meta/llama-3.1-8b-instruct", "novita/meta-llama/llama-3.1-8b-instruct", "workers-ai/@cf/meta/llama-3.1-8b-instruct" ], "intro_i18n": { "zh-CN": "Meta 最新的 Llama 3.1 系列，8B 指令微调版本，速度快、效率高。在行业评估中表现优异，超越众多领先闭源模型。（仅对企业认证用户开放）", "zh-TW": "Meta 最新的 Llama 3.1 系列，8B 指令微調版本，速度快且效率高。在業界評估中表現優異，超越多數封閉模型。（僅限企業驗證用戶使用）", "ja-JP": "Metaの最新Llama 3.1シリーズの8B命令調整バージョンで、特に高速かつ効率的です。業界評価において、多くの主要なクローズドモデルを上回る性能を発揮します。（企業認証済みの組織のみ利用可能）", "ru-RU": "Последняя серия Meta Llama 3.1, вариант с 8 миллиардами параметров, обученный на инструкциях, особенно быстр и эффективен. В отраслевых оценках демонстрирует отличные результаты, превосходя многие ведущие закрытые модели. (Доступна только для проверенных корпоративных клиентов.)" }, "price_history": [ { "date": "2026-07-08", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "perplexity/llama-3.1-sonar-huge-128k-online", "model_name": "llama-3.1-sonar-huge-128k-online", "display_name": "llama-3.1-sonar-huge-128k-online", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 127072, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "llama-3.1-sonar-huge-128k-online" } ] }, { "slug": "perplexity/llama-3.1-sonar-large-128k-chat", "model_name": "llama-3.1-sonar-large-128k-chat", "display_name": "llama-3.1-sonar-large-128k-chat", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 131072, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "llama-3.1-sonar-large-128k-chat" } ] }, { "slug": "perplexity/llama-3.1-sonar-large-128k-online", "model_name": "llama-3.1-sonar-large-128k-online", "display_name": "llama-3.1-sonar-large-128k-online", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "pydantic-prices+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "1" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "intro": "Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance.", "capabilities": {}, "max_output_tokens": 127072, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "perplexity/llama-3.1-sonar-large-128k-online" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "llama-3.1-sonar-large-128k-online" } ] }, { "slug": "perplexity/llama-3.1-sonar-small-128k-chat", "model_name": "llama-3.1-sonar-small-128k-chat", "display_name": "llama-3.1-sonar-small-128k-chat", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_output_tokens": 131072, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "llama-3.1-sonar-small-128k-chat" } ] }, { "slug": "perplexity/llama-3.1-sonar-small-128k-online", "model_name": "llama-3.1-sonar-small-128k-online", "display_name": "llama-3.1-sonar-small-128k-online", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "pydantic-prices+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "intro": "Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance.", "capabilities": {}, "max_output_tokens": 127072, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "perplexity/llama-3.1-sonar-small-128k-online" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "llama-3.1-sonar-small-128k-online" } ] }, { "slug": "perplexity/mistral-7b-instruct", "model_name": "mistral-7b-instruct", "display_name": "mistral-7b-instruct", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.07" }, "completion": { "unit": "per_M_tokens", "price": "0.28" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 4096, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "function_calling": true, "stream": true, "open_weights": true }, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2025-04-01", "family": "mistral", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mistral-7b-instruct:free", "mistral.mistral-7b-instruct-v0:2", "mistralai/mistral-7b-instruct", "mistralai/mistral-7b-instruct:free" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "perplexity/mixtral-8x7b-instruct", "model_name": "mixtral-8x7b-instruct", "display_name": "mixtral-8x7b-instruct", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.07" }, "completion": { "unit": "per_M_tokens", "price": "0.28" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 4096, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true }, "intro": "Mistral model for multilingual chat, reasoning, and tool-assisted workflows", "released_at": "2023-12-10", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "deprecated": true, "family": "mixtral", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "accounts/fireworks/models/mixtral-8x7b-instruct", "mistral.mixtral-8x7b-instruct-v0:1", "mistralai/mixtral-8x7b-instruct" ], "intro_i18n": { "zh-CN": "Mixtral MoE 8x7B Instruct 是 Mixtral MoE 8x7B 的指令微调版本，启用了聊天补全 API。", "zh-TW": "Mixtral MoE 8x7B Instruct 是 Mixtral MoE 8x7B 的指令微調版本，已啟用聊天補全 API。", "ja-JP": "Mixtral MoE 8x7B Instructは、Mixtral MoE 8x7Bの命令調整済みバージョンで、チャット補完APIが有効化されています。", "ru-RU": "Mixtral MoE 8x7B Instruct — это дообученная на инструкциях версия модели Mixtral MoE 8x7B с включенной поддержкой API завершения чата." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "perplexity/pplx-70b-chat", "model_name": "pplx-70b-chat", "display_name": "pplx-70b-chat", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.7" }, "completion": { "unit": "per_M_tokens", "price": "2.8" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 4096, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "perplexity/pplx-70b-online", "model_name": "pplx-70b-online", "display_name": "pplx-70b-online", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "2.8" }, "request": { "unit": "per_request", "price": "0.005" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "request": "truefoundry" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 4096, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "perplexity/pplx-7b-chat", "model_name": "pplx-7b-chat", "display_name": "pplx-7b-chat", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.07" }, "completion": { "unit": "per_M_tokens", "price": "0.28" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 8192, "max_output_tokens": 8192, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "perplexity/pplx-7b-online", "model_name": "pplx-7b-online", "display_name": "pplx-7b-online", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0.28" }, "request": { "unit": "per_request", "price": "0.005" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "request": "truefoundry" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 4096, "max_output_tokens": 4096, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "perplexity/pplx-embed-v1-0.6b", "model_name": "pplx-embed-v1-0.6b", "display_name": "pplx-embed-v1-0.6b", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.004" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://docs.perplexity.ai/docs/embeddings/quickstart", "max_input_tokens": 32768, "model_type": "text_embedding", "capabilities": { "stream": true }, "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2026-02-26", "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "v0", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "perplexity/pplx-embed-v1-0.6b" ], "price_history": [ { "date": "2026-08-03", "kind": "limit", "new": "0", "note": "max_output_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "perplexity/pplx-embed-v1-4b", "model_name": "pplx-embed-v1-4b", "display_name": "pplx-embed-v1-4b", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.03" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "docs_url": "https://docs.perplexity.ai/docs/embeddings/quickstart", "max_input_tokens": 32768, "model_type": "text_embedding", "capabilities": { "stream": true }, "intro": "Embedding model for semantic search, retrieval, clustering, and ranking pipelines", "released_at": "2026-02-26", "max_output_tokens": 0, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "perplexity/pplx-embed-v1-4b" ], "price_history": [ { "date": "2026-08-03", "kind": "limit", "new": "0", "note": "max_output_tokens" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "perplexity/r1-1776", "model_name": "r1-1776", "display_name": "R1 1776", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "pydantic-prices+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "8" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "cross_checked" } } ], "intro": "R1 1776 is a version of DeepSeek-R1 that has been post-trained to remove censorship constraints related to topics restricted by the Chinese government. The model retains its original reasoning capabilities while providing direct responses to a wider range of queries. R1 1776 is an offline chat model that does not use the perplexity search subsystem.", "capabilities": { "reasoning": true, "vision": true }, "released_at": "2025-02-18", "max_input_tokens": 127072, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "perplexity/r1-1776" ], "intro_i18n": { "zh-CN": "R1-1776 是 DeepSeek R1 的后训练版本，旨在提供无审查、无偏见的真实信息。", "zh-TW": "R1-1776 是 DeepSeek R1 的後訓練版本，旨在提供未經審查、無偏見的事實資訊。", "ja-JP": "R1-1776は、DeepSeek R1のポストトレーニングバリアントで、検閲のない偏りのない事実情報を提供するよう設計されています。", "ru-RU": "R1-1776 — дообученный вариант DeepSeek R1, предназначенный для предоставления нецензурированной, объективной и достоверной информации." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "R1 1776" } ] }, { "slug": "perplexity/sonar", "model_name": "sonar", "display_name": "Sonar", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "provider_name": "Perplexity", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "1" }, "web_search": { "unit": "per_k_calls", "price": "8" }, "request": { "unit": "per_k_calls", "price": "12" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0625" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "request": "pydantic-prices", "cache_read": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.25" }, "message": "prompt from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from truefoundry conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "8" }, "discarded_charge": { "unit": "per_k_calls", "price": "5" }, "message": "web_search from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "pydantic-prices", "charge": "request", "selected_charge": { "unit": "per_k_calls", "price": "12" }, "discarded_charge": { "unit": "per_request", "price": "0.005" }, "message": "request from helicone-registry conflicts with pydantic-prices; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "perplexity/sonar" } ], "intro": "Fast web-grounded Sonar for current answers, citations, and lightweight retrieval", "released_at": "2024-01-01", "knowledge_cutoff": "2025-09", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "sonar", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "model_type": "text_generation", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "response_format", "stop", "temperature", "top_p" ] }, "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "perplexity/sonar" ], "intro_i18n": { "zh-CN": "Perplexity 的轻量级产品，具备搜索支撑，速度更快、成本更低于 Sonar Pro。", "zh-TW": "Perplexity 的輕量產品，具備搜尋依據，速度更快、成本更低於 Sonar Pro。", "ja-JP": "Perplexityの軽量製品で、検索に基づいた応答を提供し、Sonar Proよりも高速かつ低コストです。", "ru-RU": "Легковесный продукт с привязкой к поиску, быстрее и дешевле, чем Sonar Pro." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "perplexity/sonar-deep-research", "model_name": "sonar-deep-research", "display_name": "Perplexity Sonar Deep Research", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "provider_name": "Perplexity", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "8" }, "internal_reasoning": { "unit": "per_M_tokens", "price": "3" }, "web_search": { "unit": "per_k_calls", "price": "5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "internal_reasoning": "models-dev", "web_search": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_request", "price": "0.005" }, "message": "prompt from truefoundry conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Sonar search model for current answers, retrieval, and citation-backed chat", "released_at": "2025-02-01", "knowledge_cutoff": "2025-01", "max_input_tokens": 128000, "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "reasoning": true, "prompt_caching": true, "structured_output": true, "web_search": true, "stream": true }, "model_type": "deep_thinking", "family": "Sonar", "deprecated": true, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "perplexity/sonar-deep-research" ], "intro_i18n": { "zh-CN": "Deep Research 提供专家级的深度研究，并将其整合为易于理解和可操作的报告。", "zh-TW": "Deep Research 提供專業級的深入研究，並將其整合為易於理解與採取行動的報告。", "ja-JP": "Deep Research は、専門家レベルの包括的な調査を行い、それを分かりやすく実用的なレポートにまとめます。", "ru-RU": "Deep Research проводит всесторонние экспертные исследования и преобразует их в доступные и практичные отчеты." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "perplexity/sonar-medium-chat", "model_name": "sonar-medium-chat", "display_name": "sonar-medium-chat", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "1.8" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 16384, "max_output_tokens": 16384, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "perplexity/sonar-medium-online", "model_name": "sonar-medium-online", "display_name": "sonar-medium-online", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "1.8" }, "request": { "unit": "per_request", "price": "0.005" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "request": "truefoundry" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 12000, "max_output_tokens": 12000, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "perplexity/sonar-pro", "model_name": "sonar-pro", "display_name": "Sonar Pro", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "provider_name": "Perplexity", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "request": { "unit": "per_k_calls", "price": "14" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "request": "pydantic-prices" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "10" }, "discarded_charge": { "unit": "per_k_calls", "price": "6" }, "message": "web_search from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "pydantic-prices", "charge": "request", "selected_charge": { "unit": "per_k_calls", "price": "14" }, "discarded_charge": { "unit": "per_request", "price": "0.006" }, "message": "request from helicone-registry conflicts with pydantic-prices; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Deeper Sonar search model with broader retrieval and stronger synthesis", "released_at": "2024-01-01", "knowledge_cutoff": "2025-09", "max_input_tokens": 200000, "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "sonar-pro", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "model_type": "vision_understanding", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "response_format", "stop", "temperature", "top_p" ] }, "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "perplexity/sonar-pro" ], "intro_i18n": { "zh-CN": "Perplexity 的旗舰产品，具备搜索支撑，支持高级查询和追问。", "zh-TW": "Perplexity 的旗艦產品，具備搜尋依據，支援進階查詢與後續提問。", "ja-JP": "Perplexityの主力製品で、検索に基づいた高度なクエリやフォローアップに対応します。", "ru-RU": "Флагманский продукт Perplexity с привязкой к поиску, поддерживающий сложные запросы и уточнения." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "perplexity/sonar-pro-search", "model_name": "sonar-pro-search", "display_name": "Sonar Pro Search", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "pydantic-prices", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" } }, "provenance": { "base_charges": { "prompt": "pydantic-prices", "completion": "pydantic-prices" }, "verification_status": "aggregator_only" } } ], "intro": "Sonar Pro Search is Perplexity's advanced agentic search system for deeper reasoning and analysis.", "capabilities": { "vision": true, "reasoning": true, "structured_output": true, "pdf_input": true }, "released_at": "2025-10-30", "max_input_tokens": 200000, "max_output_tokens": 8000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "sonar-pro", "model_type": "deep_thinking", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "structured_outputs", "temperature", "top_k", "top_p", "web_search_options" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "perplexity/sonar-pro-search" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Perplexity: Sonar Pro Search" } ] }, { "slug": "perplexity/sonar-reasoning", "model_name": "sonar-reasoning", "display_name": "sonar-reasoning", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+pydantic-prices+helicone-registry+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "5" }, "web_search": { "unit": "per_k_calls", "price": "8" }, "request": { "unit": "per_k_calls", "price": "12" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "web_search": "litellm", "request": "pydantic-prices" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "8" }, "discarded_charge": { "unit": "per_k_calls", "price": "5" }, "message": "web_search from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "pydantic-prices", "charge": "request", "selected_charge": { "unit": "per_k_calls", "price": "12" }, "discarded_charge": { "unit": "per_request", "price": "0.005" }, "message": "request from helicone-registry conflicts with pydantic-prices; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 128000, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "structured_output": true, "web_search": true, "stream": true }, "intro": "Sonar Reasoning is a reasoning model provided by Perplexity based on DeepSeek R1.", "knowledge_cutoff": "2025-01", "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "parameters": { "supported": [ "frequency_penalty", "max_tokens", "reasoning", "response_format", "stop", "temperature", "top_p" ] }, "released_at": "2025-01-21", "family": "sonar-reasoning", "deprecated": true, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "perplexity/sonar-reasoning" ], "intro_i18n": { "zh-CN": "专注推理的模型，输出详细的搜索支撑解释和思维链。", "zh-TW": "一款專注推理的模型，輸出具詳細搜尋依據的思考鏈（CoT）解釋。", "ja-JP": "詳細な検索に基づく説明を伴う思考の連鎖（CoT）を出力する推論特化モデルです。", "ru-RU": "Модель, ориентированная на рассуждение, выводящая цепочку мыслей с подробными объяснениями, основанными на поиске." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "perplexity/sonar-reasoning-pro", "model_name": "sonar-reasoning-pro", "display_name": "Sonar Reasoning Pro", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "provider_name": "Perplexity", "official": true, "source": "models-dev+litellm+pydantic-prices+truefoundry+helicone-registry+computeprices+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "8" }, "web_search": { "unit": "per_k_calls", "price": "10" }, "request": { "unit": "per_k_calls", "price": "14" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "web_search": "litellm", "request": "pydantic-prices" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "pydantic-prices", "charge": "request", "selected_charge": { "unit": "per_k_calls", "price": "14" }, "discarded_charge": { "unit": "per_request", "price": "0.006" }, "message": "request from truefoundry conflicts with pydantic-prices; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "10" }, "discarded_charge": { "unit": "per_k_calls", "price": "6" }, "message": "web_search from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "pydantic-prices", "charge": "request", "selected_charge": { "unit": "per_k_calls", "price": "14" }, "discarded_charge": { "unit": "per_request", "price": "0.006" }, "message": "request from helicone-registry conflicts with pydantic-prices; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Web-grounded Sonar for multi-step research questions that need cited reasoning", "released_at": "2024-01-01", "knowledge_cutoff": "2025-09", "max_input_tokens": 128000, "max_output_tokens": 4096, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "sonar-reasoning", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "model_type": "deep_thinking", "parameters": { "supported": [ "frequency_penalty", "max_tokens", "reasoning", "response_format", "stop", "temperature", "top_p" ] }, "deprecated": true, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "perplexity/sonar-reasoning-pro" ], "intro_i18n": { "zh-CN": "专注推理的高级模型，输出带搜索增强的思维链，每次请求可包含多个搜索查询。", "zh-TW": "一款專注推理的進階模型，輸出包含增強搜尋的思考鏈（CoT），每次請求可包含多個搜尋查詢。", "ja-JP": "強化された検索機能を備えた高度な推論特化モデル。1リクエストあたり複数の検索クエリを含むCoT（思考の連鎖）を出力します。", "ru-RU": "Продвинутая модель, ориентированная на рассуждение, выводящая цепочку мыслей с расширенным поиском, включая несколько поисковых запросов на один запрос." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "perplexity/sonar-small-chat", "model_name": "sonar-small-chat", "display_name": "sonar-small-chat", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.07" }, "completion": { "unit": "per_M_tokens", "price": "0.28" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 16384, "max_output_tokens": 16384, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "perplexity/sonar-small-online", "model_name": "sonar-small-online", "display_name": "sonar-small-online", "vendor": "perplexity", "pricing": [ { "provider": "perplexity", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0.28" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 12000, "max_output_tokens": 12000, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "sensenova/sensenova-6.7-flash-lite", "model_name": "sensenova-6.7-flash-lite", "display_name": "SenseNova 6.7 Flash Lite", "vendor": "sensenova", "pricing": [ { "provider": "sensenova", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-05-08", "max_input_tokens": 262144, "max_output_tokens": 65536, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "一款为真实工作流设计的轻量级多模态代理模型，支持基于文本的对话和图像理解。轻量高效，平衡性能、成本和可部署性。原生多模态架构，支持图像理解，包括OCR和图表解析。针对办公和生产力场景进行了增强，稳定支持复杂的长链任务。改进了令牌效率，为复杂工作负载提供更好的成本控制。上下文长度为256K令牌（最大输入：252K，最大输出：64K）。", "zh-TW": "一款為現實工作流程設計的輕量級多模態代理模型，支持基於文本的對話和圖像理解。輕量高效，平衡性能、成本和可部署性。原生多模態架構，支持圖像理解，包括 OCR 和圖表解讀。針對辦公和生產力場景進行增強，穩定支持複雜的長鏈任務。改進的令牌效率，實現對複雜工作負載的更好成本控制。上下文長度為 256K 令牌（最大輸入：252K，最大輸出：64K）。", "ja-JP": "現実世界のワークフロー向けに設計された軽量マルチモーダルエージェントモデルで、テキストベースの会話と画像理解の両方をサポートします。軽量かつ効率的で、性能、コスト、展開性のバランスを実現しています。画像理解を含むネイティブマルチモーダルアーキテクチャで、OCRやチャート解釈をサポートします。オフィスや生産性シナリオ向けに強化されており、複雑な長鎖タスクを安定してサポートします。トークン効率が向上し、複雑なワークロードのコスト管理が可能です。コンテキスト長は256Kトークン（最大入力: 252K、最大出力: 64K）。", "ru-RU": "Легковесная мультимодальная модель-агент, разработанная для рабочих процессов в реальном мире, поддерживающая как текстовые беседы, так и понимание изображений. Легкая и эффективная, сбалансированная по производительности, стоимости и возможностям развертывания. Родная мультимодальная архитектура с поддержкой понимания изображений, включая OCR и интерпретацию диаграмм. Улучшена для офисных и производственных сценариев, со стабильной поддержкой сложных задач с длинной цепочкой. Повышена эффективность токенов, что позволяет лучше контролировать затраты на сложные рабочие нагрузки. Контекстная длина составляет 256K токенов (максимальный ввод: 252K, максимальный вывод: 64K)." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "SenseNova 6.7 Flash Lite" } ] }, { "slug": "sensenova/sensenova-u1-fast", "model_name": "sensenova-u1-fast", "display_name": "SenseNova U1 Fast", "vendor": "sensenova", "pricing": [ { "provider": "sensenova", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-05-08", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "基于SenseNova U1的加速版本，专为信息图生成进行了优化。", "zh-TW": "基於 SenseNova U1 的加速版本，專為信息圖生成進行了優化。", "ja-JP": "SenseNova U1をベースにした高速版で、特にインフォグラフィック生成に最適化されています。", "ru-RU": "Ускоренная версия на основе SenseNova U1, специально оптимизированная для генерации инфографики." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "SenseNova U1 Fast" } ] }, { "slug": "stepfun/step-1-256k", "model_name": "step-1-256k", "display_name": "Step 1 256K", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "2.794118" }, "prompt": { "unit": "per_M_tokens", "price": "13.970588" }, "completion": { "unit": "per_M_tokens", "price": "44.117647" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 256000, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "支持超长上下文，适合长文档分析。", "zh-TW": "支援超長上下文，適合長文檔分析。", "ja-JP": "超長文コンテキスト処理に対応し、長文ドキュメントの分析に最適です。", "ru-RU": "Обработка сверхдлинного контекста, идеально подходит для анализа длинных документов." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Step 1 256K" } ] }, { "slug": "stepfun/step-1-32k", "model_name": "step-1-32k", "display_name": "Step 1 (32K)", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "provider_name": "StepFun (China)", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.05" }, "completion": { "unit": "per_M_tokens", "price": "9.59" }, "cache_read": { "unit": "per_M_tokens", "price": "0.41" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.41" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2.05" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "9.59" }, "discarded_charge": { "unit": "per_M_tokens", "price": "70", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "released_at": "2025-01-01", "knowledge_cutoff": "2024-06", "max_input_tokens": 32768, "max_output_tokens": 32768, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "stream": true, "web_search": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "支持中等长度对话，适用于多种场景。", "zh-TW": "支援中等長度對話，適用於多種場景。", "ja-JP": "中程度の長さの会話を幅広いシナリオでサポートします。", "ru-RU": "Поддержка диалогов средней длины для широкого круга задач." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "stepfun/step-1-8k", "model_name": "step-1-8k", "display_name": "Step 1 8K", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.147059" }, "prompt": { "unit": "per_M_tokens", "price": "0.735294" }, "completion": { "unit": "per_M_tokens", "price": "2.941176" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 8000, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "小型模型，适合轻量级任务。", "zh-TW": "小型模型，適合輕量任務。", "ja-JP": "軽量なタスクに適した小型モデルです。", "ru-RU": "Небольшая модель, подходящая для легких задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Step 1 8K" } ] }, { "slug": "stepfun/step-1o-turbo-vision", "model_name": "step-1o-turbo-vision", "display_name": "Step 1o Turbo Vision", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.073529" }, "prompt": { "unit": "per_M_tokens", "price": "0.367647" }, "completion": { "unit": "per_M_tokens", "price": "1.176471" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-02-14", "max_input_tokens": 32000, "model_type": "vision_understanding", "capabilities": { "vision": true, "video_input": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "图像理解能力强，在数学与编程方面优于 1o。体积更小，输出更快。", "zh-TW": "具備強大圖像理解能力，在數學與程式碼任務上超越 1o。體積更小，輸出更快。", "ja-JP": "画像理解に優れ、数学やコーディングで 1o を上回る性能を発揮します。1o より小型で出力も高速です。", "ru-RU": "Продвинутое понимание изображений, превосходит 1o в математике и программировании. Меньше по размеру и быстрее по скорости вывода." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Step 1o Turbo Vision" } ] }, { "slug": "stepfun/step-1o-vision-32k", "model_name": "step-1o-vision-32k", "display_name": "Step 1o Vision 32K", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.441176" }, "prompt": { "unit": "per_M_tokens", "price": "2.205882" }, "completion": { "unit": "per_M_tokens", "price": "0.088235" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-01-22", "max_input_tokens": 32000, "model_type": "vision_understanding", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "图像理解能力强，视觉表现优于 Step-1V 系列。", "zh-TW": "具備強大圖像理解能力，視覺表現優於 Step-1V 系列。", "ja-JP": "Step-1V シリーズよりも優れた視覚性能を持つ画像理解モデルです。", "ru-RU": "Продвинутое понимание изображений с лучшей визуальной производительностью, чем серия Step-1V." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Step 1o Vision 32K" } ] }, { "slug": "stepfun/step-1v-32k", "model_name": "step-1v-32k", "display_name": "Step 1V 32K", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.441176" }, "prompt": { "unit": "per_M_tokens", "price": "2.205882" }, "completion": { "unit": "per_M_tokens", "price": "0.088235" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "web_search": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "支持视觉输入，实现更丰富的多模态交互。", "zh-TW": "支援視覺輸入，實現更豐富的多模態互動。", "ja-JP": "視覚入力に対応し、より豊かなマルチモーダル対話を実現します。", "ru-RU": "Поддержка визуального ввода для более насыщенного мультимодального взаимодействия." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Step 1V 32K" } ] }, { "slug": "stepfun/step-1v-8k", "model_name": "step-1v-8k", "display_name": "Step 1V 8K", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.147059" }, "prompt": { "unit": "per_M_tokens", "price": "0.735294" }, "completion": { "unit": "per_M_tokens", "price": "0.029412" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 8000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "web_search": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "小型视觉模型，适用于基础图文任务。", "zh-TW": "小型視覺模型，適用於基本圖文任務。", "ja-JP": "基本的な画像とテキストのタスクに対応する小型ビジョンモデルです。", "ru-RU": "Небольшая визуальная модель для базовых задач с изображениями и текстом." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Step 1V 8K" } ] }, { "slug": "stepfun/step-1x-edit", "model_name": "step-1x-edit", "display_name": "Step 1X Edit", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-03-04", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "专注于图像编辑的模型，可根据用户提供的图像与文本进行修改与增强。支持多种输入格式，包括文本描述与示例图像，生成符合用户意图的编辑结果。", "zh-TW": "此模型專注於圖像編輯，可根據使用者提供的圖像與文字進行修改與增強。支援多種輸入格式，包括文字描述與範例圖像，並生成符合使用者意圖的編輯結果。", "ja-JP": "このモデルは画像編集に特化しており、ユーザーが提供した画像やテキストに基づいて画像を修正・強化します。テキスト説明や例示画像など複数の入力形式に対応し、ユーザーの意図に沿った編集を生成します。", "ru-RU": "Модель для редактирования изображений, модифицирует и улучшает изображения на основе текста и примеров. Поддерживает различные форматы ввода и генерирует правки в соответствии с намерением пользователя." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Step 1X Edit" } ] }, { "slug": "stepfun/step-1x-medium", "model_name": "step-1x-medium", "display_name": "Step 1X Medium", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.014706" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-07-15", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "具备强大图像生成能力，支持中文提示输入，能更好理解中文语义并转化为视觉特征，实现高分辨率、高质量图像生成，并支持一定程度的风格迁移。", "zh-TW": "此模型具備強大的文字提示圖像生成能力。原生支援中文，能更好理解中文描述並轉化為視覺特徵，實現更準確的生成。可產出高解析度、高品質圖像，並支援一定程度的風格轉換。", "ja-JP": "このモデルはテキストプロンプトによる強力な画像生成を提供します。中国語にネイティブ対応しており、中国語の記述をより正確に理解し、意味を視覚的特徴に変換して高解像度・高品質な画像を生成します。スタイル変換にも一定の対応があります。", "ru-RU": "Модель с мощной генерацией изображений по текстовому описанию. Благодаря поддержке китайского языка, лучше понимает и визуализирует китайские описания. Генерирует изображения высокого разрешения и качества, поддерживает перенос стиля." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Step 1X Medium" } ] }, { "slug": "stepfun/step-2-16k", "model_name": "step-2-16k", "display_name": "Step 2 (16K)", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "provider_name": "StepFun (China)", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5.21" }, "completion": { "unit": "per_M_tokens", "price": "16.44" }, "cache_read": { "unit": "per_M_tokens", "price": "1.04" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "1.04" }, "discarded_charge": { "unit": "per_M_tokens", "price": "7.6", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "5.21" }, "discarded_charge": { "unit": "per_M_tokens", "price": "38", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "16.44" }, "discarded_charge": { "unit": "per_M_tokens", "price": "120", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "released_at": "2025-01-01", "knowledge_cutoff": "2024-06", "max_input_tokens": 16384, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "stream": true, "web_search": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "支持大上下文交互，适用于复杂对话。", "zh-TW": "支援大上下文互動，適合複雜對話場景。", "ja-JP": "複雑な対話に対応する大規模コンテキスト処理をサポートします。", "ru-RU": "Поддержка взаимодействия с большим контекстом для сложных диалогов." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "stepfun/step-2-16k-exp", "model_name": "step-2-16k-exp", "display_name": "Step 2 16K Exp", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "1.117647" }, "prompt": { "unit": "per_M_tokens", "price": "5.588235" }, "completion": { "unit": "per_M_tokens", "price": "17.647059" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-01-15", "max_input_tokens": 16000, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "step", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Step-2 实验版本，包含最新功能与持续更新。不建议用于生产环境。", "zh-TW": "Step-2 實驗版本，具備最新功能與持續更新。不建議用於生產環境。", "ja-JP": "最新機能と継続的なアップデートを備えた Step-2 の実験的ビルドです。本番環境での使用は推奨されません。", "ru-RU": "Экспериментальная сборка Step-2 с новейшими функциями и обновлениями. Не рекомендуется для продакшена." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Step 2 16K Exp" } ] }, { "slug": "stepfun/step-2-mini", "model_name": "step-2-mini", "display_name": "Step 2 Mini", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.029412" }, "prompt": { "unit": "per_M_tokens", "price": "0.147059" }, "completion": { "unit": "per_M_tokens", "price": "0.294118" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-01-14", "max_input_tokens": 8000, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "step", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "基于下一代自研 MFA 注意力架构构建，在大幅降低成本的同时实现 Step-1 级别效果，具备更高吞吐与更低延迟，适用于通用任务，编程能力强。", "zh-TW": "基於新一代自研 MFA 注意力架構，提供類似 Step-1 的效能，成本更低、吞吐更高、延遲更低。具備強大程式能力，適用於通用任務。", "ja-JP": "次世代の社内開発 MFA アテンションアーキテクチャに基づき、Step-1 に近い性能を大幅に低コストで実現し、高スループットと低レイテンシを達成します。一般的なタスクに対応し、コーディング能力にも優れています。", "ru-RU": "Построена на архитектуре MFA следующего поколения, обеспечивает производительность уровня Step-1 при значительно меньших затратах, с высокой пропускной способностью и низкой задержкой. Отлично справляется с общими задачами и программированием." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Step 2 Mini" } ] }, { "slug": "stepfun/step-2x-large", "model_name": "step-2x-large", "display_name": "Step 2X Large", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2024-08-07", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "新一代 StepFun 图像模型，专注于图像生成，可根据文本提示生成高质量图像，具备更真实的纹理与更强的中英文文本渲染能力。", "zh-TW": "新一代 StepFun 圖像模型，專注於文字提示圖像生成，能產出高品質圖像，具備更真實的質感與更強的中英文文字渲染能力。", "ja-JP": "StepFun による次世代画像生成モデルで、テキストプロンプトから高品質な画像を生成します。よりリアルな質感と強力な中英テキスト描画能力を備えています。", "ru-RU": "Модель нового поколения StepFun для генерации изображений, создает изображения высокого качества по текстовому описанию. Обеспечивает реалистичную текстуру и качественную отрисовку текста на китайском и английском языках." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Step 2X Large" } ] }, { "slug": "stepfun/step-3", "model_name": "step-3", "display_name": "Step 3", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.044118" }, "prompt": { "unit": "per_M_tokens", "price": "0.220588" }, "completion": { "unit": "per_M_tokens", "price": "0.588235" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "tracks": [ { "label": "Context >4K", "source": "lobehub-modelbank", "charge_sources": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" } }, { "label": "Base pricing", "source": "lobehub-modelbank", "charge_sources": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Context >4K", "factor": "1", "charge_factors": { "cache_read": "2.666667", "prompt": "2.666667", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 4000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 64000, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "reasoning": true, "vision": true, "pdf_input": true, "prompt_caching": true, "open_weights": true, "stream": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-07-31", "max_output_tokens": 8192, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "step", "knowledge_cutoff": "2025-01", "deprecated": true, "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "stepfun/step-3" ], "intro_i18n": { "zh-CN": "该模型具备强大的视觉感知与复杂推理能力，能准确处理跨领域知识理解、数学与视觉交叉分析及多种日常视觉分析任务。", "zh-TW": "此模型具備強大的視覺感知與複雜推理能力，能準確處理跨領域知識理解、數學與視覺交叉分析，以及多種日常視覺分析任務。", "ja-JP": "このモデルは優れた視覚認識と複雑な推論能力を持ち、分野横断的な知識理解、数学と視覚の複合分析、日常的な視覚分析タスクに正確に対応します。", "ru-RU": "Модель с мощным визуальным восприятием и сложным логическим выводом, точно обрабатывает знания из разных областей, анализ математики и изображений, а также широкий спектр повседневных визуальных задач." }, "price_history": [ { "date": "2026-08-10", "kind": "delisted", "note": "deprecated" }, { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-08-03", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-07-15", "kind": "limit", "old": "64000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Step 3" } ] }, { "slug": "stepfun/step-3.5-flash", "model_name": "step-3.5-flash", "display_name": "Step 3.5 Flash", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "provider_name": "StepFun (China)", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.02" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.096" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.288" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.02" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.019" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.02" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.14", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.7", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.1", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "StepFun flash lane for quick multimodal reasoning and coding assistance", "released_at": "2026-01-29", "knowledge_cutoff": "2025-01", "max_input_tokens": 256000, "max_output_tokens": 256000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "web_search": true }, "model_type": "deep_thinking", "family": "step", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "reasoning", "temperature", "tool_choice", "tools", "top_k", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "step-3-5-flash", "stepfun-ai/Step-3.5-Flash", "stepfun-ai/step-3.5-flash", "stepfun/step-3.5-flash", "stepfun/step-3.5-flash:free" ], "intro_i18n": { "zh-CN": "Stepfun 的旗舰语言推理模型。该模型具备顶级的推理能力和快速可靠的执行能力。能够分解和规划复杂任务，快速可靠地调用工具执行任务，并胜任逻辑推理、数学、软件工程和深入研究等各种复杂任务。", "zh-TW": "Stepfun 的旗艦語言推理模型。該模型具備頂級推理能力及快速可靠的執行能力。能分解並規劃複雜任務，快速可靠地調用工具執行任務，並勝任邏輯推理、數學、軟件工程及深入研究等各種複雜任務。", "ja-JP": "Stepfunのフラッグシップ言語推論モデル。このモデルは、トップクラスの推論能力と迅速かつ信頼性の高い実行能力を備えています。複雑なタスクを分解して計画し、ツールを迅速かつ確実に呼び出してタスクを実行し、論理推論、数学、ソフトウェアエンジニアリング、深い研究などのさまざまな複雑なタスクに対応できます。", "ru-RU": "Флагманская модель языкового рассуждения от Stepfun. Эта модель обладает первоклассными возможностями рассуждения и быстрой и надёжной способностью выполнения задач. Она способна разбирать и планировать сложные задачи, быстро и надёжно вызывать инструменты для выполнения задач, а также справляться с различными сложными задачами, такими как логическое рассуждение, математика, разработка программного обеспечения и углублённые исследования." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "stepfun/step-3.5-flash-2603", "model_name": "step-3.5-flash-2603", "display_name": "Step 3.5 Flash 2603", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "provider_name": "StepFun (China)", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.1" }, "completion": { "unit": "per_M_tokens", "price": "0.3" }, "cache_read": { "unit": "per_M_tokens", "price": "0.02" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.02" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.14", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.7", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.1", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "StepFun flash model for efficient multimodal reasoning, coding, and tool use", "released_at": "2026-04-02", "knowledge_cutoff": "2025-01", "max_input_tokens": 256000, "max_output_tokens": 256000, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "web_search": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "step-3-5-flash-2603", "stepfun-ai/step-3.5-flash-2603", "stepfun/step-3.5-flash-2603" ], "intro_i18n": { "zh-CN": "基于 Step 3.5 Flash 打造，并针对高频 Agent 场景优化，进一步提升 token 效率与推理速度，同时保留旗舰级推理与工具调用能力。支持切换至低推理模式以降低资源消耗，并对编码任务与 Agent 框架进行专项优化。", "zh-TW": "基於 Step 3.5 Flash 打造並針對高頻代理場景優化，進一步提升 token 效率與推理速度，同時保留旗艦級推理與工具調用能力。也支援切換至低推理模式以降低資源消耗，並針對程式任務與代理框架進行相容性優化。", "ja-JP": "Step 3.5 Flashを基盤とし、高頻度エージェントシナリオ向けに最適化されており、トークン効率と推論速度をさらに向上させています。フラッグシップレベルの推論とツール呼び出し能力を維持しながら、リソース消費を削減するために低推論モードへの切り替えをサポートします。また、コーディングタスクとエージェントフレームワークとの互換性を向上させるためのターゲット最適化が行われています。", "ru-RU": "Создана на базе Step 3.5 Flash и оптимизирована для высокочастотных агентных сценариев. Улучшает эффективность токенов и скорость инференции, сохраняя флагманский уровень рассуждений и вызова инструментов. Поддерживает переключение в режим с низким уровнем рассуждений для снижения расходов. Также добавлены оптимизации для повышения совместимости с задачами программирования и агентными фреймворками." }, "price_history": [ { "date": "2026-07-06", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "stepfun/step-3.7-flash", "model_name": "step-3.7-flash", "display_name": "Step 3.7 Flash", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "provider_name": "StepFun (China)", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.185" }, "completion": { "unit": "per_M_tokens", "price": "1.11" }, "cache_read": { "unit": "per_M_tokens", "price": "0.037" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.037" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.27", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.185" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.35", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "1.11" }, "discarded_charge": { "unit": "per_M_tokens", "price": "8.1", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Newer StepFun flash model for faster agents, coding, and multimodal prompts", "released_at": "2026-05-29", "knowledge_cutoff": "2026-03", "max_input_tokens": 256000, "max_output_tokens": 256000, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "web_search": true }, "model_type": "deep_thinking", "family": "step", "benchmarks": { "intelligence_index": 30.9, "coding_index": 39.6, "agentic_index": 21.7 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "reasoning_effort", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "Step-3.7-Flash", "novita/stepfun/step-3.7-flash", "step-3-7-flash", "step-3.7-flash:free", "stepfun-ai/Step-3.7-Flash", "stepfun-ai/step-3.7-flash", "stepfun/step-3.7-flash", "stepfun/step-3.7-flash-free", "stepfun/step-3.7-flash:free", "stepfun/step-3.7-flash:thinking" ], "intro_i18n": { "zh-CN": "StepFun的旗舰多模态推理模型。基于step-3.5-flash的高速推理和工具调用能力，增加了原生多模态输入支持，能够直接理解图像和视频内容，无需依赖视觉MCP或额外的视觉模型。该模型支持三种推理级别（低/中/高），是代理工作流、编码任务和多模态应用的快速可靠选择。", "zh-TW": "StepFun 的旗艦多模態推理模型。基於 step-3.5-flash 的高速推理和工具調用能力，增加了原生多模態輸入支持，能直接理解影像和視頻內容，而無需依賴視覺 MCP 或額外的視覺模型。該模型支持三種推理級別（低/中/高），是代理工作流、編程任務和多模態應用的快速可靠選擇。", "ja-JP": "StepFunのフラッグシップマルチモーダル推論モデルです。step-3.5-flashの高速推論およびツール呼び出し機能を基盤に、ネイティブなマルチモーダル入力サポートを追加し、視覚MCPや追加のビジョンモデルに依存せずに画像や動画コンテンツを直接理解できます。このモデルは3つの推論レベル（低/中/高）をサポートし、エージェントワークフロー、コーディングタスク、マルチモーダルアプリケーションにおいて迅速かつ信頼性の高い選択肢です。", "ru-RU": "Флагманская мультимодальная модель рассуждений от StepFun. Основываясь на высокоскоростных возможностях рассуждений и вызова инструментов step-3.5-flash, она добавляет поддержку нативного мультимодального ввода, позволяя напрямую понимать изображения и видео без использования визуальных MCP или дополнительных моделей визуализации. Модель поддерживает три уровня рассуждений (низкий / средний / высокий), что делает её быстрым и надёжным выбором для агентных рабочих процессов, задач кодирования и мультимодальных приложений." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.200696615", "new": "1.201081041" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.2001161025", "new": "0.2001801735" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.200884373", "new": "1.200696615" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.2001473955", "new": "0.2001161025" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.200786768", "new": "1.200884373" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.200131128", "new": "0.2001473955" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.200423159", "new": "1.200786768" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.2000705265", "new": "0.200131128" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.200336003", "new": "1.200423159" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.2000560005", "new": "0.2000705265" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.200467628", "new": "1.200336003" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.200077938", "new": "0.2000560005" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.200487068", "new": "1.200467628" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.200081178", "new": "0.200077938" }, { "date": "2026-08-08", "kind": "price", "provider": "zenmux", "charge": "cache_read", "old": "0.02700708", "new": "0.04" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.200393513", "new": "1.200487068" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.2000655855", "new": "0.200081178" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.198669914", "new": "1.200393513" }, { "date": "2026-08-06", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.199778319", "new": "0.2000655855" }, { "date": "2026-08-05", "kind": "price", "provider": "moark", "charge": "completion", "old": "1.199434635", "new": "1.198669914" } ] }, { "slug": "stepfun/step-image-edit-2", "model_name": "step-image-edit-2", "display_name": "Step Image Edit 2", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.002941" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-04-28", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Stepfun 最新迭代的轻量级编辑模型，支持文本生成图像和图像编辑于一体。尽管参数少于 60 亿，但在其规模内实现了最先进的性能，可与 120 亿至 200 亿参数范围的开源模型相媲美。每个编辑任务仅需 1-2 秒，重新定义了实时交互式图像编辑体验。", "zh-TW": "Stepfun 最新迭代推出的輕量級編輯模型，支持文本生成圖像和圖像編輯，集成於單一模型中。儘管參數少於 60 億，但在其規模內實現了最先進的性能，與 12B–20B 參數範圍的開源模型相媲美。每個編輯任務僅需 1–2 秒，重新定義了實時交互式圖像編輯的體驗。", "ja-JP": "Stepfunの最新バージョンからの軽量編集モデルで、単一モデル内でテキストから画像生成と画像編集の両方をサポートします。6億未満のパラメータでありながら、12B〜20Bパラメータ範囲のオープンソースモデルに匹敵する性能を達成し、各編集タスクはわずか1〜2秒で完了します。リアルタイムのインタラクティブ画像編集体験を再定義します。", "ru-RU": "Легковесная модель редактирования от последней итерации Stepfun, поддерживающая как генерацию изображений по тексту, так и редактирование изображений в рамках одной модели. Несмотря на менее чем 6 миллиардов параметров, она достигает передовых результатов на своем уровне, соперничая с открытыми моделями в диапазоне 12–20 миллиардов параметров. Каждая задача редактирования занимает всего 1–2 секунды, переопределяя опыт интерактивного редактирования изображений в реальном времени." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Step Image Edit 2" } ] }, { "slug": "stepfun/step-r1-v-mini", "model_name": "step-r1-v-mini", "display_name": "Step R1 V Mini", "vendor": "stepfun", "pricing": [ { "provider": "stepfun", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.073529" }, "prompt": { "unit": "per_M_tokens", "price": "0.367647" }, "completion": { "unit": "per_M_tokens", "price": "1.176471" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 100000, "model_type": "deep_thinking", "capabilities": { "reasoning": true, "vision": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2024-01-01", "max_output_tokens": 65536, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "step", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "具备强图像理解能力的推理模型，可处理图像与文本，并在深度推理后生成文本。擅长视觉推理，在数学、编程与文本推理方面表现出色，支持 100K 上下文窗口。", "zh-TW": "具備強大圖像理解能力的推理模型，能處理圖像與文字，並在深度推理後生成文字。擅長視覺推理，在數學、程式碼與文字推理方面表現頂尖，支援 100K 上下文。", "ja-JP": "画像理解に優れた推論モデルで、画像とテキストを処理し、深い推論を経てテキストを生成します。視覚的推論に強く、数学、コーディング、テキスト推論において最高水準の性能を発揮し、100K のコンテキストウィンドウに対応します。", "ru-RU": "Модель логического вывода с продвинутым пониманием изображений, способна обрабатывать изображения и текст, а затем генерировать текст после глубокого анализа. Отлично справляется с визуальной логикой, математикой, программированием и текстовыми задачами, поддерживает контекст до 100K." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Step R1 V Mini" } ] }, { "slug": "upstage/solar-pro2", "model_name": "solar-pro2", "display_name": "solar-pro2", "vendor": "upstage", "pricing": [ { "provider": "upstage", "provider_name": "Upstage", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Flagship model for demanding analysis, coding, and production agent workflows", "released_at": "2025-05-20", "knowledge_cutoff": "2025-03", "max_input_tokens": 65536, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "solar-pro", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "stream": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "upstage/solar-pro2" ], "price_history": [ { "date": "2026-08-12", "kind": "listed", "note": "solar-pro2" } ] }, { "slug": "upstage/solar-pro3", "model_name": "solar-pro3", "display_name": "solar-pro3", "vendor": "upstage", "pricing": [ { "provider": "upstage", "provider_name": "Upstage", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.25" }, "completion": { "unit": "per_M_tokens", "price": "0.25" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev" }, "verification_status": "cross_checked" } } ], "intro": "Flagship model for demanding analysis, coding, and production agent workflows", "released_at": "2026-01", "knowledge_cutoff": "2025-03", "max_input_tokens": 131072, "max_output_tokens": 8192, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "solar-pro", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "stream": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "upstage/solar-pro3" ], "price_history": [ { "date": "2026-08-12", "kind": "listed", "note": "solar-pro3" } ] }, { "slug": "upstage/solar-pro4", "model_name": "solar-pro4", "display_name": "Solar Pro 4", "vendor": "upstage", "pricing": [ { "provider": "upstage", "provider_name": "Upstage", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "1.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.06" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Upstage's flagship model, specialized for agentic use", "released_at": "2026-08-06", "knowledge_cutoff": "2026-02", "max_input_tokens": 524288, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "solar-pro", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true }, "benchmarks": { "intelligence_index": 41.6, "coding_index": 52.7, "agentic_index": 33.6 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "response_format", "structured_outputs", "temperature", "tool_choice", "tools", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "upstage/solar-pro4", "upstage/solar-pro4:thinking" ], "model_type": "deep_thinking", "price_history": [ { "date": "2026-08-11", "kind": "listed", "note": "Solar Pro 4" } ] }, { "slug": "xai/grok-2", "model_name": "grok-2", "display_name": "grok-2", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "xai/grok-2" ], "intro_i18n": { "zh-CN": "Grok 2 是一款前沿模型，具备先进的推理能力，强大的对话、编程和推理表现，在 LMSYS 排名中优于 Claude 3.5 Sonnet 和 GPT-4 Turbo。", "zh-TW": "Grok 2 是前沿模型，具備最先進的推理能力，擅長聊天、編碼與推理，在 LMSYS 排名中超越 Claude 3.5 Sonnet 與 GPT-4 Turbo。", "ja-JP": "Grok 2は、最先端の推論力、優れたチャット、コーディング、推論性能を備えた先進モデルで、LMSYSにおいてClaude 3.5 SonnetやGPT-4 Turboを上回る評価を得ています。", "ru-RU": "Grok 2 — передовая модель с передовыми возможностями рассуждения, чата и программирования, превосходящая Claude 3.5 Sonnet и GPT-4 Turbo по LMSYS." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" } ] }, { "slug": "xai/grok-2-1212", "model_name": "grok-2-1212", "display_name": "grok-2-1212", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "x-ai/grok-2-1212" ] }, { "slug": "xai/grok-2-image", "model_name": "grok-2-image", "display_name": "grok-2-image", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "image_output": { "unit": "per_image", "price": "0.07" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "image_output": "truefoundry" }, "verification_status": "aggregator_only" } } ], "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-2-image" } ] }, { "slug": "xai/grok-2-image-1212", "model_name": "grok-2-image-1212", "display_name": "grok-2-image-1212", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "image_output": { "unit": "per_image", "price": "0.07" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "image_output": "truefoundry" }, "verification_status": "aggregator_only" } } ], "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-2-image-1212" } ] }, { "slug": "xai/grok-2-image-latest", "model_name": "grok-2-image-latest", "display_name": "grok-2-image-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "image_output": { "unit": "per_image", "price": "0.07" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "image_output": "truefoundry" }, "verification_status": "aggregator_only" } } ], "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-2-image-latest" } ] }, { "slug": "xai/grok-2-latest", "model_name": "grok-2-latest", "display_name": "grok-2-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "10" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "xai/grok-2-vision", "model_name": "grok-2-vision", "display_name": "grok-2-vision", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "image_input": { "unit": "per_image", "price": "0.000002" }, "cache_read": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm", "cache_read": "truefoundry" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "pdf_input": true, "web_search": true, "stream": true }, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2024-08-20", "knowledge_cutoff": "2024-08", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "xai/grok-2-vision" ], "intro_i18n": { "zh-CN": "Grok 2 Vision 擅长视觉任务，在视觉数学推理（MathVista）和文档问答（DocVQA）方面表现卓越，支持文档、图表、截图和照片等多种图像类型。", "zh-TW": "Grok 2 Vision 擅長視覺任務，在視覺數學推理（MathVista）與文件問答（DocVQA）上表現領先。可處理文件、圖表、截圖與照片。", "ja-JP": "Grok 2 Visionは視覚タスクに優れ、MathVistaによる視覚的数学推論やDocVQAによる文書QAで最先端の性能を発揮します。文書、チャート、グラフ、スクリーンショット、写真を処理可能です。", "ru-RU": "Grok 2 Vision превосходно справляется с визуальными задачами, демонстрируя передовые результаты в визуальном математическом рассуждении (MathVista) и вопросах по документам (DocVQA). Обрабатывает документы, диаграммы, графики, скриншоты и фотографии." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "xai/grok-2-vision-1212", "model_name": "grok-2-vision-1212", "display_name": "grok-2-vision-1212", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "image_input": { "unit": "per_image", "price": "0.000002" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 32768, "max_output_tokens": 32768, "deprecated": true, "model_type": "vision_understanding", "deprecation_date": "2026-02-28", "capabilities": { "vision": true, "function_calling": true, "pdf_input": true, "web_search": true, "image_output": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2024-12-12", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "x-ai/grok-2-vision-1212" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "xai/grok-2-vision-latest", "model_name": "grok-2-vision-latest", "display_name": "grok-2-vision-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "10" }, "image_input": { "unit": "per_image", "price": "0.000002" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "web_search": true }, "deprecated": true, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "xai/grok-3", "model_name": "grok-3", "display_name": "grok-3", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+helicone-registry+llmdb+pricetoken+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.75" }, "web_search": { "unit": "per_k_calls", "price": "25" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+helicone-registry+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "helicone-registry", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "25" }, "discarded_charge": { "unit": "per_k_calls", "price": "5" }, "message": "web_search from llmdb conflicts with helicone-registry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://x.ai/api#pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-05-15", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "intro": "Excels at enterprise use cases like data extraction, coding, and text summarization. Possesses deep domain knowledge in finance, healthcare, law, and science. Features function calling, structured outputs, and reasoning capabilities.", "knowledge_cutoff": "2024-06", "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "released_at": "2025-02-17", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "azure_ai/global/grok-3", "x-ai/grok-3", "xai/grok-3" ], "intro_i18n": { "zh-CN": "xAI 的 Grok 3 —— 具备强大推理能力的模型。", "zh-TW": "xAI Grok 3 —— 擁有強大推理能力。", "ja-JP": "xAIのGrok 3は、強力な推論能力を備えています。", "ru-RU": "Grok 3 от xAI — модель с высокой способностью к рассуждениям." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "xai/grok-3-beta", "model_name": "grok-3-beta", "display_name": "grok-3-beta", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.75" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://x.ai/api#pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "web_search": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "deprecated": true, "released_at": "2025-04-09", "knowledge_cutoff": "2024-11", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "x-ai/grok-3-beta" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "xai/grok-3-fast", "model_name": "grok-3-fast", "display_name": "Grok 3 Fast", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+llmdb", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.75" }, "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry+llmdb", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "5" }, "message": "prompt from llmdb conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "25" }, "message": "completion from llmdb conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.75" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.25" }, "message": "cache_read from llmdb conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 131072, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "stream": true, "vision": true }, "released_at": "2025-02-17", "knowledge_cutoff": "2024-11", "max_output_tokens": 8192, "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "xai/grok-3-fast" ], "intro_i18n": { "zh-CN": "xAI 的旗舰模型，擅长企业场景如数据提取、编程和摘要，具备金融、医疗、法律和科学等领域的深度知识。快速版本运行在更快的基础设施上，响应速度更快但每个 token 成本更高。", "zh-TW": "xAI 的旗艦模型，擅長企業應用如資料擷取、編碼與摘要，具備金融、醫療、法律與科學等領域的深度知識。快速版本運行於更快基礎設施，回應速度更快但每字成本較高。", "ja-JP": "xAIのフラッグシップモデルで、データ抽出、コーディング、要約などのエンタープライズ用途に優れ、金融、医療、法律、科学分野における深い専門知識を備えています。高速バリアントは高速インフラ上で動作し、より迅速な応答を提供します（トークン単価は高め）。", "ru-RU": "Флагманская модель xAI, превосходно подходящая для корпоративных задач, таких как извлечение данных, программирование и суммирование, с глубокими знаниями в области финансов, здравоохранения, права и науки. Быстрая версия работает на ускоренной инфраструктуре для более быстрых ответов при более высокой стоимости за токен." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Grok 3 Fast" } ] }, { "slug": "xai/grok-3-fast-beta", "model_name": "grok-3-fast-beta", "display_name": "grok-3-fast-beta", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "25" }, "cache_read": { "unit": "per_M_tokens", "price": "1.25" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.75" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "5" }, "discarded_charge": { "unit": "per_request", "price": "0.025" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://x.ai/api#pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "structured_output": true, "web_search": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" } ] }, { "slug": "xai/grok-3-fast-latest", "model_name": "grok-3-fast-latest", "display_name": "grok-3-fast-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "25" }, "cache_read": { "unit": "per_M_tokens", "price": "1.25" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.75" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "15" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://x.ai/api#pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "web_search": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2025-02-17", "knowledge_cutoff": "2024-11", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "xai/grok-3-latest", "model_name": "grok-3-latest", "display_name": "grok-3-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.75" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://x.ai/api#pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "web_search": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2025-02-17", "knowledge_cutoff": "2024-11", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "xai/grok-3-mini", "model_name": "grok-3-mini", "display_name": "grok-3-mini", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+helicone-registry+llmdb+pricetoken+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "web_search": { "unit": "per_k_calls", "price": "25" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.07" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "helicone-registry", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "25" }, "discarded_charge": { "unit": "per_k_calls", "price": "5" }, "message": "web_search from llmdb conflicts with helicone-registry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://x.ai/api#pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-02-28", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "intro": "Lightweight model that thinks before responding. Fast, smart, and great for logic-based tasks that do not require deep domain knowledge. Features function calling, structured outputs, and reasoning capabilities.", "knowledge_cutoff": "2024-06", "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "released_at": "2025-02-17", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "azure_ai/global/grok-3-mini", "pa/grok-3-mini", "x-ai/grok-3-mini", "xai/grok-3-mini" ], "intro_i18n": { "zh-CN": "xAI 的 Grok 3 Mini —— 推理强、响应快的小型模型。", "zh-TW": "xAI Grok 3 Mini —— 具備強大推理與快速回應能力。", "ja-JP": "xAIのGrok 3 Miniは、強力な推論能力と高速応答を備えています。", "ru-RU": "Grok 3 Mini от xAI — модель с сильными возможностями рассуждения и быстрыми ответами." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "xai/grok-3-mini-beta", "model_name": "grok-3-mini-beta", "display_name": "grok-3-mini-beta", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.075" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.07" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://x.ai/api#pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "deprecated": true, "model_type": "text_generation", "deprecation_date": "2026-02-28", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "web_search": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2025-04-09", "knowledge_cutoff": "2024-11", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "x-ai/grok-3-mini-beta" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "xai/grok-3-mini-fast", "model_name": "grok-3-mini-fast", "display_name": "grok-3-mini-fast", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.07" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://x.ai/api#pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "web_search": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2025-02-17", "knowledge_cutoff": "2024-11", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "xai/grok-3-mini-fast" ], "intro_i18n": { "zh-CN": "xAI 的轻量模型，在回答前进行思考，适用于简单或基于逻辑的任务，无需深度领域知识。提供原始推理轨迹。快速版本运行在更快的基础设施上，响应速度更快但每个 token 成本更高。", "zh-TW": "xAI 的輕量模型，在回應前會進行思考，適合簡單或邏輯型任務，不需深度領域知識。提供原始推理軌跡。快速版本運行於更快基礎設施，回應速度更快但每字成本較高。", "ja-JP": "xAIの軽量モデルで、応答前に思考を行い、シンプルまたは論理ベースのタスクに最適です。生の推論トレースが利用可能です。高速バリアントは高速インフラ上で動作し、より迅速な応答を提供します（トークン単価は高め）。", "ru-RU": "Легковесная модель xAI, которая «думает» перед ответом, идеально подходит для простых или логических задач без необходимости в глубоких знаниях. Доступны необработанные следы рассуждений. Быстрая версия работает на ускоренной инфраструктуре для более быстрых ответов при более высокой стоимости за токен." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "xai/grok-3-mini-fast-beta", "model_name": "grok-3-mini-fast-beta", "display_name": "grok-3-mini-fast-beta", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.07" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://x.ai/api#pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "web_search": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" } ] }, { "slug": "xai/grok-3-mini-fast-high", "model_name": "grok-3-mini-fast-high", "display_name": "grok-3-mini-fast-high", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "reasoning": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-3-mini-fast-high" } ] }, { "slug": "xai/grok-3-mini-fast-high-beta", "model_name": "grok-3-mini-fast-high-beta", "display_name": "grok-3-mini-fast-high-beta", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "reasoning": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-3-mini-fast-high-beta" } ] }, { "slug": "xai/grok-3-mini-fast-latest", "model_name": "grok-3-mini-fast-latest", "display_name": "grok-3-mini-fast-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.15" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.075" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.6" }, "discarded_charge": { "unit": "per_request", "price": "0.005" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "docs_url": "https://x.ai/api#pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "web_search": true, "stream": true }, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2025-02-17", "knowledge_cutoff": "2024-11", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "xai/grok-3-mini-high", "model_name": "grok-3-mini-high", "display_name": "grok-3-mini-high", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-3-mini-high" } ] }, { "slug": "xai/grok-3-mini-high-beta", "model_name": "grok-3-mini-high-beta", "display_name": "grok-3-mini-high-beta", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "structured_output": true, "reasoning": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-3-mini-high-beta" } ] }, { "slug": "xai/grok-3-mini-latest", "model_name": "grok-3-mini-latest", "display_name": "grok-3-mini-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.075" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "litellm+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://x.ai/api#pricing", "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "web_search": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2025-02-17", "knowledge_cutoff": "2024-11", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "xai/grok-4", "model_name": "grok-4", "display_name": "grok-4", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+helicone-registry+llmdb+pricetoken+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.75" }, "web_search": { "unit": "per_k_calls", "price": "25" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "truefoundry", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥128K", "source": "helicone-registry", "charge_sources": { "prompt": "helicone-registry", "completion": "helicone-registry", "cache_read": "helicone-registry", "web_search": "helicone-registry" } }, { "label": "Base pricing", "source": "litellm+truefoundry+helicone-registry+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "truefoundry", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "helicone-registry", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "25" }, "discarded_charge": { "unit": "per_k_calls", "price": "5" }, "message": "web_search from llmdb conflicts with helicone-registry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2", "cache_read": "1", "web_search": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true, "stream": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "Latest and greatest flagship model, offering unparalleled performance in natural language, math and reasoning - the perfect jack of all trades. Features function calling, structured outputs, and reasoning capabilities.", "knowledge_cutoff": "2024-07", "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "released_at": "2025-07-09", "family": "grok", "deprecated": true, "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "x-ai/grok-4", "xai/grok-4" ], "intro_i18n": { "zh-CN": "xAI 最新旗舰模型，在自然语言、数学和推理方面表现卓越，是理想的全能型模型。", "zh-TW": "xAI 最新旗艦模型，在自然語言、數學與推理方面表現卓越，是理想的全能型選擇。", "ja-JP": "xAIの最新フラッグシップモデルで、自然言語、数学、推論において比類なき性能を発揮する万能モデルです。", "ru-RU": "Новейшая флагманская модель xAI с непревзойденной производительностью в области естественного языка, математики и рассуждений — универсальный лидер." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "parallel_function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "xai/grok-4-0709", "model_name": "grok-4-0709", "display_name": "grok-4-0709", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.75" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >128K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm+truefoundry+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 256000, "max_output_tokens": 256000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-05-15", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2025-07-09", "knowledge_cutoff": "2025-07", "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "xAI 的 Grok 4，具备强大的推理能力。", "zh-TW": "xAI 的 Grok 4，具備強大的推理能力。", "ja-JP": "xAI による Grok 4 は、強力な推論能力を備えています。", "ru-RU": "Grok 4 от xAI с мощными логическими возможностями." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "xai/grok-4-1-fast", "model_name": "grok-4-1-fast", "display_name": "grok-4-1-fast", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+llmdb+pricetoken", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >128K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "verification_status": "cross_checked" }, "provider_model_id": "grok-4.1-fast", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2025-11-19", "knowledge_cutoff": "2025-07", "family": "grok", "intro": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "deprecated": true, "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4.1-fast", "x-ai/grok-4.1-fast" ], "intro_i18n": { "zh-CN": "Grok 4 Fast 是 xAI 推出的高吞吐、低成本模型（支持 2M 上下文窗口），适用于高并发和长上下文场景。", "zh-TW": "Grok 4.1 Fast 是 xAI 推出的高吞吐、低成本模型（支援 2M 上下文），適用於高併發與長上下文應用場景。", "ja-JP": "Grok 4.1 Fastは、xAIによる高スループット・低コストモデルで、2Mのコンテキストウィンドウをサポートし、高並列性および長文コンテキストのユースケースに最適です。", "ru-RU": "Grok 4 Fast — это высокопроизводительная, недорогая модель от xAI (поддерживает контекст до 2M), идеально подходящая для сценариев с высокой конкуренцией и длинным контекстом." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "xai/grok-4-1-fast-non-reasoning", "model_name": "grok-4-1-fast-non-reasoning", "display_name": "grok-4-1-fast-non-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+helicone-registry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "web_search": { "unit": "per_k_calls", "price": "25" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >128K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm+helicone-registry+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "helicone-registry", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "25" }, "discarded_charge": { "unit": "per_k_calls", "price": "5" }, "message": "web_search from llmdb conflicts with helicone-registry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-05-15", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "image_output": true, "stream": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "A frontier multimodal model optimized specifically for high-performance agentic tool calling.", "knowledge_cutoff": "2025-11", "parameters": { "supported": [ "logprobs", "max_tokens", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "released_at": "2025-11-19", "family": "grok", "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4.1-fast-non-reasoning", "pa/grok-4-1-fast-non-reasoning", "x-ai/grok-4.1-fast-non-reasoning", "xai/grok-4-1-fast-non-reasoning", "xai/grok-4.1-fast-non-reasoning" ], "intro_i18n": { "zh-CN": "Grok 4 Fast（非推理版）是 xAI 推出的高吞吐、低成本多模态模型（支持 2M 上下文窗口），适用于对延迟和成本敏感但不需要模型内推理的场景。可通过 API 的 reasoning 参数启用推理功能。提示词和生成内容可能被 xAI 或 OpenRouter 用于改进未来模型。", "zh-TW": "Grok 4.1 Fast（非推理版）是 xAI 推出的高吞吐、低成本多模態模型（支援 2M 上下文），適用於對延遲與成本敏感但不需模型內推理的場景。可透過 API 的 reasoning 參數啟用推理功能。提示與完成可能被 xAI 或 OpenRouter 用於改進未來模型。", "ja-JP": "Grok 4.1 Fast（非推論）は、xAIによる高スループット・低コストのマルチモーダルモデルで、2Mのコンテキストウィンドウをサポートし、レイテンシやコストに敏感な推論不要のシナリオに最適です。必要に応じてAPIのreasoningパラメータで推論を有効化できます。プロンプトと出力は、xAIまたはOpenRouterによって将来のモデル改善に使用される可能性があります。", "ru-RU": "Grok 4 Fast (без рассуждений) — это высокопроизводительная, недорогая мультимодальная модель от xAI (поддерживает контекст до 2M), предназначенная для сценариев, чувствительных к задержке и стоимости, не требующих встроенного рассуждения. Рассуждение можно включить через параметр reasoning в API. Подсказки и ответы могут использоваться xAI или OpenRouter для улучшения будущих моделей." }, "price_history": [ { "date": "2026-07-18", "kind": "capability", "note": "reasoning: true→false" }, { "date": "2026-07-13", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "xai/grok-4-1-fast-non-reasoning-latest", "model_name": "grok-4-1-fast-non-reasoning-latest", "display_name": "grok-4-1-fast-non-reasoning-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >128K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-05-15", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "web_search": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "xai/grok-4-1-fast-reasoning", "model_name": "grok-4-1-fast-reasoning", "display_name": "grok-4-1-fast-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+helicone-registry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "web_search": { "unit": "per_k_calls", "price": "25" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >128K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm+helicone-registry+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "helicone-registry", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "25" }, "discarded_charge": { "unit": "per_k_calls", "price": "5" }, "message": "web_search from llmdb conflicts with helicone-registry; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "helicone-registry", "selected_source": "litellm", "threshold": 128000, "inclusive": true, "message": "helicone-registry introduced a ≥128000 tier outside the litellm schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-05-15", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true, "image_output": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "A frontier multimodal model optimized for high-performance agentic tool calling with reasoning capabilities.", "knowledge_cutoff": "2025-11", "parameters": { "supported": [ "logprobs", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "released_at": "2025-11-19", "family": "grok", "status": "beta", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4.1-fast-reasoning", "pa/grok-4-1-fast-reasoning", "x-ai/grok-4.1-fast-reasoning", "xai/grok-4-1-fast-reasoning", "xai/grok-4.1-fast-reasoning" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "xai/grok-4-1-fast-reasoning-latest", "model_name": "grok-4-1-fast-reasoning-latest", "display_name": "grok-4-1-fast-reasoning-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >128K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-05-15", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "web_search": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] } }, { "slug": "xai/grok-4-128k", "model_name": "grok-4-128k", "display_name": "Grok 4", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "6" }, "completion": { "unit": "per_M_tokens", "price": "30" }, "cache_read": { "unit": "per_M_tokens", "price": "0.75" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www", "cache_read": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Grok 4" } ] }, { "slug": "xai/grok-4-20", "model_name": "grok-4-20", "display_name": "Grok 4.20", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+pricetoken+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "pricetoken", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "prompt from pricetoken conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pricetoken", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6" }, "message": "completion from pricetoken conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "provider_model_id": "grok-4.20", "tracks": [ { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true, "pdf_input": true }, "released_at": "2026-03-09", "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance", "max_output_tokens": 131072, "family": "grok", "knowledge_cutoff": "2025-09", "parameters": { "supported": [ "include_reasoning", "logprobs", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4.20", "x-ai/grok-4.20" ], "price_history": [ { "date": "2026-07-15", "kind": "limit", "old": "128000", "new": "131072", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "Grok 4.20" } ] }, { "slug": "xai/grok-4-20-multi-agent", "model_name": "grok-4-20-multi-agent", "display_name": "grok-4.20-multi-agent", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "provider_model_id": "grok-4.20-multi-agent", "tracks": [ { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "reasoning": true, "vision": true, "pdf_input": true, "web_search": true }, "released_at": "2026-03-09", "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance", "max_output_tokens": 131072, "family": "grok", "knowledge_cutoff": "2025-09", "parameters": { "unsupported": [ "temperature" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4.20-multi-agent", "x-ai/grok-4.20-multi-agent", "xai/grok-4.20-multi-agent" ], "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "131072", "new": "0", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "0", "new": "131072", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "0", "new": "131072", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "131072", "new": "0", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "0", "new": "131072", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "131072", "new": "0", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "0", "new": "131072", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "131072", "new": "0", "note": "max_output_tokens" }, { "date": "2026-07-25", "kind": "limit", "old": "131072", "new": "0", "note": "max_output_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "2000000", "new": "131072", "note": "max_output_tokens" } ] }, { "slug": "xai/grok-4-20-non-reasoning", "model_name": "grok-4-20-non-reasoning", "display_name": "grok-4.20-non-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "provider_model_id": "grok-4.20-non-reasoning", "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "vision": true, "reasoning": true, "pdf_input": true, "web_search": true }, "released_at": "2026-03-09", "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance", "knowledge_cutoff": "2025-09", "max_output_tokens": 8192, "family": "grok", "status": "beta", "docs_url": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4.20-non-reasoning", "xai/grok-4.20-non-reasoning" ], "intro_i18n": { "zh-CN": "无推理模式版本，适用于简单场景。", "zh-TW": "不具推理功能的版本，適用於簡單使用情境。", "ja-JP": "単純なユースケース向けの非推論バリアント。", "ru-RU": "Вариант без рассуждений для простых задач." }, "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "8192", "new": "30000", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "30000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "30000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "8192", "new": "30000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "30000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "8192", "new": "30000", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "30000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "8192", "new": "30000", "note": "max_output_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "2000000", "new": "30000", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-non-reasoning" } ] }, { "slug": "xai/grok-4-20-reasoning", "model_name": "grok-4-20-reasoning", "display_name": "grok-4.20-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "provider_model_id": "grok-4.20-reasoning", "tracks": [ { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true, "pdf_input": true, "web_search": true }, "released_at": "2026-03-09", "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance", "knowledge_cutoff": "2025-09", "max_output_tokens": 8192, "family": "grok", "status": "beta", "docs_url": "https://docs.x.ai/docs/models (Vertex AI Model Garden)", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4.20-reasoning", "x-ai/grok-4.20-reasoning", "xai/grok-4.20-reasoning" ], "intro_i18n": { "zh-CN": "智能、高速的推理模型，先思考后回答。", "zh-TW": "智慧、極速的模型，會先思考再作答。", "ja-JP": "応答前に推論する知的で超高速なモデル。", "ru-RU": "Интеллектуальная, сверхбыстрая модель, которая размышляет перед тем, как ответить." }, "price_history": [ { "date": "2026-08-14", "kind": "limit", "old": "8192", "new": "30000", "note": "max_output_tokens" }, { "date": "2026-08-14", "kind": "limit", "old": "30000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "30000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-08-13", "kind": "limit", "old": "8192", "new": "30000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "30000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "8192", "new": "30000", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "30000", "new": "8192", "note": "max_output_tokens" }, { "date": "2026-08-11", "kind": "limit", "old": "8192", "new": "30000", "note": "max_output_tokens" }, { "date": "2026-07-15", "kind": "limit", "old": "2000000", "new": "30000", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-reasoning" } ] }, { "slug": "xai/grok-4-fast", "model_name": "grok-4-fast", "display_name": "Grok 4 Fast Reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+helicone-registry+llmdb+llm-prices-www", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.5" }, "web_search": { "unit": "per_k_calls", "price": "25" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥128K", "source": "helicone-registry", "charge_sources": { "prompt": "helicone-registry", "completion": "helicone-registry", "cache_read": "helicone-registry", "web_search": "helicone-registry" } }, { "label": "Base pricing", "source": "truefoundry+helicone-registry+llmdb", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "helicone-registry", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "25" }, "discarded_charge": { "unit": "per_k_calls", "price": "5" }, "message": "web_search from llmdb conflicts with helicone-registry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2", "cache_read": "1", "web_search": "1" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 2000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true, "web_search": true, "stream": true, "pdf_input": true, "audio_input": true, "video_input": true }, "intro": "Grok 4 Fast is xAI's latest advancement in cost-efficient reasoning models. Built on xAI’s learnings from Grok 4, Grok 4 Fast delivers frontier-level performance across Enterprise and Consumer domains—with exceptional token efficiency. This model pushes the boundaries for smaller and faster AI, making high-quality reasoning accessible to more users and developers. Grok 4 Fast features state-of-the-art (SOTA) cost-efficiency, cutting-edge web and X search capabilities, a 2M token context window, and a unified architecture that blends reasoning and non-reasoning modes in one model.", "knowledge_cutoff": "2025-09", "max_output_tokens": 2000000, "parameters": { "supported": [ "logprobs", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "released_at": "2025-09-19", "family": "grok", "deprecated": true, "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "x-ai/grok-4-fast", "x-ai/grok-4-fast:free", "xai/grok-4-fast" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Grok 4 Fast Reasoning" } ] }, { "slug": "xai/grok-4-fast-128k", "model_name": "grok-4-fast-128k", "display_name": "Grok 4 Fast", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www", "cache_read": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Grok 4 Fast" } ] }, { "slug": "xai/grok-4-fast-non-reasoning", "model_name": "grok-4-fast-non-reasoning", "display_name": "grok-4-fast-non-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+helicone-registry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "web_search": { "unit": "per_k_calls", "price": "25" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >128K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm+helicone-registry+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "helicone-registry", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "helicone-registry", "charge": "web_search", "selected_charge": { "unit": "per_k_calls", "price": "25" }, "discarded_charge": { "unit": "per_k_calls", "price": "5" }, "message": "web_search from llmdb conflicts with helicone-registry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.05" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.02" }, "message": "cache_read from llmdb conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-05-15", "capabilities": { "vision": true, "function_calling": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true, "image_output": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "intro": "Grok 4 Fast is xAI's latest advancement in cost-efficient reasoning models. Built on xAI’s learnings from Grok 4, Grok 4 Fast delivers frontier-level performance across Enterprise and Consumer domains—with exceptional token efficiency. This model pushes the boundaries for smaller and faster AI, making high-quality reasoning accessible to more users and developers. Grok 4 Fast features state-of-the-art (SOTA) cost-efficiency, cutting-edge web and X search capabilities, a 2M token context window. This non-reasoning model specifically excludes reasoning capabilities.", "knowledge_cutoff": "2025-09", "parameters": { "supported": [ "logprobs", "max_tokens", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "released_at": "2025-09-21", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "pa/grok-4-fast-non-reasoning", "x-ai/grok-4-fast-non-reasoning", "xai/grok-4-fast-non-reasoning" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "xai/grok-4-fast-non-reasoning-latest", "model_name": "grok-4-fast-non-reasoning-latest", "display_name": "grok-4-fast-non-reasoning-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 2000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4-fast-non-reasoning-latest" } ] }, { "slug": "xai/grok-4-fast-reasoning", "model_name": "grok-4-fast-reasoning", "display_name": "grok-4-fast-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+llmdb+llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >128K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.05" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.02" }, "message": "cache_read from llmdb conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 2000000, "max_output_tokens": 2000000, "deprecated": true, "model_type": "deep_thinking", "deprecation_date": "2026-05-15", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true, "image_output": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2025-09-21", "knowledge_cutoff": "2024-11", "intro": "Fast Grok model for responsive chat, reasoning, and tool-assisted work", "family": "grok", "parameters": { "unsupported": [ "temperature" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "pa/grok-4-fast-reasoning", "x-ai/grok-4-fast-reasoning", "xai/grok-4-fast-reasoning" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "xai/grok-4-fast-reasoning-128k", "model_name": "grok-4-fast-reasoning-128k", "display_name": "Grok 4 Fast Reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "llm-prices-www", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.4" }, "completion": { "unit": "per_M_tokens", "price": "1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.05" } }, "provenance": { "base_charges": { "prompt": "llm-prices-www", "completion": "llm-prices-www", "cache_read": "llm-prices-www" }, "verification_status": "aggregator_only" } } ], "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Grok 4 Fast Reasoning" } ] }, { "slug": "xai/grok-4-fast-reasoning-latest", "model_name": "grok-4-fast-reasoning-latest", "display_name": "grok-4-fast-reasoning-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.05" }, "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 2000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4-fast-reasoning-latest" } ] }, { "slug": "xai/grok-4-latest", "model_name": "grok-4-latest", "display_name": "grok-4-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "3" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >128K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm+truefoundry", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "15" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.333333", "completion": "0.2" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >128K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 128000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "web_search": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" } ] }, { "slug": "xai/grok-4.20-0309", "model_name": "grok-4.20-0309", "display_name": "grok-4.20-0309", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-0309" } ] }, { "slug": "xai/grok-4.20-0309-non-reasoning", "model_name": "grok-4.20-0309-non-reasoning", "display_name": "Grok 4.20 (Non-Reasoning)", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "models-dev+litellm+truefoundry+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance", "released_at": "2026-03-09", "max_input_tokens": 1000000, "max_output_tokens": 30000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "grok", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true }, "docs_url": "https://docs.x.ai/docs/models", "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "xai/grok-4.20-0309-non-reasoning" ], "intro_i18n": { "zh-CN": "无推理模式版本，适用于简单场景。", "zh-TW": "不具推理功能的版本，適用於簡單使用情境。", "ja-JP": "単純なユースケース向けの非推論バリアント。", "ru-RU": "Вариант без рассуждений для простых задач." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "xai/grok-4.20-0309-reasoning", "model_name": "grok-4.20-0309-reasoning", "display_name": "Grok 4.20 (Reasoning)", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "models-dev+litellm+truefoundry+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "tracks": [ { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Reasoning Grok for document-heavy analysis and long-horizon tool use", "released_at": "2026-03-09", "max_input_tokens": 1000000, "max_output_tokens": 30000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "grok", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true }, "docs_url": "https://docs.x.ai/docs/models", "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "xai/grok-4.20-0309-reasoning" ], "intro_i18n": { "zh-CN": "智能、高速的推理模型，先思考后回答。", "zh-TW": "智慧、極速的模型，會先思考再作答。", "ja-JP": "応答前に推論する知的で超高速なモデル。", "ru-RU": "Интеллектуальная, сверхбыстрая модель, которая размышляет перед тем, как ответить." }, "price_history": [ { "date": "2026-07-09", "kind": "price", "provider": "tetrate", "charge": "completion", "old": "6", "new": "2.5" }, { "date": "2026-07-09", "kind": "price", "provider": "tetrate", "charge": "prompt", "old": "2", "new": "1.25" } ] }, { "slug": "xai/grok-4.20-beta", "model_name": "grok-4.20-beta", "display_name": "grok-4.20-beta", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8", "completion": "0.8" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "reasoning": true, "vision": true, "prompt_caching": true, "pdf_input": true }, "released_at": "2026-03-09", "deprecated": true, "max_output_tokens": 0, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "x-ai/grok-4.20-beta" ], "price_history": [ { "date": "2026-07-29", "kind": "limit", "old": "2000000", "new": "1000000", "note": "max_input_tokens" }, { "date": "2026-07-29", "kind": "price", "provider": "xai", "charge": "completion", "old": "6", "new": "2.5" }, { "date": "2026-07-29", "kind": "price", "provider": "xai", "charge": "prompt", "old": "2", "new": "1.25" }, { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-beta" } ] }, { "slug": "xai/grok-4.20-beta-0309", "model_name": "grok-4.20-beta-0309", "display_name": "grok-4.20-beta-0309", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8", "completion": "0.8" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-29", "kind": "limit", "old": "2000000", "new": "1000000", "note": "max_input_tokens" }, { "date": "2026-07-29", "kind": "price", "provider": "xai", "charge": "completion", "old": "6", "new": "2.5" }, { "date": "2026-07-29", "kind": "price", "provider": "xai", "charge": "prompt", "old": "2", "new": "1.25" }, { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-beta-0309" } ] }, { "slug": "xai/grok-4.20-beta-0309-non-reasoning", "model_name": "grok-4.20-beta-0309-non-reasoning", "display_name": "grok-4.20-beta-0309-non-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >200K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the litellm schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "image_output": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2026-03-09", "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4-20-beta-0309-non-reasoning" ], "intro_i18n": { "zh-CN": "适用于简单用例的非推理版本", "zh-TW": "適用於簡單使用場景的非推理版本", "ja-JP": "シンプルなユースケース向けの非推論型バリアント。", "ru-RU": "Вариант без рассуждений для простых случаев использования." }, "price_history": [ { "date": "2026-08-12", "kind": "limit", "old": "2000000", "new": "1000000", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "2000000", "new": "1000000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "completion", "old": "6", "new": "2.5" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "prompt", "old": "2", "new": "1.25" }, { "date": "2026-07-02", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "xai/grok-4.20-beta-0309-reasoning", "model_name": "grok-4.20-beta-0309-reasoning", "display_name": "grok-4.20-beta-0309-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "tracks": [ { "label": "Context >200K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the litellm schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "image_output": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2026-03-09", "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance", "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4-20-beta-0309-reasoning" ], "intro_i18n": { "zh-CN": "智能且极速的模型，在响应前进行推理", "zh-TW": "智能且極速的模型，在回應前進行推理", "ja-JP": "応答前に推論を行う、知的で超高速なモデル。", "ru-RU": "Интеллектуальная, сверхбыстрая модель, которая рассуждает перед ответом." }, "price_history": [ { "date": "2026-08-12", "kind": "limit", "old": "2000000", "new": "1000000", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "2000000", "new": "1000000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "completion", "old": "6", "new": "2.5" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "prompt", "old": "2", "new": "1.25" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "xai/grok-4.20-beta-latest", "model_name": "grok-4.20-beta-latest", "display_name": "grok-4.20-beta-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "limit", "old": "2000000", "new": "1000000", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "completion", "old": "6", "new": "2.5" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "prompt", "old": "2", "new": "1.25" }, { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-beta-latest" } ] }, { "slug": "xai/grok-4.20-beta-latest-non-reasoning", "model_name": "grok-4.20-beta-latest-non-reasoning", "display_name": "grok-4.20-beta-latest-non-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "vision": true, "reasoning": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-beta-latest-non-reasoning" } ] }, { "slug": "xai/grok-4.20-beta-latest-reasoning", "model_name": "grok-4.20-beta-latest-reasoning", "display_name": "grok-4.20-beta-latest-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "reasoning": true, "vision": true, "prompt_caching": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-beta-latest-reasoning" } ] }, { "slug": "xai/grok-4.20-beta-non-reasoning", "model_name": "grok-4.20-beta-non-reasoning", "display_name": "grok-4.20-beta-non-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "vision": true, "reasoning": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-beta-non-reasoning" } ] }, { "slug": "xai/grok-4.20-beta-reasoning", "model_name": "grok-4.20-beta-reasoning", "display_name": "grok-4.20-beta-reasoning", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-17", "kind": "limit", "old": "2000000", "new": "1000000", "note": "max_input_tokens" }, { "date": "2026-07-17", "kind": "price", "provider": "xai", "charge": "completion", "old": "6", "new": "2.5" }, { "date": "2026-07-17", "kind": "price", "provider": "xai", "charge": "prompt", "old": "2", "new": "1.25" }, { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-beta-reasoning" } ] }, { "slug": "xai/grok-4.20-experimental-beta-0304", "model_name": "grok-4.20-experimental-beta-0304", "display_name": "grok-4.20-experimental-beta-0304", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.25" }, "message": "prompt from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 2000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "vision": true, "reasoning": true, "prompt_caching": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-experimental-beta-0304" } ] }, { "slug": "xai/grok-4.20-experimental-beta-0304-non-reasoning", "model_name": "grok-4.20-experimental-beta-0304-non-reasoning", "display_name": "Grok 4.20 (Experimental, Non-Reasoning)", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+llmdb+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry+llmdb", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "prompt from llmdb conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6" }, "message": "completion from llmdb conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "vision": true, "stream": true, "pdf_input": true, "reasoning": true }, "released_at": "2026-03-04", "max_output_tokens": 30000, "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Grok 4.20 (Experimental, Non-Reasoning)" } ] }, { "slug": "xai/grok-4.20-experimental-beta-0304-reasoning", "model_name": "grok-4.20-experimental-beta-0304-reasoning", "display_name": "Grok 4.20 (Experimental, Reasoning)", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+llmdb+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry+llmdb", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.25" }, "message": "prompt from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 2000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "reasoning": true, "vision": true, "prompt_caching": true, "stream": true, "pdf_input": true }, "released_at": "2026-03-04", "max_output_tokens": 30000, "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Grok 4.20 (Experimental, Reasoning)" } ] }, { "slug": "xai/grok-4.20-experimental-beta-latest", "model_name": "grok-4.20-experimental-beta-latest", "display_name": "grok-4.20-experimental-beta-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.25" }, "message": "prompt from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 2000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "reasoning": true, "vision": true, "prompt_caching": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-experimental-beta-latest" } ] }, { "slug": "xai/grok-4.20-experimental-beta-non-reasoning-latest", "model_name": "grok-4.20-experimental-beta-non-reasoning-latest", "display_name": "grok-4.20-experimental-beta-non-reasoning-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "vision": true, "reasoning": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-experimental-beta-non-reasoning-latest" } ] }, { "slug": "xai/grok-4.20-experimental-beta-reasoning-latest", "model_name": "grok-4.20-experimental-beta-reasoning-latest", "display_name": "grok-4.20-experimental-beta-reasoning-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 2000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "reasoning": true, "vision": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-17", "kind": "price", "provider": "xai", "charge": "completion", "old": "6", "new": "2.5" }, { "date": "2026-07-17", "kind": "price", "provider": "xai", "charge": "prompt", "old": "2", "new": "1.25" }, { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-experimental-beta-reasoning-latest" } ] }, { "slug": "xai/grok-4.20-multi-agent-0309", "model_name": "grok-4.20-multi-agent-0309", "display_name": "Grok 4.20 Multi-Agent", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "models-dev+litellm+truefoundry+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "tracks": [ { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance", "released_at": "2026-03-09", "max_input_tokens": 1000000, "max_output_tokens": 30000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "grok", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true }, "docs_url": "https://docs.x.ai/docs/models", "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "xai/grok-4.20-multi-agent-0309" ], "intro_i18n": { "zh-CN": "由 4 至 16 个 Agent 组成的团队，擅长科研类任务。目前不支持客户端工具，只支持 xAI 服务器端工具（如 X Search、Web Search）及远程 MCP 工具。", "zh-TW": "由 4 或 16 個代理組成的團隊，擅長研究類任務。目前不支援客戶端工具，只支援 xAI 伺服器端工具（如 X Search、Web Search）及遠端 MCP 工具。", "ja-JP": "4または16のエージェントチーム。研究ユースケースに優れています。現在、クライアントサイドツールはサポートしていません。xAIサーバーサイドツール（例：X Search、Web Searchツール）およびリモートMCPツールのみをサポートします。", "ru-RU": "Команда из 4 или 16 агентов. Превосходна для исследовательских задач. Пока не поддерживает клиентские инструменты. Поддерживает только серверные инструменты xAI (например, X Search, Web Search) и удалённые MCP-инструменты." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "xai/grok-4.20-multi-agent-beta-0309", "model_name": "grok-4.20-multi-agent-beta-0309", "display_name": "grok-4.20-multi-agent-beta-0309", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "tracks": [ { "label": "Context >200K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the litellm schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "image_output": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2026-03-09", "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "limit", "old": "2000000", "new": "1000000", "note": "max_input_tokens" }, { "date": "2026-08-12", "kind": "limit", "old": "2000000", "new": "1000000", "note": "max_output_tokens" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "completion", "old": "6", "new": "2.5" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "prompt", "old": "2", "new": "1.25" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "xai/grok-4.20-multi-agent-beta-0309-exp-ma", "model_name": "grok-4.20-multi-agent-beta-0309-exp-ma", "display_name": "grok-4.20-multi-agent-beta-0309-exp-ma", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 2000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-multi-agent-beta-0309-exp-ma" } ] }, { "slug": "xai/grok-4.20-multi-agent-beta-latest", "model_name": "grok-4.20-multi-agent-beta-latest", "display_name": "grok-4.20-multi-agent-beta-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "reasoning": true, "vision": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-multi-agent-beta-latest" } ] }, { "slug": "xai/grok-4.20-multi-agent-experimental-beta-0304", "model_name": "grok-4.20-multi-agent-experimental-beta-0304", "display_name": "Grok 4.20 Multi-Agent (Experimental)", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+llmdb+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1.25" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "prompt from llmdb conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2.5" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6" }, "message": "completion from llmdb conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "reasoning": true, "vision": true, "stream": true, "pdf_input": true }, "released_at": "2026-03-04", "max_output_tokens": 30000, "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Grok 4.20 Multi-Agent (Experimental)" } ] }, { "slug": "xai/grok-4.20-multi-agent-experimental-beta-latest", "model_name": "grok-4.20-multi-agent-experimental-beta-latest", "display_name": "grok-4.20-multi-agent-experimental-beta-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8", "completion": "0.8" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "reasoning": true, "vision": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-29", "kind": "limit", "old": "2000000", "new": "1000000", "note": "max_input_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-multi-agent-experimental-beta-latest" } ] }, { "slug": "xai/grok-4.20-multi-agent-latest", "model_name": "grok-4.20-multi-agent-latest", "display_name": "grok-4.20-multi-agent-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.5", "completion": "0.5" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "reasoning": true, "vision": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-multi-agent-latest" } ] }, { "slug": "xai/grok-4.20-non-reasoning-gv2", "model_name": "grok-4.20-non-reasoning-gv2", "display_name": "grok-4.20-non-reasoning-gv2", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "prompt_caching": true, "vision": true, "reasoning": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-non-reasoning-gv2" } ] }, { "slug": "xai/grok-4.20-non-reasoning-latest", "model_name": "grok-4.20-non-reasoning-latest", "display_name": "grok-4.20-non-reasoning-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8", "completion": "0.8" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "vision": true, "reasoning": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-non-reasoning-latest" } ] }, { "slug": "xai/grok-4.20-reasoning-gv2", "model_name": "grok-4.20-reasoning-gv2", "display_name": "grok-4.20-reasoning-gv2", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.25" }, "message": "prompt from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "6" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2.5" }, "message": "completion from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "max_input_tokens": 2000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "structured_output": true, "reasoning": true, "vision": true, "prompt_caching": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-reasoning-gv2" } ] }, { "slug": "xai/grok-4.20-reasoning-latest", "model_name": "grok-4.20-reasoning-latest", "display_name": "grok-4.20-reasoning-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "cross_checked" }, "tracks": [ { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "prompt_caching": true, "structured_output": true, "reasoning": true, "vision": true, "pdf_input": true }, "released_at": "2026-03-09", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-4.20-reasoning-latest" } ] }, { "slug": "xai/grok-4.3", "model_name": "grok-4.3", "display_name": "Grok 4.3", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "models-dev+litellm+truefoundry+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "tracks": [ { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "xAI's Grok for chat, coding, agentic tools, and lower hallucination risk", "released_at": "2026-04-17", "max_input_tokens": 1000000, "max_output_tokens": 30000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "grok", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true }, "docs_url": "https://docs.x.ai/docs/models", "model_type": "deep_thinking", "knowledge_cutoff": "2025-12", "benchmarks": { "intelligence_index": 37.9, "coding_index": 42.2, "agentic_index": 24.2 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4-3", "grok/grok-4.3", "x-ai/grok-4.3", "xai/grok-4.3" ], "intro_i18n": { "zh-CN": "世界上最追求真理的大型语言模型", "zh-TW": "世界上最追求真理的大型語言模型", "ja-JP": "世界で最も真実を追求する大規模言語モデル", "ru-RU": "Самая правдолюбивая крупная языковая модель в мире." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "image_output: false→true" } ] }, { "slug": "xai/grok-4.3-latest", "model_name": "grok-4.3-latest", "display_name": "grok-4.3-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "tracks": [ { "label": "Context >200K", "source": "litellm", "charge_sources": { "cache_read": "litellm", "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the litellm schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 1000000, "max_output_tokens": 1000000, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2026-04-17", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "xai/grok-4.5", "model_name": "grok-4.5", "display_name": "Grok 4.5", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "models-dev+litellm+truefoundry+lobehub-modelbank+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "tracks": [ { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.3" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk", "released_at": "2026-07-08", "max_input_tokens": 500000, "max_output_tokens": 500000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "grok", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "image_output": true, "web_search": true }, "docs_url": "https://docs.x.ai/docs/models", "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 55.8, "coding_index": 72.4, "agentic_index": 48.9 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4-5", "grok/grok-4.5", "x-ai/grok-4.5", "xai/grok-4.5" ], "intro_i18n": { "zh-CN": "SpaceXAI 的旗舰模型，专注于代理任务和知识工作——速度极快，编程能力可与 Claude Opus 媲美。", "zh-TW": "SpaceXAI 的旗艦模型，專注於代理任務和知識工作——速度驚人，編程能力可媲美 Claude Opus。", "ja-JP": "SpaceXAIの主力モデルで、エージェントタスクや知識作業に対応し、驚くほど高速で、コーディング能力はClaude Opusに匹敵します。", "ru-RU": "Флагманская модель SpaceXAI для агентных задач и работы с знаниями — исключительно быстрая, с возможностями кодирования на уровне Claude Opus." }, "price_history": [ { "date": "2026-07-19", "kind": "price", "provider": "xai", "charge": "cache_read", "old": "0.5", "new": "0.3" }, { "date": "2026-07-14", "kind": "capability", "note": "image_output: false→true" }, { "date": "2026-07-08", "kind": "listed", "note": "Grok 4.5" } ] }, { "slug": "xai/grok-4.5-latest", "model_name": "grok-4.5-latest", "display_name": "grok-4.5-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.3" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "tracks": [ { "label": "Context >200K", "source": "litellm", "charge_sources": { "cache_read": "litellm", "prompt": "litellm", "completion": "litellm" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "litellm", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the litellm schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 500000, "max_output_tokens": 500000, "model_type": "deep_thinking", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "released_at": "2026-06-29", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "cache_read", "old": "0.5", "new": "0.3" }, { "date": "2026-07-09", "kind": "capability", "note": "function_calling: false→true" }, { "date": "2026-07-09", "kind": "capability", "note": "reasoning: false→true" }, { "date": "2026-07-09", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-09", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-09", "kind": "limit", "new": "500000", "note": "max_input_tokens" }, { "date": "2026-07-09", "kind": "limit", "new": "500000", "note": "max_output_tokens" }, { "date": "2026-07-09", "kind": "listed", "note": "grok-4.5-latest" } ] }, { "slug": "xai/grok-4.6", "model_name": "grok-4.6", "display_name": "Grok 4.6", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "models-dev+truefoundry+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2" }, "completion": { "unit": "per_M_tokens", "price": "6" }, "cache_read": { "unit": "per_M_tokens", "price": "0.5" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "tracks": [ { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "xAI's frontier model for long-running agents, coding, knowledge work, and visual projects", "released_at": "2026-08-12", "knowledge_cutoff": "2026-02", "max_input_tokens": 500000, "max_output_tokens": 500000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "grok", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true }, "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 60.9, "coding_index": 76.8, "agentic_index": 58.7 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "reasoning_effort", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-4-6", "grok/grok-4.6", "x-ai/grok-4.6", "xai/grok-4.6" ], "price_history": [ { "date": "2026-08-12", "kind": "listed", "note": "Grok 4.6" } ] }, { "slug": "xai/grok-beta", "model_name": "grok-beta", "display_name": "grok-beta", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm+truefoundry", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "15" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm" }, "verification_status": "cross_checked" } } ], "max_input_tokens": 131072, "max_output_tokens": 131072, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "web_search": true }, "modalities": { "input": [ "image" ], "output": [] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "x-ai/grok-beta" ] }, { "slug": "xai/grok-build-0.1", "model_name": "grok-build-0.1", "display_name": "Grok Build 0.1", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "models-dev+litellm+truefoundry+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "tracks": [ { "label": "Context >200K", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } }, { "label": "Base pricing", "source": "models-dev", "charge_sources": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" } } ], "discarded_conflicts": [ { "kind": "tier_schedule", "source": "truefoundry", "selected_source": "models-dev", "threshold": 200000, "inclusive": true, "message": "truefoundry introduced a ≥200000 tier outside the models-dev schedule; it was discarded." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "intro": "Fast Grok coding model tuned for agentic engineering and iterative edits", "released_at": "2026-04-16", "max_input_tokens": 256000, "max_output_tokens": 256000, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "family": "grok-build", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true }, "docs_url": "https://docs.x.ai/docs/models", "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 40.7, "coding_index": 51.5, "agentic_index": 28.9 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logprobs", "max_tokens", "presence_penalty", "reasoning", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "reasoning_config": { "mandatory": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-build-0-1", "x-ai/grok-build-0.1", "xai/grok-build-0.1" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "xai/grok-build-latest", "model_name": "grok-build-latest", "display_name": "grok-build-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+ai-model-directory", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "2" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "2" }, "message": "prompt from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "6" }, "message": "completion from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." }, { "kind": "base_charge", "source": "ai-model-directory", "selected_source": "truefoundry", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "cache_read from ai-model-directory conflicts with truefoundry; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "max_input_tokens": 256000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "vision": true, "prompt_caching": true, "pdf_input": true }, "released_at": "2026-06-29", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-16", "kind": "limit", "new": "256000", "note": "max_input_tokens" }, { "date": "2026-07-16", "kind": "price", "provider": "xai", "charge": "cache_read", "old": "0.5", "new": "0.2" }, { "date": "2026-07-16", "kind": "price", "provider": "xai", "charge": "completion", "old": "6", "new": "2" }, { "date": "2026-07-16", "kind": "price", "provider": "xai", "charge": "prompt", "old": "2", "new": "1" }, { "date": "2026-07-09", "kind": "listed", "note": "grok-build-latest" } ] }, { "slug": "xai/grok-code-fast", "model_name": "grok-code-fast", "display_name": "grok-code-fast", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context >200K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.02" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.1", "completion": "0.375" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2026-04-16", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "cache_read", "old": "0.02", "new": "0.2" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "completion", "old": "1.5", "new": "2" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "prompt", "old": "0.2", "new": "1" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "xai/grok-code-fast-1", "model_name": "grok-code-fast-1", "display_name": "grok-code-fast-1", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+helicone-registry+llmdb+pricetoken+llm-prices-www+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "tracks": [ { "label": "Context >200K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } }, { "label": "Base pricing", "source": "litellm+llmdb", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.02" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "helicone-registry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.02" }, "message": "cache_read from helicone-registry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.02" }, "message": "cache_read from llmdb conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pricetoken", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from pricetoken conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "pricetoken", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from pricetoken conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from llm-prices-www conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from llm-prices-www conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llm-prices-www", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.02" }, "message": "cache_read from llm-prices-www conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "1", "charge_factors": { "prompt": "2", "completion": "2", "cache_read": "2" }, "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true, "web_search": true, "stream": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "intro": "Speedy and economical reasoning model that excels at agentic coding. Features function calling, structured outputs, and reasoning capabilities.", "knowledge_cutoff": "2024-08", "parameters": { "supported": [ "frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_logprobs", "top_p" ] }, "released_at": "2025-08-28", "family": "grok", "deprecated": true, "status": "deprecated", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "pa/grok-code-fast-1", "x-ai/grok-code-fast-1", "xai/grok-code-fast-1" ], "price_history": [ { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "cache_read", "old": "0.02", "new": "0.2" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "completion", "old": "1.5", "new": "2" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "prompt", "old": "0.2", "new": "1" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "xai/grok-code-fast-1-0825", "model_name": "grok-code-fast-1-0825", "display_name": "grok-code-fast-1-0825", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "litellm+truefoundry+ai-model-directory", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" }, "tracks": [ { "label": "Context >200K", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } }, { "label": "Base pricing", "source": "litellm", "charge_sources": { "prompt": "litellm", "completion": "litellm", "cache_read": "litellm" } } ], "discarded_conflicts": [ { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.02" }, "message": "cache_read from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "1" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.2" }, "message": "prompt from truefoundry conflicts with litellm; the higher-priority value was kept." }, { "kind": "base_charge", "source": "truefoundry", "selected_source": "litellm", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "2" }, "discarded_charge": { "unit": "per_M_tokens", "price": "1.5" }, "message": "completion from truefoundry conflicts with litellm; the higher-priority value was kept." } ], "verification_status": "conflicting" }, "tracks": [ { "label": "Context >200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": false } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ] } ], "docs_url": "https://docs.x.ai/docs/models", "max_input_tokens": 256000, "max_output_tokens": 256000, "model_type": "text_generation", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "pdf_input": true }, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "released_at": "2026-04-16", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "cache_read", "old": "0.02", "new": "0.2" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "completion", "old": "1.5", "new": "2" }, { "date": "2026-08-12", "kind": "price", "provider": "xai", "charge": "prompt", "old": "0.2", "new": "1" }, { "date": "2026-07-02", "kind": "capability", "note": "vision: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "xai/grok-imagine-image", "model_name": "grok-imagine-image", "display_name": "Grok Imagine Image", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "models-dev+truefoundry+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "image_output": { "unit": "per_image", "price": "0.02" }, "image_input": { "unit": "per_image", "price": "0.02" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "image_output": "truefoundry", "image_input": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "verification_status": "cross_checked" }, "provider_model_id": "grok-imagine-image-2026-03-02" } ], "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2026-01-28", "max_input_tokens": 8000, "max_output_tokens": 0, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "image", "pdf" ] }, "family": "grok", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "pdf_input": true, "image_output": true, "stream": true }, "model_type": "image_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-imagine-image-2026-03-02", "xai/grok-imagine-image" ], "intro_i18n": { "zh-CN": "通过文本提示生成图像，用自然语言编辑现有图像，或通过多轮对话迭代优化图像。", "zh-TW": "從文本提示生成圖像，使用自然語言編輯現有圖像，或通過多輪對話迭代優化圖像。", "ja-JP": "テキストプロンプトから画像を生成し、自然言語で既存の画像を編集したり、マルチターン会話を通じて画像を反復的に改良します。", "ru-RU": "Создавайте изображения из текстовых подсказок, редактируйте существующие изображения с помощью естественного языка или итеративно улучшайте изображения через многократные диалоги." }, "price_history": [ { "date": "2026-07-02", "kind": "listed", "note": "Grok Imagine Image" } ] }, { "slug": "xai/grok-imagine-image-pro", "model_name": "grok-imagine-image-pro", "display_name": "grok-imagine-image-pro", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "truefoundry+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "image_output": { "unit": "per_image", "price": "0.07" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" } }, "provenance": { "base_charges": { "prompt": "truefoundry", "image_output": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb" }, "verification_status": "aggregator_only" } } ], "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "xai/grok-imagine-image-pro" ], "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-imagine-image-pro" } ] }, { "slug": "xai/grok-imagine-image-quality", "model_name": "grok-imagine-image-quality", "display_name": "Grok Imagine Image Quality", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "models-dev+truefoundry+lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.05" } }, "provenance": { "base_charges": { "image_output": "truefoundry" }, "verification_status": "cross_checked" }, "provider_model_id": "grok-imagine-image-quality-20260403" } ], "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2026-04-03", "max_input_tokens": 8000, "max_output_tokens": 0, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "image", "pdf" ] }, "family": "grok", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "pdf_input": true, "image_output": true }, "model_type": "image_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-imagine-image-quality-20260403" ], "intro_i18n": { "zh-CN": "根据文本提示生成图像，用自然语言编辑现有图像，或通过多轮对话迭代优化图像。", "zh-TW": "從文本提示生成圖像，使用自然語言編輯現有圖像，或通過多輪對話迭代優化圖像。", "ja-JP": "テキストプロンプトから画像を生成したり、自然言語で既存の画像を編集したり、マルチターン会話を通じて画像を反復的に改良したりします。", "ru-RU": "Генерация изображений из текстовых подсказок, редактирование существующих изображений с помощью естественного языка или итеративное улучшение изображений через многократные взаимодействия." }, "price_history": [ { "date": "2026-07-02", "kind": "listed", "note": "Grok Imagine Image Quality" } ] }, { "slug": "xai/grok-imagine-image-quality-latest", "model_name": "grok-imagine-image-quality-latest", "display_name": "grok-imagine-image-quality-latest", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "image_input": { "unit": "per_image", "price": "0.01" }, "image_output": { "unit": "per_image", "price": "0.05" } }, "provenance": { "base_charges": { "image_input": "truefoundry", "image_output": "truefoundry" }, "verification_status": "aggregator_only" } } ], "modalities": { "input": [ "text", "image" ], "output": [ "image" ] }, "model_type": "image_generation", "capabilities": { "vision": true, "image_output": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "grok-imagine-image-quality-latest" } ] }, { "slug": "xai/grok-imagine-video", "model_name": "grok-imagine-video", "display_name": "Grok Imagine Video", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "models-dev+truefoundry+llmdb+lobehub-modelbank", "charges": { "audio_output": { "unit": "per_second", "price": "0.05" }, "web_search": { "unit": "per_k_calls", "price": "5" }, "x_search": { "unit": "per_k_calls", "price": "5" }, "code_execution": { "unit": "per_k_calls", "price": "5" }, "document_search": { "unit": "per_k_calls", "price": "5" }, "collections_search": { "unit": "per_k_calls", "price": "2.5" }, "video_output": { "unit": "per_second", "price": "0.05" } }, "provenance": { "base_charges": { "audio_output": "truefoundry", "web_search": "llmdb", "x_search": "llmdb", "code_execution": "llmdb", "document_search": "llmdb", "collections_search": "llmdb", "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2026-01-28", "max_input_tokens": 1024, "max_output_tokens": 0, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "video" ] }, "family": "grok", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "prompt_caching": true, "video_input": true, "pdf_input": true }, "model_type": "video_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "xai/grok-imagine-video" ], "intro_i18n": { "zh-CN": "在质量、成本和延迟方面的最先进视频生成技术。", "zh-TW": "在質量、成本及延遲方面的最先進影像生成技術。", "ja-JP": "品質、コスト、遅延のすべてにおいて最先端のビデオ生成。", "ru-RU": "Передовая генерация видео с учетом качества, стоимости и задержки." }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-02", "kind": "listed", "note": "Grok Imagine Video" } ] }, { "slug": "xai/grok-imagine-video-1.5", "model_name": "grok-imagine-video-1.5", "display_name": "Grok Imagine Video 1.5", "vendor": "xai", "pricing": [ { "provider": "xai", "provider_name": "xAI", "official": true, "source": "models-dev+truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.08" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" }, "provider_model_id": "grok-imagine-video-1.5-2026-05-30" } ], "intro": "Video model for image-to-video generation, editing, and extension workflows", "released_at": "2026-05-30", "max_input_tokens": 1024, "max_output_tokens": 0, "modalities": { "input": [ "text", "image", "audio", "pdf" ], "output": [ "video" ] }, "family": "grok", "parameters": { "unsupported": [ "temperature" ] }, "capabilities": { "vision": true, "audio_input": true, "pdf_input": true }, "model_type": "video_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "grok-imagine-video-1.5-2026-05-30", "xai/grok-imagine-video-1.5" ], "price_history": [ { "date": "2026-08-01", "kind": "capability", "note": "audio_input: false→true" }, { "date": "2026-07-25", "kind": "listed", "note": "Grok Imagine Video 1.5" } ] }, { "slug": "xai/grok-imagine-video-1.5-preview", "model_name": "grok-imagine-video-1.5-preview", "display_name": "Grok Imagine Video 1.5 Preview", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "audio_output": { "unit": "per_second", "price": "0.08" } }, "provenance": { "base_charges": { "audio_output": "truefoundry" }, "verification_status": "aggregator_only" } } ], "modalities": { "input": [ "text", "image" ], "output": [ "video" ] }, "model_type": "video_generation", "capabilities": { "vision": true, "prompt_caching": true }, "intro": "Image model for prompt-driven generation, editing, and visual design workflows", "released_at": "2026-05-30", "max_input_tokens": 0, "max_output_tokens": 0, "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "xai/grok-imagine-video-1.5-preview" ], "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "Grok Imagine Video 1.5 Preview" } ] }, { "slug": "xai/grok-latest", "model_name": "grok-latest", "display_name": "Grok Latest", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "truefoundry", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "prompt": { "unit": "per_M_tokens", "price": "1.25" }, "completion": { "unit": "per_M_tokens", "price": "2.5" } }, "provenance": { "base_charges": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" }, "tracks": [ { "label": "Batch", "source": "truefoundry", "charge_sources": { "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Context ≥200K", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } }, { "label": "Base pricing", "source": "truefoundry", "charge_sources": { "cache_read": "truefoundry", "prompt": "truefoundry", "completion": "truefoundry" } } ], "verification_status": "aggregator_only" }, "tracks": [ { "label": "Batch", "factor": "1", "charge_factors": { "prompt": "0.8", "completion": "0.8" }, "triggers": [ { "kind": "endpoint_matches", "pattern": "^batch\\." } ] }, { "label": "Context ≥200K", "factor": "2", "triggers": [ { "kind": "input_tokens_above", "threshold": 200000, "inclusive": true } ] }, { "label": "Base pricing", "factor": "1", "triggers": [] } ], "warnings": [ { "code": "unresolved_track_combination", "service_tier": "batch", "source": "truefoundry", "message": "batch pricing and context tiers are both published, but no exact combined batch + context prices were provided." } ] } ], "max_input_tokens": 1000000, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "model_type": "vision_understanding", "capabilities": { "function_calling": true, "parallel_function_calling": true, "structured_output": true, "prompt_caching": true, "reasoning": true, "vision": true, "pdf_input": true }, "intro": "Grok model for agentic tool use, reasoning, coding, and live assistance", "released_at": "2026-05-03", "max_output_tokens": 500000, "family": "grok", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "x-ai/grok-latest", "~x-ai/grok-latest" ], "price_history": [ { "date": "2026-08-03", "kind": "limit", "old": "1000000", "new": "500000", "note": "max_output_tokens" }, { "date": "2026-07-03", "kind": "listed", "note": "grok-latest" } ] }, { "slug": "xai/grok-vision-beta", "model_name": "grok-vision-beta", "display_name": "grok-vision-beta", "vendor": "xai", "pricing": [ { "provider": "xai", "official": true, "source": "litellm", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "15" }, "image_input": { "unit": "per_image", "price": "0.000005" } }, "provenance": { "base_charges": { "prompt": "litellm", "completion": "litellm", "image_input": "litellm" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 8192, "max_output_tokens": 8192, "model_type": "vision_understanding", "capabilities": { "vision": true, "function_calling": true, "pdf_input": true, "web_search": true }, "modalities": { "input": [ "image", "text" ], "output": [] }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "x-ai/grok-vision-beta" ], "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "pdf_input: false→true" } ] }, { "slug": "xiaomi/mimo-v2-flash", "model_name": "mimo-v2-flash", "display_name": "MiMo-V2-Flash", "vendor": "xiaomi", "pricing": [ { "provider": "xiaomi", "provider_name": "Xiaomi", "official": true, "source": "models-dev+llmdb", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.14" }, "completion": { "unit": "per_M_tokens", "price": "0.28" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0028" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.14" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1" }, "message": "prompt from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.28" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.3" }, "message": "completion from llmdb conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "llmdb", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.0028" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.01" }, "message": "cache_read from llmdb conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Legacy model retained for compatibility with older integrations", "released_at": "2025-12-16", "knowledge_cutoff": "2024-12", "max_input_tokens": 262144, "max_output_tokens": 65536, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mimo", "status": "deprecated", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true, "parallel_function_calling": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "XiaomiMiMo/MiMo-V2-Flash", "mimo-v2-flash-free", "xiaomi/mimo-v2-flash", "xiaomimimo/mimo-v2-flash" ], "price_history": [ { "date": "2026-08-02", "kind": "capability", "note": "web_search: true→false" }, { "date": "2026-07-03", "kind": "listed", "note": "MiMo-V2-Flash" } ] }, { "slug": "xiaomi/mimo-v2-omni", "model_name": "mimo-v2-omni", "display_name": "MiMo-V2-Omni", "vendor": "xiaomi", "pricing": [ { "provider": "xiaomi", "provider_name": "Xiaomi", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.14" }, "completion": { "unit": "per_M_tokens", "price": "0.28" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0028" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Legacy model retained for compatibility with older integrations", "released_at": "2026-03-18", "knowledge_cutoff": "2024-12", "max_input_tokens": 262144, "max_output_tokens": 131072, "deprecated": true, "modalities": { "input": [ "text", "image", "audio", "video", "pdf" ], "output": [ "text" ] }, "family": "mimo", "status": "deprecated", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "open_weights": true, "pdf_input": true }, "model_type": "omni", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mimo-v2-omni-free", "xiaomi/mimo-v2-omni" ], "price_history": [ { "date": "2026-07-12", "kind": "capability", "note": "structured_output: true→false" }, { "date": "2026-07-03", "kind": "listed", "note": "MiMo-V2-Omni" } ] }, { "slug": "xiaomi/mimo-v2-pro", "model_name": "mimo-v2-pro", "display_name": "MiMo-V2-Pro", "vendor": "xiaomi", "pricing": [ { "provider": "xiaomi", "provider_name": "Xiaomi", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.435" }, "completion": { "unit": "per_M_tokens", "price": "0.87" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0036" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Earlier MiMo Pro model for multimodal agents, reasoning, and code tasks", "released_at": "2026-03-18", "knowledge_cutoff": "2024-12", "max_input_tokens": 1048576, "max_output_tokens": 131072, "deprecated": true, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mimo", "status": "deprecated", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true }, "model_type": "text_generation", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "MiMo-V2-Pro", "mimo-v2-pro-free", "xiaomi/mimo-v2-pro", "xiaomimimo/mimo-v2-pro" ], "intro_i18n": { "zh-CN": "MiMo-V2-Pro 专为真实世界中的高强度智能体工作流设计。其总参数量超过 1 万亿（激活参数 42B），采用创新的混合注意力架构，支持超长上下文长度（最高 100 万 tokens）。基于强大的基础模型，我们持续在更广泛的智能体场景中扩展算力，进一步拓展智能的行动空间，在从编码到真实任务执行（“钳爪”）等方面实现显著泛化。", "zh-TW": "MiMo-V2-Pro 專為真實場景中的高強度智能體工作流設計，總參數規模超過 1 兆（啟用參數 42B），採用創新的混合注意力架構，並支援高達 100 萬 token 的超長脈絡。基於強大的基礎模型，我們持續在更多智能體場景擴大計算規模，拓展智能行為空間，並在從編碼到實體任務執行（「claw」）的多領域展現卓越泛化能力。", "ja-JP": "MiMo-V2-Pro は実世界の高負荷エージェントワークフロー向けに設計されています。総パラメータは 1 兆超（42B アクティブ）で、革新的なハイブリッドアテンション構造を採用し、最大 100 万トークンの超長コンテキストをサポートします。強力な基盤モデルをもとに、幅広いエージェントシナリオで計算資源を拡張し、知能の行動範囲を拡大して、コーディングから実世界タスク実行（「claw」）まで高い汎化能力を発揮します。", "ru-RU": "MiMo-V2-Pro специально создана для высокоинтенсивных агентных рабочих процессов в реальных условиях. Содержит более 1 триллиона общих параметров (42B активных), использует гибридную архитектуру внимания и поддерживает сверхдлинный контекст до 1 миллиона токенов. На основе мощной базовой модели мы постепенно масштабируем вычислительные ресурсы под более широкий спектр агентных сценариев, расширяя пространство действий и достигая значительной обобщающей способности — от кодирования до выполнения реальных задач («claw»)." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "MiMo-V2-Pro" } ] }, { "slug": "xiaomi/mimo-v2.5", "model_name": "mimo-v2.5", "display_name": "MiMo-V2.5", "vendor": "xiaomi", "pricing": [ { "provider": "xiaomi", "provider_name": "Xiaomi", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.14" }, "completion": { "unit": "per_M_tokens", "price": "0.28" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0028" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Open MiMo model for multimodal coding agents and long-context automation", "released_at": "2026-04-22", "knowledge_cutoff": "2024-12", "max_input_tokens": 1048576, "max_output_tokens": 131072, "modalities": { "input": [ "text", "image", "audio", "video" ], "output": [ "text" ] }, "family": "mimo", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "web_search": true }, "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 38, "coding_index": 56.8, "agentic_index": 24.4 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "XiaomiMiMo/MiMo-V2.5", "cline-pass/mimo-v2.5", "deepinfra/XiaomiMiMo/MiMo-V2.5", "mimo-v2-5", "mimo-v2-5:free", "mimo-v2.5-free", "xiaomi/mimo-v2.5", "xiaomi/mimo-v2.5:thinking", "xiaomimimo/mimo-v2.5" ], "intro_i18n": { "zh-CN": "MiMo-V2.5 是原生全模态 Agent 基础模型，能够在统一架构下理解图像、视频、音频与文本，具备 100 万上下文窗口。以约 MiMo-V2.5-Pro 一半成本提供接近 Pro 级的 Agent 能力，并在多模态感知上显著优于 MiMo-V2-Omni。其内置 Agent 能力（浏览、理解、推理、执行）与更快推理速度，使其非常适合 OpenClaw 等对延迟敏感的多步 Agent 框架。", "zh-TW": "MiMo-V2.5 是原生全模態代理基座模型，以統一架構理解圖片、影片、音訊與文本，具備 100 萬上下文。其代理能力（瀏覽、理解、推理、執行）與更快的推理速度，使其非常適合 OpenClaw 等重視延遲與多步推理的代理框架。", "ja-JP": "MiMo-V2.5は、画像、動画、音声、テキストを統一アーキテクチャで理解するネイティブオムニモーダルエージェント基盤モデルであり、1Mコンテキストウィンドウを備えています。MiMo-V2.5-Proの約半分の推論コストでプロレベルのエージェント性能を提供し、MiMo-V2-Omniよりもマルチモーダル認識が向上しています。組み込みのエージェント能力（ブラウジング、理解、推論、実行）と高速な推論により、OpenClawなどのレイテンシーに敏感なマルチステップエージェントフレームワークに適しています。", "ru-RU": "MiMo-V2.5 — нативная омнимодальная агентная модель, понимающая изображения, видео, аудио и текст в единой архитектуре с контекстом 1M. Обеспечивает производительность уровня Pro примерно за половину стоимости MiMo-V2.5-Pro и улучшенную мультимодальную перцепцию по сравнению с MiMo-V2-Omni. Благодаря встроенным агентным возможностям (обзор, понимание, рассуждение, выполнение) и более быстрой инференции отлично подходит для сценариев с низкой задержкой и многошаговых агентных фреймворков, таких как OpenClaw." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "MiMo-V2.5" } ] }, { "slug": "xiaomi/mimo-v2.5-pro", "model_name": "mimo-v2.5-pro", "display_name": "MiMo-V2.5-Pro", "vendor": "xiaomi", "pricing": [ { "provider": "xiaomi", "provider_name": "Xiaomi", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.435" }, "completion": { "unit": "per_M_tokens", "price": "0.87" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0036" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Stronger MiMo Pro tier for multimodal reasoning and coding-agent execution", "released_at": "2026-04-22", "knowledge_cutoff": "2024-12", "max_input_tokens": 1048576, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mimo", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "web_search": true }, "model_type": "deep_thinking", "benchmarks": { "intelligence_index": 42.9, "coding_index": 60.2, "agentic_index": 29.5 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "MiMo-V2.5-Pro", "XiaomiMiMo/MiMo-V2.5-Pro", "cline-pass/mimo-v2.5-pro", "deepinfra/XiaomiMiMo/MiMo-V2.5-Pro", "mimo-v2-5-pro", "xiaomi/mimo-v2.5-pro", "xiaomi/mimo-v2.5-pro:thinking", "xiaomimimo/mimo-v2.5-pro" ], "intro_i18n": { "zh-CN": "MiMo-V2.5-Pro 是小米迄今最强旗舰模型，在通用 Agent 能力、复杂软件工程与长程任务方面大幅提升。延续 1T 总参数 / 42B 激活的混合注意力架构与 100 万上下文窗口，可完成包含上千次工具调用的长链任务。在 ClawEval、GDPVal、SWE-bench Pro 等高难 Agent 基准上表现可比 Claude Opus 4.6。", "zh-TW": "MiMo-V2.5-Pro 是小米迄今最強大的旗艦模型，在通用代理能力、複雜軟體工程與長程任務上有重大提升。延續 1T 總參數 / 42B 啟動參數的混合注意力架構與 100 萬上下文，可處理上千次工具調用的長程任務。在 ClawEval、GDPVal、SWE-bench Pro 等高難度代理基準中表現接近 Claude Opus 4.6。", "ja-JP": "MiMo-V2.5-Proは、Xiaomiのこれまでで最も能力の高いフラッグシップモデルであり、一般的なエージェント能力、複雑なソフトウェアエンジニアリング、長期的なタスクにおいて大幅な改善を提供します。1T総パラメータ/42Bアクティブハイブリッドアテンションアーキテクチャを維持し、1Mコンテキストウィンドウを備えています。ClawEval、GDPVal、SWE-bench Proなどの要求の厳しいエージェントベンチマークでClaude Opus 4.6に匹敵する性能を発揮します。", "ru-RU": "MiMo-V2.5-Pro — самая мощная флагманская модель Xiaomi на сегодняшний день. Существенно улучшены общие агентные способности, сложная разработка ПО и долгосрочные задачи. Она сохраняет гибридную архитектуру с 1T общих / 42B активных параметров и поддержкой контекста 1M. Модель способна выполнять сложные долгосрочные задачи с более чем 1000 вызовов инструментов. Её производительность в сложных агентных бенчмарках (ClawEval, GDPVal, SWE-bench Pro) сопоставима с Claude Opus 4.6." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.11291715", "new": "3.11391381" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.03763905", "new": "1.03797127" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.11340393", "new": "3.11291715" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.03780131", "new": "1.03763905" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.11315088", "new": "3.11340393" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.03771696", "new": "1.03780131" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.11220819", "new": "3.11315088" }, { "date": "2026-08-11", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.03740273", "new": "1.03771696" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.11198223", "new": "3.11220819" }, { "date": "2026-08-10", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.03732741", "new": "1.03740273" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.11232348", "new": "3.11198223" }, { "date": "2026-08-09", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.03744116", "new": "1.03732741" }, { "date": "2026-08-08", "kind": "price", "provider": "kilo", "charge": "cache_read", "old": "0.004", "new": "0.08" }, { "date": "2026-08-08", "kind": "price", "provider": "kilo", "charge": "completion", "old": "0.87", "new": "1.5" }, { "date": "2026-08-08", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "0.435", "new": "0.4" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.11237388", "new": "3.11232348" }, { "date": "2026-08-08", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.03745796", "new": "1.03744116" }, { "date": "2026-08-08", "kind": "price", "provider": "zenmux", "charge": "web_search", "old": "4.94318", "new": "5" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "completion", "old": "3.11213133", "new": "3.11237388" }, { "date": "2026-08-07", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.03737711", "new": "1.03745796" } ] }, { "slug": "xiaomi/mimo-v2.5-pro-ultraspeed", "model_name": "mimo-v2.5-pro-ultraspeed", "display_name": "MiMo-V2.5-Pro-UltraSpeed", "vendor": "xiaomi", "pricing": [ { "provider": "xiaomi", "provider_name": "Xiaomi", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.305" }, "completion": { "unit": "per_M_tokens", "price": "2.61" }, "cache_read": { "unit": "per_M_tokens", "price": "0.0108" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "MiMo pro model for strong multimodal reasoning and agent execution", "released_at": "2026-06-08", "knowledge_cutoff": "2024-12", "max_input_tokens": 1048576, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "mimo", "status": "beta", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "mimo-v2-5-pro-ultraspeed", "xiaomi/mimo-v2.5-pro-ultraspeed" ], "model_type": "text_generation", "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "MiMo-V2.5-Pro-UltraSpeed" } ] }, { "slug": "zhipuai/charglm-4", "model_name": "charglm-4", "display_name": "CharGLM-4", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.147059" }, "completion": { "unit": "per_M_tokens", "price": "0.147059" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 8192, "max_output_tokens": 4000, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "CharGLM-4 专为角色扮演和情感陪伴设计，支持超长多轮记忆和个性化对话。", "zh-TW": "CharGLM-4 專為角色扮演與情感陪伴設計，支援超長多輪記憶與個性化對話。", "ja-JP": "CharGLM-4は、ロールプレイと感情的な対話を目的に設計されており、超長期のマルチターン記憶とパーソナライズされた会話をサポートします。", "ru-RU": "CharGLM-4 создана для ролевых игр и эмоционального общения, поддерживает сверхдолгую многотуровую память и персонализированный диалог." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "CharGLM-4" } ] }, { "slug": "zhipuai/codegeex-4", "model_name": "codegeex-4", "display_name": "CodeGeeX-4", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.014706" }, "completion": { "unit": "per_M_tokens", "price": "0.014706" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "CodeGeeX-4 是一款强大的 AI 编程助手，支持多语言问答和代码补全，提升开发者效率。", "zh-TW": "CodeGeeX-4 是一款強大的 AI 程式輔助工具，支援多語言問答與程式碼補全，能有效提升開發者的生產力。", "ja-JP": "CodeGeeX-4は、開発者の生産性を向上させる多言語対応のAIコーディングアシスタントで、Q&Aやコード補完をサポートします。", "ru-RU": "CodeGeeX-4 — мощный AI-помощник для программирования, поддерживающий многоязычные вопросы и автодополнение кода для повышения продуктивности разработчиков." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "CodeGeeX-4" } ] }, { "slug": "zhipuai/cogvideox-2", "model_name": "cogvideox-2", "display_name": "CogVideoX-2", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_request", "price": "0.073529" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "CogVideoX-2是智谱推出的新一代视频生成基础模型，图像转视频能力提升38%。在大规模动作处理、视觉稳定性、指令遵循性、艺术风格和整体视觉美感方面实现了显著增强。", "zh-TW": "CogVideoX-2是智譜新一代影像生成基礎模型，影像生成能力提升38%。在大規模動作處理、視覺穩定性、指令遵循性、藝術風格及整體視覺美學方面有顯著增強。", "ja-JP": "CogVideoX-2は、Zhipuの新世代ビデオ生成基盤モデルで、画像からビデオへの変換能力が38%向上しました。大規模な動きの処理、視覚的安定性、指示の遵守、芸術的スタイル、全体的な視覚美学において大幅な改善を実現します。", "ru-RU": "CogVideoX-2 — новая модель генерации видео от Zhipu, с улучшением возможностей преобразования изображения в видео на 38%. Она обеспечивает значительные улучшения в обработке крупномасштабных движений, визуальной стабильности, следовании инструкциям, художественном стиле и общей визуальной эстетике." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "CogVideoX-2" } ] }, { "slug": "zhipuai/cogvideox-3", "model_name": "cogvideox-3", "display_name": "CogVideoX-3", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_request", "price": "0.147059" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-07-15", "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "CogVideoX-3新增起始帧和结束帧生成功能，大幅提升视觉稳定性和清晰度。支持平滑自然的大规模主体运动，提供更好的指令遵循性和更真实的物理模拟，并进一步提升高清真实感和3D风格场景的表现能力。", "zh-TW": "CogVideoX-3新增起始及結束影格生成功能，顯著提升視覺穩定性及清晰度。實現流暢自然的大規模主題動作，提供更好的指令遵循性及更真實的物理模擬，並進一步提升高解析度真實及3D風格場景的性能。", "ja-JP": "CogVideoX-3は、開始フレームと終了フレームの生成機能を追加し、視覚的安定性と明瞭性を大幅に向上させます。滑らかで自然な大規模な被写体の動きを可能にし、指示の遵守とより現実的な物理シミュレーションを提供します。高精細なリアルなシーンや3Dスタイルのシーンでのパフォーマンスをさらに向上させます。", "ru-RU": "CogVideoX-3 добавляет функцию генерации начальных и конечных кадров, значительно улучшая визуальную стабильность и четкость. Она обеспечивает плавные и естественные крупномасштабные движения объектов, лучшее следование инструкциям и более реалистичную физическую симуляцию, а также улучшает производительность в высококачественных реалистичных и 3D-стилях." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "CogVideoX-3" } ] }, { "slug": "zhipuai/cogvideox-flash", "model_name": "cogvideox-flash", "display_name": "CogVideoX-Flash", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "video_output": { "unit": "per_request", "price": "0" } }, "provenance": { "base_charges": { "video_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "model_type": "video_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "CogVideoX-Flash是智谱发布的免费视频生成模型，能够生成遵循用户指令的视频，同时实现更高的美学质量评分。", "zh-TW": "CogVideoX-Flash是智譜發布的免費影像生成模型，能生成符合用戶指令的影像，同時達到更高的美學質量分數。", "ja-JP": "CogVideoX-Flashは、Zhipuがリリースした無料のビデオ生成モデルで、ユーザーの指示に従いながら、より高い美的品質スコアを達成するビデオを生成できます。", "ru-RU": "CogVideoX-Flash — бесплатная модель генерации видео от Zhipu, способная создавать видео, следуя инструкциям пользователя, с достижением более высоких оценок эстетического качества." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "CogVideoX-Flash" } ] }, { "slug": "zhipuai/cogview-3-flash", "model_name": "cogview-3-flash", "display_name": "CogView-3-Flash", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "CogView-3-Flash 是智谱推出的免费图像生成模型。它能够根据用户指令生成与之匹配的图像，同时实现更高的美学质量评分。CogView-3-Flash 主要应用于艺术创作、设计参考、游戏开发和虚拟现实等领域，帮助用户快速将文本描述转化为图像。", "zh-TW": "CogView-3-Flash 是智譜推出的免費圖像生成模型。它能根據使用者指令生成符合要求的圖像，同時達到更高的美學品質分數。CogView-3-Flash 主要應用於藝術創作、設計參考、遊戲開發和虛擬現實等領域，幫助使用者快速將文字描述轉換為圖像。", "ja-JP": "CogView-3-Flashは、Zhipuが提供する無料の画像生成モデルです。ユーザーの指示に沿った画像を生成し、より高い美的品質スコアを実現します。CogView-3-Flashは主に、芸術的創作、デザインの参考、ゲーム開発、仮想現実などの分野で使用され、テキストの説明を迅速に画像に変換することを支援します。", "ru-RU": "CogView-3-Flash — это бесплатная модель генерации изображений, запущенная Zhipu. Она создает изображения, соответствующие инструкциям пользователя, при этом достигая более высоких оценок эстетического качества. CogView-3-Flash в основном используется в таких областях, как художественное творчество, дизайн, разработка игр и виртуальная реальность, помогая пользователям быстро преобразовывать текстовые описания в изображения." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "CogView-3-Flash" } ] }, { "slug": "zhipuai/cogview-4", "model_name": "cogview-4", "display_name": "CogView-4", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.008824" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-03-04", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "CogView-4 是智谱推出的首个支持中文字符生成的开源文生图模型，提升了语义理解、图像质量和中英文文本渲染能力，支持任意长度的中英文提示词，并可在指定范围内生成任意分辨率图像。", "zh-TW": "CogView-4 是智譜推出的首款開源文字轉圖像模型，支援中文字符生成。它提升了語意理解、圖像品質與中英文文字渲染能力，支援任意長度的雙語提示詞，並可在指定範圍內生成任意解析度的圖像。", "ja-JP": "CogView-4はZhipuが開発した初のオープンソースのテキストから画像への生成モデルであり、中国語の文字生成に対応しています。意味理解、画像品質、中英テキストの描画能力が向上し、任意の長さのバイリンガルプロンプトをサポートし、指定範囲内で任意の解像度の画像を生成できます。", "ru-RU": "CogView-4 — первая открытая модель от Zhipu для генерации изображений по тексту с поддержкой китайских иероглифов. Улучшает семантическое понимание, качество изображений и рендеринг текста на китайском и английском языках, поддерживает произвольную длину двуязычных подсказок и может генерировать изображения в любом разрешении в заданных пределах." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "CogView-4" } ] }, { "slug": "zhipuai/emohaa", "model_name": "emohaa", "display_name": "Emohaa", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "2.205882" }, "completion": { "unit": "per_M_tokens", "price": "2.205882" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 8192, "max_output_tokens": 4000, "model_type": "text_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "Emohaa 是一款心理健康模型，具备专业咨询能力，帮助用户理解情绪问题。", "zh-TW": "Emohaa 是一款心理健康模型，具備專業諮詢能力，協助使用者理解情緒問題。", "ja-JP": "Emohaa は、専門的なカウンセリング能力を備えたメンタルヘルスモデルで、ユーザーが感情的な問題を理解するのを支援します。", "ru-RU": "Emohaa — модель для поддержки психического здоровья с профессиональными навыками консультирования, помогающая пользователям разобраться в эмоциональных проблемах." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "Emohaa" } ] }, { "slug": "zhipuai/glm-4-0520", "model_name": "glm-4-0520", "display_name": "GLM-4-0520", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "14.705882" }, "completion": { "unit": "per_M_tokens", "price": "14.705882" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4-0520 是最新版本模型，专为处理高度复杂与多样化任务而设计，性能卓越。", "zh-TW": "GLM-4-0520 是最新版本模型，專為高度複雜與多樣化任務設計，具備卓越效能。", "ja-JP": "GLM-4-0520 は最新バージョンのモデルで、非常に複雑かつ多様なタスクに対応し、優れた性能を発揮します。", "ru-RU": "GLM-4-0520 — последняя версия модели, разработанная для сложных и разнообразных задач с отличной производительностью." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-4-0520" } ] }, { "slug": "zhipuai/glm-4-air-250414", "model_name": "glm-4-air-250414", "display_name": "GLM-4-Air-250414", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.073529" }, "completion": { "unit": "per_M_tokens", "price": "0.073529" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 16384, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4-Air 是一款高性价比模型，性能接近 GLM-4，速度快、成本低。", "zh-TW": "GLM-4-Air 是一款高性價比選擇，效能接近 GLM-4，速度快且成本低。", "ja-JP": "GLM-4-Air は、GLM-4 に近い性能を持ちながら、高速かつ低コストで利用できる高コストパフォーマンスモデルです。", "ru-RU": "GLM-4-Air — выгодный вариант с производительностью, близкой к GLM-4, высокой скоростью и низкой стоимостью." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-4-Air-250414" } ] }, { "slug": "zhipuai/glm-4-airx", "model_name": "glm-4-airx", "display_name": "GLM-4-AirX", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.470588" }, "completion": { "unit": "per_M_tokens", "price": "1.470588" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 8192, "max_output_tokens": 4095, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2024-01-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4-AirX 是 GLM-4-Air 的高效变体，推理速度提升至 2.6 倍。", "zh-TW": "GLM-4-AirX 是 GLM-4-Air 的高效版本，推理速度提升至 2.6 倍。", "ja-JP": "GLM-4-AirX は、GLM-4-Air のより効率的なバリアントで、最大2.6倍の高速推論を実現します。", "ru-RU": "GLM-4-AirX — более эффективный вариант GLM-4-Air с ускорением рассуждений до 2.6 раз." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "GLM-4-AirX" } ] }, { "slug": "zhipuai/glm-4-flash-250414", "model_name": "glm-4-flash-250414", "display_name": "GLM-4-Flash-250414", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4-Flash 适用于简单任务：速度最快且免费。", "zh-TW": "GLM-4-Flash 適合簡單任務：速度最快且免費。", "ja-JP": "GLM-4-Flash は、シンプルなタスクに最適：最速かつ無料で利用可能です。", "ru-RU": "GLM-4-Flash идеально подходит для простых задач: самая быстрая и бесплатная." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-4-Flash-250414" } ] }, { "slug": "zhipuai/glm-4-flashx", "model_name": "glm-4-flashx", "display_name": "GLM-4-FlashX-250414", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.014706" }, "completion": { "unit": "per_M_tokens", "price": "0.014706" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 4095, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4-FlashX 是 Flash 的增强版，具备超快推理能力。", "zh-TW": "GLM-4-FlashX 是 Flash 的增強版，具備超快推理能力。", "ja-JP": "GLM-4-FlashX は、超高速推論を実現した Flash の強化版です。", "ru-RU": "GLM-4-FlashX — улучшенная версия Flash с ультрабыстрым рассуждением." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-4-FlashX-250414" } ] }, { "slug": "zhipuai/glm-4-long", "model_name": "glm-4-long", "display_name": "GLM-4-Long", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.147059" }, "completion": { "unit": "per_M_tokens", "price": "0.147059" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 1024000, "max_output_tokens": 4095, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2024-01-01", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4-Long 支持超长输入，适用于记忆类任务与大规模文档处理。", "zh-TW": "GLM-4-Long 支援超長輸入，適用於記憶型任務與大規模文件處理。", "ja-JP": "GLM-4-Long は、記憶型タスクや大規模文書処理のための超長文入力をサポートします。", "ru-RU": "GLM-4-Long поддерживает сверхдлинные входные данные для задач, связанных с памятью, и обработки больших документов." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "GLM-4-Long" } ] }, { "slug": "zhipuai/glm-4-plus", "model_name": "glm-4-plus", "display_name": "GLM-4-Plus", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.735294" }, "completion": { "unit": "per_M_tokens", "price": "0.735294" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 4095, "model_type": "text_generation", "capabilities": { "function_calling": true, "web_search": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2024-09-20", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4-Plus 是一款高智能旗舰模型，具备强大的长文本与复杂任务处理能力，整体性能全面升级。", "zh-TW": "GLM-4-Plus 是高智能旗艦模型，擅長處理長文本與複雜任務，整體效能全面升級。", "ja-JP": "GLM-4-Plus は、高度な知能を備えたフラッグシップモデルで、長文や複雑なタスク処理に強く、全体的な性能が向上しています。", "ru-RU": "GLM-4-Plus — флагманская модель с высоким уровнем интеллекта, сильной поддержкой длинных текстов и сложных задач, а также улучшенной общей производительностью." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "GLM-4-Plus" } ] }, { "slug": "zhipuai/glm-4.1v-thinking-flash", "model_name": "glm-4.1v-thinking-flash", "display_name": "GLM-4.1V-Thinking-Flash", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 65536, "max_output_tokens": 32768, "model_type": "deep_thinking", "capabilities": { "reasoning": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-07-09", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4.1V-Thinking 是目前已知最强的约 100 亿参数视觉语言模型，覆盖视频理解、图像问答、学科解题、OCR、文档与图表阅读、GUI 智能体、前端编程与视觉定位等 SOTA 任务。通过先进的强化学习，采用思维链推理提升准确性与丰富性，在结果与可解释性方面均优于传统非思考模型。", "zh-TW": "GLM-4.1V-Thinking 是目前已知最強的約 10B 視覺語言模型，涵蓋影片理解、圖像問答、學科解題、OCR、文件與圖表閱讀、GUI 智能體、前端編碼與語義對齊等 SOTA 任務。透過先進強化學習與思考鏈推理，提升準確性與豐富度，超越傳統非思考模型的結果與可解釋性。", "ja-JP": "GLM-4.1V-Thinking は、既知の中で最も強力な約10Bの視覚言語モデル（VLM）で、動画理解、画像Q&A、科目解答、OCR、文書・チャート読解、GUIエージェント、フロントエンドコーディング、グラウンディングなどの最先端タスクに対応します。Qwen2.5-VL-72B（8倍のサイズ）を多くのタスクで上回ります。高度な強化学習（RL）により、思考の連鎖（Chain-of-Thought）推論を活用し、精度と情報の豊かさを向上させ、従来の非思考モデルを成果と説明性の両面で凌駕します。", "ru-RU": "GLM-4.1V-Thinking — самая мощная известная ~10B VLM, охватывающая передовые задачи, такие как понимание видео, визуальные вопросы и ответы, решение предметных задач, OCR, чтение документов и графиков, GUI-агенты, фронтенд-кодирование и привязка. Превосходит даже 8 раз более крупную Qwen2.5-VL-72B по многим задачам. Использует цепочку рассуждений для повышения точности и объяснимости, превосходя традиционные модели без мышления." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "GLM-4.1V-Thinking-Flash" } ] }, { "slug": "zhipuai/glm-4.1v-thinking-flashx", "model_name": "glm-4.1v-thinking-flashx", "display_name": "GLM-4.1V-Thinking-FlashX", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.294118" }, "completion": { "unit": "per_M_tokens", "price": "0.294118" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 65536, "max_output_tokens": 32768, "model_type": "deep_thinking", "capabilities": { "reasoning": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-07-09", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4.1V-Thinking 是目前已知最强的约 100 亿参数视觉语言模型，覆盖视频理解、图像问答、学科解题、OCR、文档与图表阅读、GUI 智能体、前端编程与视觉定位等 SOTA 任务。通过先进的强化学习，采用思维链推理提升准确性与丰富性，在结果与可解释性方面均优于传统非思考模型。", "zh-TW": "GLM-4.1V-Thinking 是目前已知最強的約 10B 視覺語言模型，涵蓋影片理解、圖像問答、學科解題、OCR、文件與圖表閱讀、GUI 智能體、前端編碼與語義對齊等 SOTA 任務。透過先進強化學習與思考鏈推理，提升準確性與豐富度，超越傳統非思考模型的結果與可解釋性。", "ja-JP": "GLM-4.1V-Thinking は、既知の中で最も強力な約10Bの視覚言語モデル（VLM）で、動画理解、画像Q&A、科目解答、OCR、文書・チャート読解、GUIエージェント、フロントエンドコーディング、グラウンディングなどの最先端タスクに対応します。Qwen2.5-VL-72B（8倍のサイズ）を多くのタスクで上回ります。高度な強化学習（RL）により、思考の連鎖（Chain-of-Thought）推論を活用し、精度と情報の豊かさを向上させ、従来の非思考モデルを成果と説明性の両面で凌駕します。", "ru-RU": "GLM-4.1V-Thinking — самая мощная известная ~10B VLM, охватывающая передовые задачи, такие как понимание видео, визуальные вопросы и ответы, решение предметных задач, OCR, чтение документов и графиков, GUI-агенты, фронтенд-кодирование и привязка. Превосходит даже 8 раз более крупную Qwen2.5-VL-72B по многим задачам. Использует цепочку рассуждений для повышения точности и объяснимости, превосходя традиционные модели без мышления." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "GLM-4.1V-Thinking-FlashX" } ] }, { "slug": "zhipuai/glm-4.5", "model_name": "glm-4.5", "display_name": "GLM-4.5", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.11" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "cache_read_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "0.058824" }, "cache_read_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "0.088235" }, "cache_read_0_032_0_128": { "unit": "per_M_tokens", "price": "0.117647" }, "prompt_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "0.294118" }, "prompt_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "0.441176" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.588235" }, "completion_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "1.176471" }, "completion_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "2.058824" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "2.352941" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_read_0_0_032_0_0_0002": "lobehub-modelbank", "cache_read_0_0_032_0_0002_infinity": "lobehub-modelbank", "cache_read_0_032_0_128": "lobehub-modelbank", "prompt_0_0_032_0_0_0002": "lobehub-modelbank", "prompt_0_0_032_0_0002_infinity": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "completion_0_0_032_0_0_0002": "lobehub-modelbank", "completion_0_0_032_0_0002_infinity": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank" }, "verification_status": "cross_checked" } } ], "intro": "Hybrid-reasoning GLM release that made the 4.5 line broadly useful", "released_at": "2025-07-28", "knowledge_cutoff": "2025-04", "max_input_tokens": 131072, "max_output_tokens": 98304, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "deprecated": true, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "defaults": { "temperature": 0.75 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "GLM-4.5", "ZhipuAI/GLM-4.5", "deepinfra/zai-org/GLM-4.5", "z-ai/glm-4.5", "zai-org/GLM-4.5", "zai-org/GLM-4.5:thinking", "zai-org/glm-4.5", "zai/GLM-4.5", "zai/glm-4.5" ], "intro_i18n": { "zh-CN": "GLM-4.5：高性能模型，适用于推理、编程和代理任务。", "zh-TW": "GLM-4.5：高性能模型，用於推理、編程和代理任務。", "ja-JP": "GLM-4.5: 推論、コーディング、エージェントタスク向けの高性能モデル。", "ru-RU": "GLM-4.5: Высокопроизводительная модель для рассуждений, программирования и агентных задач." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "zhipuai/glm-4.5-air", "model_name": "glm-4.5-air", "display_name": "GLM-4.5-Air", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.2" }, "completion": { "unit": "per_M_tokens", "price": "1.1" }, "cache_read": { "unit": "per_M_tokens", "price": "0.03" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.023529" }, "cache_read_0_032_0_128": { "unit": "per_M_tokens", "price": "0.035294" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.117647" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "0.176471" }, "completion_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "0.294118" }, "completion_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "0.882353" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "1.176471" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_0_128": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "completion_0_0_032_0_0_0002": "lobehub-modelbank", "completion_0_0_032_0_0002_infinity": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank" }, "verification_status": "cross_checked" } } ], "intro": "Lighter GLM-4.5 variant for fast coding assistance and cheaper agents", "released_at": "2025-07-28", "knowledge_cutoff": "2025-04", "max_input_tokens": 131072, "max_output_tokens": 98304, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm-air", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "stream": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "deprecated": true, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "defaults": { "temperature": 0.75 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "deepinfra/zai-org/GLM-4.5-Air", "glm-4-5-air", "glm-4.5-air:free", "z-ai/glm-4.5-air", "z-ai/glm-4.5-air:free", "zai-org/GLM-4.5-Air", "zai-org/GLM-4.5-Air:thinking", "zai-org/glm-4.5-air", "zai-org/glm-4.5-air:thinking", "zai/glm-4.5-air" ], "intro_i18n": { "zh-CN": "GLM-4.5-Air：轻量版，响应速度更快。", "zh-TW": "GLM-4.5-Air：輕量版，提供快速回應。", "ja-JP": "GLM-4.5-Air: 高速応答のための軽量版。", "ru-RU": "GLM-4.5-Air: Легковесная версия для быстрых ответов." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "delisted", "note": "deprecated" } ] }, { "slug": "zhipuai/glm-4.5-airx", "model_name": "glm-4.5-airx", "display_name": "GLM-4.5-AirX", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.117647" }, "cache_read_0_032_0_128": { "unit": "per_M_tokens", "price": "0.235294" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.588235" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "1.176471" }, "completion_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "1.764706" }, "completion_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "2.352941" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "4.705882" } }, "provenance": { "base_charges": { "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_0_128": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "completion_0_0_032_0_0_0002": "lobehub-modelbank", "completion_0_0_032_0_0002_infinity": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 98304, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "prompt_caching": true }, "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "released_at": "2025-07-29", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "zai/glm-4.5-airx" ], "intro_i18n": { "zh-CN": "GLM-4.5-Air 快速版，响应更快，适用于大规模高速使用场景。", "zh-TW": "GLM-4.5-Air 快速版，回應更迅速，適用於大規模高速應用。", "ja-JP": "GLM-4.5-Air の高速版で、大規模かつ高速な利用に対応する迅速な応答を実現します。", "ru-RU": "GLM-4.5-AirX — ускоренная версия с быстрым откликом для масштабных и высокоскоростных сценариев." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-4.5-AirX" } ] }, { "slug": "zhipuai/glm-4.5-flash", "model_name": "glm-4.5-flash", "display_name": "GLM-4.5-Flash", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "cache_read": { "unit": "per_M_tokens", "price": "0" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "verification_status": "aggregator_only" } } ], "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows", "released_at": "2025-07-28", "knowledge_cutoff": "2025-04", "max_input_tokens": 131072, "max_output_tokens": 98304, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm-flash", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "glm-4-5-flash", "glm-4.5-flash:free" ], "model_type": "deep_thinking", "price_history": [ { "date": "2026-07-10", "kind": "capability", "note": "structured_output: false→true" } ] }, { "slug": "zhipuai/glm-4.5-x", "model_name": "glm-4.5-x", "display_name": "GLM-4.5-X", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.235294" }, "cache_read_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "0.352941" }, "cache_read_0_032_0_128": { "unit": "per_M_tokens", "price": "0.470588" }, "prompt_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "1.176471" }, "prompt_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "1.764706" }, "prompt_0_032_0_128": { "unit": "per_M_tokens", "price": "2.352941" }, "completion_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "2.352941" }, "completion_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "4.705882" }, "completion_0_032_0_128": { "unit": "per_M_tokens", "price": "9.411765" } }, "provenance": { "base_charges": { "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_0_032_0_0002_infinity": "lobehub-modelbank", "cache_read_0_032_0_128": "lobehub-modelbank", "prompt_0_0_032_0_0_0002": "lobehub-modelbank", "prompt_0_0_032_0_0002_infinity": "lobehub-modelbank", "prompt_0_032_0_128": "lobehub-modelbank", "completion_0_0_032_0_0_0002": "lobehub-modelbank", "completion_0_0_032_0_0002_infinity": "lobehub-modelbank", "completion_0_032_0_128": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 98304, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "prompt_caching": true }, "intro": "Flagship GLM model for hybrid reasoning, coding, and agentic engineering", "released_at": "2025-07-29", "knowledge_cutoff": "2025-04", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "status": "beta", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "zai/glm-4.5-x" ], "intro_i18n": { "zh-CN": "GLM-4.5 快速版，生成速度高达每秒 100 个 token，性能强劲。", "zh-TW": "GLM-4.5 快速版，生成速度高達每秒 100 個 token，效能出色。", "ja-JP": "GLM-4.5 の高速版で、最大100トークン/秒の生成速度で高性能を実現します。", "ru-RU": "GLM-4.5 Fast — быстрая версия с производительностью до 100 токенов в секунду." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-4.5-X" } ] }, { "slug": "zhipuai/glm-4.5v", "model_name": "glm-4.5v", "display_name": "GLM-4.5V", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "1.8" }, "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.058824" }, "cache_read_0_032_infinity": { "unit": "per_M_tokens", "price": "0.117647" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.294118" }, "prompt_0_032_infinity": { "unit": "per_M_tokens", "price": "0.588235" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "0.882353" }, "completion_0_032_infinity": { "unit": "per_M_tokens", "price": "1.764706" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_infinity": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_infinity": "lobehub-modelbank" }, "verification_status": "cross_checked" } } ], "intro": "GLM vision model for visual reasoning, documents, and multimodal agents", "released_at": "2025-08-11", "knowledge_cutoff": "2025-04", "max_input_tokens": 64000, "max_output_tokens": 16384, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "glm", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "defaults": { "temperature": 0.75 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "z-ai/glm-4.5v", "z-ai/glm-4.5v:thinking", "zai-org/GLM-4.5V", "zai-org/glm-4.5v", "zai/glm-4.5v" ], "intro_i18n": { "zh-CN": "智谱下一代 MoE 视觉推理模型，总参数 106B，激活参数 12B，在图像、视频、文档理解与 GUI 任务中，在同规模开源多模态模型中表现领先。", "zh-TW": "智譜新一代 MoE 視覺推理模型，總參數 106B，啟用 12B，於圖像、影片、文件理解與 GUI 任務中，在同級開源多模態模型中達到 SOTA 水準。", "ja-JP": "智谱の次世代MoE視覚推論モデルで、総パラメータ数106B、アクティブ12B。画像、動画、文書理解、GUIタスクにおいて同規模のオープンソースマルチモーダルモデルの中で最先端の性能を実現します。", "ru-RU": "Модель визуального логического вывода нового поколения от Zhipu с архитектурой MoE: 106B параметров, 12B активных. Достигает SOTA среди моделей аналогичного размера в задачах обработки изображений, видео, документов и GUI." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "zhipuai/glm-4.6", "model_name": "glm-4.6", "display_name": "GLM-4.6", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.11" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "cache_read_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "0.058824" }, "cache_read_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "0.088235" }, "cache_read_0_032_0_2": { "unit": "per_M_tokens", "price": "0.117647" }, "prompt_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "0.294118" }, "prompt_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "0.441176" }, "prompt_0_032_0_2": { "unit": "per_M_tokens", "price": "0.588235" }, "completion_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "1.176471" }, "completion_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "2.058824" }, "completion_0_032_0_2": { "unit": "per_M_tokens", "price": "2.352941" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_read_0_0_032_0_0_0002": "lobehub-modelbank", "cache_read_0_0_032_0_0002_infinity": "lobehub-modelbank", "cache_read_0_032_0_2": "lobehub-modelbank", "prompt_0_0_032_0_0_0002": "lobehub-modelbank", "prompt_0_0_032_0_0002_infinity": "lobehub-modelbank", "prompt_0_032_0_2": "lobehub-modelbank", "completion_0_0_032_0_0_0002": "lobehub-modelbank", "completion_0_0_032_0_0002_infinity": "lobehub-modelbank", "completion_0_032_0_2": "lobehub-modelbank" }, "verification_status": "cross_checked" } } ], "intro": "Late GLM-4 workhorse for coding agents, reasoning, and structured tasks", "released_at": "2025-09-30", "knowledge_cutoff": "2025-04", "max_input_tokens": 204800, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "deprecated": true, "status": "deprecated", "parameters": { "unsupported": [ "temperature" ] }, "docs_url": "https://openrouter.ai/z-ai/glm-4.6", "benchmarks": { "intelligence_index": 29.3, "coding_index": 45.8, "agentic_index": 18.6 }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "GLM-4.6", "ZhipuAI/GLM-4.6", "deepinfra/zai-org/GLM-4.6", "glm-4-6", "glm-4.6:exacto", "hf:zai-org/GLM-4.6", "novita/glm-4.6", "novita/zai-org/glm-4.6", "z-ai/glm-4.6", "z-ai/glm-4.6:exacto", "z-ai/glm-4.6:thinking", "zai-org/GLM-4.6", "zai-org/glm-4.6", "zai-org/glm-4.6:thinking", "zai/GLM-4.6", "zai/glm-4.6" ], "intro_i18n": { "zh-CN": "GLM-4.6：上一代模型。", "zh-TW": "GLM-4.6：上一代模型。", "ja-JP": "GLM-4.6: 前世代モデル。", "ru-RU": "GLM-4.6: Модель предыдущего поколения." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "1.65", "new": "1.61" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.45", "new": "0.4" }, { "date": "2026-08-14", "kind": "price", "provider": "berget", "charge": "completion", "old": "2.8840816", "new": "2.880833975" }, { "date": "2026-08-14", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.807542848", "new": "0.806633513" }, { "date": "2026-08-14", "kind": "price", "provider": "kilo", "charge": "cache_read", "old": "0.1", "new": "0.11" }, { "date": "2026-08-14", "kind": "price", "provider": "kilo", "charge": "cache_read", "old": "0.11", "new": "0.1" }, { "date": "2026-08-14", "kind": "price", "provider": "kilo", "charge": "completion", "old": "2", "new": "2.2" }, { "date": "2026-08-14", "kind": "price", "provider": "kilo", "charge": "completion", "old": "2.2", "new": "2" }, { "date": "2026-08-14", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "0.5", "new": "0.55" }, { "date": "2026-08-14", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "0.55", "new": "0.5" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.0752781", "new": "2.07594254" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.518819525", "new": "0.518985635" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.1", "new": "0.11" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.11", "new": "0.1" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "2", "new": "2.2" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "2.2", "new": "2" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.5", "new": "0.55" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.55", "new": "0.5" }, { "date": "2026-08-13", "kind": "price", "provider": "berget", "charge": "completion", "old": "2.88640205", "new": "2.8840816" }, { "date": "2026-08-13", "kind": "price", "provider": "berget", "charge": "prompt", "old": "0.808192574", "new": "0.807542848" } ] }, { "slug": "zhipuai/glm-4.6v", "model_name": "glm-4.6v", "display_name": "GLM-4.6V", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.3" }, "completion": { "unit": "per_M_tokens", "price": "0.9" }, "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.029412" }, "cache_read_0_032_infinity": { "unit": "per_M_tokens", "price": "0.058824" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.147059" }, "prompt_0_032_infinity": { "unit": "per_M_tokens", "price": "0.294118" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "0.441176" }, "completion_0_032_infinity": { "unit": "per_M_tokens", "price": "0.882353" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_infinity": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_infinity": "lobehub-modelbank" }, "verification_status": "cross_checked" } } ], "intro": "GLM vision model for visual reasoning, documents, and multimodal agents", "released_at": "2025-12-08", "knowledge_cutoff": "2025-04", "max_input_tokens": 128000, "max_output_tokens": 32768, "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "glm", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "parameters": { "unsupported": [ "temperature" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "deepinfra/zai-org/GLM-4.6V", "novita/glm-4.6v", "z-ai/glm-4.6v", "zai-org/GLM-4.6V", "zai-org/glm-4.6v", "zai/glm-4.6v" ], "intro_i18n": { "zh-CN": "GLM-4.6V 系列是 GLM 家族在多模态方向上的重要迭代，包括 GLM-4.6V（旗舰版）、GLM-4.6V-FlashX（轻量化高效版）和 GLM-4.6V-Flash（完全免费版）。该系列将训练时间上下文窗口扩展至 128k tokens，在相似参数规模下实现了最先进的视觉理解准确性，并首次将功能调用（工具调用）能力原生集成到视觉模型架构中。这一设计统一了从“视觉感知”到“可执行动作”的流程，为多模态智能体在真实生产场景中的应用提供了稳定的技术基础。", "zh-TW": "GLM-4.6V 系列是 GLM 家族在多模態方向上的重要迭代，包括 GLM-4.6V（旗艦版）、GLM-4.6V-FlashX（輕量化且高速版）以及 GLM-4.6V-Flash（完全免費版）。該系列將訓練時間上下文窗口擴展至 128k tokens，在相似參數規模下實現了最先進的視覺理解準確度，並首次將功能調用（工具調用）能力原生整合到視覺模型架構中。這統一了從「視覺感知」到「可執行動作」的流程，為多模態代理在實際生產場景中提供了一致的技術基礎。", "ja-JP": "GLM-4.6Vシリーズは、マルチモーダル方向におけるGLMファミリーの主要な進化を表しており、GLM-4.6V（フラッグシップ）、GLM-4.6V-FlashX（軽量かつ高速）、GLM-4.6V-Flash（完全無料）で構成されています。トレーニング時のコンテキストウィンドウを128kトークンに拡張し、同等のパラメータスケールで最先端の視覚理解精度を達成します。また、初めてFunction Call（ツール呼び出し）機能を視覚モデルアーキテクチャにネイティブ統合しました。これにより、「視覚認識」から「実行可能なアクション」までのパイプラインが統一され、実世界の生産シナリオにおけるマルチモーダルエージェントの一貫した技術基盤を提供します。", "ru-RU": "Серия GLM-4.6V представляет собой значительную итерацию семейства GLM в мультимодальном направлении, включая GLM-4.6V (флагман), GLM-4.6V-FlashX (легковесная и высокоскоростная версия) и GLM-4.6V-Flash (полностью бесплатная версия). Она расширяет окно контекста времени обучения до 128k токенов, достигает передовой точности визуального восприятия при сопоставимых масштабах параметров и впервые нативно интегрирует возможности Function Call (вызов инструментов) в архитектуру визуальной модели. Это объединяет процесс от «визуального восприятия» до «исполняемых действий», предоставляя единый технический фундамент для мультимодальных агентов в реальных производственных сценариях." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "zhipuai/glm-4.6v-flash-free", "model_name": "glm-4.6v-flash-free", "display_name": "GLM-4.6V-Flash", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0" }, "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "glm-4.6v-flash" } ], "released_at": "2025-12-08", "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true, "stream": true }, "intro": "GLM vision model for visual reasoning, documents, and multimodal agents", "knowledge_cutoff": "2025-01", "modalities": { "input": [ "text", "image", "video" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "glm-4.6v-flash", "z-ai/glm-4.6v-flash", "z-ai/glm-4.6v-flash-free", "zai-org/GLM-4.6V-Flash", "zai/glm-4.6v-flash" ], "intro_i18n": { "zh-CN": "GLM-4.6V 系列是 GLM 家族在多模态方向上的重要迭代，包括 GLM-4.6V（旗舰版）、GLM-4.6V-FlashX（轻量化高效版）和 GLM-4.6V-Flash（完全免费版）。该系列将训练时间上下文窗口扩展至 128k tokens，在相似参数规模下实现了最先进的视觉理解准确性，并首次将功能调用（工具调用）能力原生集成到视觉模型架构中。这一设计统一了从“视觉感知”到“可执行动作”的流程，为多模态智能体在真实生产场景中的应用提供了稳定的技术基础。", "zh-TW": "GLM-4.6V 系列是 GLM 家族在多模態方向上的重要迭代，包括 GLM-4.6V（旗艦版）、GLM-4.6V-FlashX（輕量化且高速版）以及 GLM-4.6V-Flash（完全免費版）。該系列將訓練時間上下文窗口擴展至 128k tokens，在相似參數規模下實現了最先進的視覺理解準確度，並首次將功能調用（工具調用）能力原生整合到視覺模型架構中。這統一了從「視覺感知」到「可執行動作」的流程，為多模態代理在實際生產場景中提供了一致的技術基礎。", "ja-JP": "GLM-4.6Vシリーズは、マルチモーダル方向におけるGLMファミリーの主要な進化を表しており、GLM-4.6V（フラッグシップ）、GLM-4.6V-FlashX（軽量かつ高速）、GLM-4.6V-Flash（完全無料）で構成されています。トレーニング時のコンテキストウィンドウを128kトークンに拡張し、同等のパラメータスケールで最先端の視覚理解精度を達成します。また、初めてFunction Call（ツール呼び出し）機能を視覚モデルアーキテクチャにネイティブ統合しました。これにより、「視覚認識」から「実行可能なアクション」までのパイプラインが統一され、実世界の生産シナリオにおけるマルチモーダルエージェントの一貫した技術基盤を提供します。", "ru-RU": "Серия GLM-4.6V представляет собой значительную итерацию семейства GLM в мультимодальном направлении, включая GLM-4.6V (флагман), GLM-4.6V-FlashX (легковесная и высокоскоростная версия) и GLM-4.6V-Flash (полностью бесплатная версия). Она расширяет окно контекста времени обучения до 128k токенов, достигает передовой точности визуального восприятия при сопоставимых масштабах параметров и впервые нативно интегрирует возможности Function Call (вызов инструментов) в архитектуру визуальной модели. Это объединяет процесс от «визуального восприятия» до «исполняемых действий», предоставляя единый технический фундамент для мультимодальных агентов в реальных производственных сценариях." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-4.6V-Flash" } ] }, { "slug": "zhipuai/glm-4.6v-flashx", "model_name": "glm-4.6v-flashx", "display_name": "GLM-4.6V-FlashX", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.004412" }, "cache_read_0_032_infinity": { "unit": "per_M_tokens", "price": "0.004412" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.022059" }, "prompt_0_032_infinity": { "unit": "per_M_tokens", "price": "0.044118" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "0.220588" }, "completion_0_032_infinity": { "unit": "per_M_tokens", "price": "0.441176" } }, "provenance": { "base_charges": { "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_infinity": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_infinity": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2025-12-08", "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "vision": true, "video_input": true, "pdf_input": true, "prompt_caching": true }, "intro": "GLM vision model for visual reasoning, documents, and multimodal agents", "modalities": { "input": [ "text", "image" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "zai/glm-4.6v-flashx" ], "intro_i18n": { "zh-CN": "GLM-4.6V 系列是 GLM 家族在多模态方向上的重要迭代，包括 GLM-4.6V（旗舰版）、GLM-4.6V-FlashX（轻量化高效版）和 GLM-4.6V-Flash（完全免费版）。该系列将训练时间上下文窗口扩展至 128k tokens，在相似参数规模下实现了最先进的视觉理解准确性，并首次将功能调用（工具调用）能力原生集成到视觉模型架构中。这一设计统一了从“视觉感知”到“可执行动作”的流程，为多模态智能体在真实生产场景中的应用提供了稳定的技术基础。", "zh-TW": "GLM-4.6V 系列是 GLM 家族在多模態方向上的重要迭代，包括 GLM-4.6V（旗艦版）、GLM-4.6V-FlashX（輕量化且高速版）以及 GLM-4.6V-Flash（完全免費版）。該系列將訓練時間上下文窗口擴展至 128k tokens，在相似參數規模下實現了最先進的視覺理解準確度，並首次將功能調用（工具調用）能力原生整合到視覺模型架構中。這統一了從「視覺感知」到「可執行動作」的流程，為多模態代理在實際生產場景中提供了一致的技術基礎。", "ja-JP": "GLM-4.6Vシリーズは、マルチモーダル方向におけるGLMファミリーの主要な進化を表しており、GLM-4.6V（フラッグシップ）、GLM-4.6V-FlashX（軽量かつ高速）、GLM-4.6V-Flash（完全無料）で構成されています。トレーニング時のコンテキストウィンドウを128kトークンに拡張し、同等のパラメータスケールで最先端の視覚理解精度を達成します。また、初めてFunction Call（ツール呼び出し）機能を視覚モデルアーキテクチャにネイティブ統合しました。これにより、「視覚認識」から「実行可能なアクション」までのパイプラインが統一され、実世界の生産シナリオにおけるマルチモーダルエージェントの一貫した技術基盤を提供します。", "ru-RU": "Серия GLM-4.6V представляет собой значительную итерацию семейства GLM в мультимодальном направлении, включая GLM-4.6V (флагман), GLM-4.6V-FlashX (легковесная и высокоскоростная версия) и GLM-4.6V-Flash (полностью бесплатная версия). Она расширяет окно контекста времени обучения до 128k токенов, достигает передовой точности визуального восприятия при сопоставимых масштабах параметров и впервые нативно интегрирует возможности Function Call (вызов инструментов) в архитектуру визуальной модели. Это объединяет процесс от «визуального восприятия» до «исполняемых действий», предоставляя единый технический фундамент для мультимодальных агентов в реальных производственных сценариях." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-4.6V-FlashX" } ] }, { "slug": "zhipuai/glm-4.7", "model_name": "glm-4.7", "display_name": "GLM-4.7", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.6" }, "completion": { "unit": "per_M_tokens", "price": "2.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.11" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "cache_read_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "0.058824" }, "cache_read_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "0.088235" }, "cache_read_0_032_0_2": { "unit": "per_M_tokens", "price": "0.117647" }, "prompt_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "0.294118" }, "prompt_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "0.441176" }, "prompt_0_032_0_2": { "unit": "per_M_tokens", "price": "0.588235" }, "completion_0_0_032_0_0_0002": { "unit": "per_M_tokens", "price": "1.176471" }, "completion_0_0_032_0_0002_infinity": { "unit": "per_M_tokens", "price": "2.058824" }, "completion_0_032_0_2": { "unit": "per_M_tokens", "price": "2.352941" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_read_0_0_032_0_0_0002": "lobehub-modelbank", "cache_read_0_0_032_0_0002_infinity": "lobehub-modelbank", "cache_read_0_032_0_2": "lobehub-modelbank", "prompt_0_0_032_0_0_0002": "lobehub-modelbank", "prompt_0_0_032_0_0002_infinity": "lobehub-modelbank", "prompt_0_032_0_2": "lobehub-modelbank", "completion_0_0_032_0_0_0002": "lobehub-modelbank", "completion_0_0_032_0_0002_infinity": "lobehub-modelbank", "completion_0_032_0_2": "lobehub-modelbank" }, "verification_status": "cross_checked" } } ], "intro": "Mature GLM model for dependable coding, reasoning, and structured agent tasks", "released_at": "2025-12-22", "knowledge_cutoff": "2025-04", "max_input_tokens": 204800, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "web_search": true, "assistant_prefill": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "deprecated": true, "status": "deprecated", "docs_url": "https://www.together.ai/models/glm-4-7", "benchmarks": { "intelligence_index": 34.5, "coding_index": 45.3, "agentic_index": 26.2 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_a", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "GLM-4.7", "Pro/zai-org/GLM-4.7", "TEE/glm-4.7", "glm-4-7", "glm-4.7-free", "hf:zai-org/GLM-4.7", "novita/glm-4.7", "z-ai/glm-4.7", "zai-org/GLM-4.7", "zai-org/glm-4.7", "zai-org/glm-4.7:thinking", "zai/GLM-4.7", "zai/glm-4.7" ], "intro_i18n": { "zh-CN": "GLM-4.7是智谱最新旗舰模型，针对代理编程场景进行了增强，具备更强的编程能力、长期任务规划能力以及工具协作能力。", "zh-TW": "GLM-4.7 是智譜最新的旗艦模型，針對代理編程場景進行增強，具備改進的編程能力、長期任務規劃和工具協作能力。", "ja-JP": "GLM-4.7は智譜の最新フラッグシップモデルで、エージェンティックコーディングシナリオ向けに強化され、コーディング能力、長期タスク計画、ツール連携が向上しています。", "ru-RU": "GLM-4.7: Последняя флагманская модель Zhipu, улучшенная для сценариев агентного программирования с расширенными возможностями кодирования, долгосрочного планирования задач и взаимодействия с инструментами." }, "price_history": [ { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.432", "new": "0.44" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "2.24", "new": "2.37" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.864", "new": "0.88" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "cache_read", "old": "0.11", "new": "0.08" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "completion", "old": "2.2", "new": "1.75" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "0.6", "new": "0.4" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.44", "new": "0.432" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "completion", "old": "2.37", "new": "2.24" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.88", "new": "0.864" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "2.18", "new": "2.31" }, { "date": "2026-08-09", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.59", "new": "0.63" }, { "date": "2026-08-07", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.445", "new": "0.44" }, { "date": "2026-08-07", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.89", "new": "0.88" }, { "date": "2026-08-06", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.426", "new": "0.445" }, { "date": "2026-08-06", "kind": "price", "provider": "io-net", "charge": "completion", "old": "2.196", "new": "2.37" }, { "date": "2026-08-06", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.852", "new": "0.89" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "completion", "old": "2.23", "new": "2.785" }, { "date": "2026-08-05", "kind": "price", "provider": "cortecs", "charge": "prompt", "old": "0.45", "new": "0.78" }, { "date": "2026-08-05", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.432", "new": "0.426" }, { "date": "2026-08-05", "kind": "price", "provider": "io-net", "charge": "completion", "old": "2.24", "new": "2.196" } ] }, { "slug": "zhipuai/glm-4.7-flash", "model_name": "glm-4.7-flash", "display_name": "GLM-4.7-Flash", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" }, "cache_read": { "unit": "per_M_tokens", "price": "0" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Budget GLM lane for fast coding help, routing, and everyday automation", "released_at": "2026-01-19", "knowledge_cutoff": "2025-04", "max_input_tokens": 200000, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm-flash", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "web_search": true, "stream": true }, "model_type": "deep_thinking", "parameters": { "unsupported": [ "temperature" ] }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "@cf/zai-org/glm-4.7-flash", "glm-4-7-flash", "glm-4-7-flash:free", "hf:zai-org/GLM-4.7-Flash", "novita/glm-4.7-flash", "workers-ai/@cf/zai-org/glm-4.7-flash", "z-ai/glm-4.7-flash", "z-ai/glm-4.7-flash-free", "zai-org/GLM-4.7-Flash", "zai-org/glm-4.7-flash", "zai-org/glm-4.7-flash:thinking", "zai/glm-4.7-flash" ], "intro_i18n": { "zh-CN": "GLM-4.7-Flash 是一款 30B 级别的 SOTA 模型，在性能与效率之间实现平衡。它提升了编程能力、长期任务规划和工具协作能力，适用于 Agentic Coding 场景，在多个当前基准排行榜中，在同体量开源模型中表现领先。在执行复杂智能体任务时，工具调用的指令遵循性更强，进一步提升了 Artifacts 和 Agentic Coding 的前端美学和长期任务完成效率。", "zh-TW": "GLM-4.7-Flash 作為 30B 級別的 SOTA 模型，提供在效能與效率間取得平衡的新選擇。它強化了程式能力、長期任務規劃與工具協作，適用於 Agentic Coding 場景，在多項當前基準排行榜中於同級開源模型中表現領先。在執行複雜智慧代理任務時，其工具調用的指令遵循能力更強，並進一步提升 Artifacts 與 Agentic Coding 前端的美學與長期任務完成效率。", "ja-JP": "GLM-4.7-Flashは、30BクラスのSOTAモデルとして、性能と効率のバランスを実現する新たな選択肢です。Agentic Codingシナリオにおけるコーディング能力、長期タスク計画、ツール連携を強化し、同規模のオープンソースモデルの中でベンチマーク上位の性能を発揮します。複雑なインテリジェントエージェントタスクの実行時には、ツール呼び出し時の指示遵守が強化され、フロントエンドの美的品質や長期タスク完了効率も向上しています。", "ru-RU": "GLM-4.7-Flash — модель уровня 30B SOTA, предлагающая баланс между производительностью и эффективностью. Улучшает программирование, долгосрочное планирование задач и взаимодействие с инструментами в сценариях Agentic Coding, достигая лидирующих результатов среди моделей аналогичного размера с открытым исходным кодом. При выполнении сложных задач интеллектуальных агентов демонстрирует лучшее следование инструкциям при вызове инструментов, а также улучшает эстетику интерфейса и эффективность выполнения долгосрочных задач в Artifacts и Agentic Coding." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "zhipuai/glm-4.7-flashx", "model_name": "glm-4.7-flashx", "display_name": "GLM-4.7-FlashX", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.07" }, "completion": { "unit": "per_M_tokens", "price": "0.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.01" }, "cache_write": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev" }, "discarded_conflicts": [ { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "cache_read", "selected_charge": { "unit": "per_M_tokens", "price": "0.01" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.1", "currency": "CNY" }, "message": "cache_read from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "prompt", "selected_charge": { "unit": "per_M_tokens", "price": "0.07" }, "discarded_charge": { "unit": "per_M_tokens", "price": "0.5", "currency": "CNY" }, "message": "prompt from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." }, { "kind": "base_charge", "source": "lobehub-modelbank", "selected_source": "models-dev", "charge": "completion", "selected_charge": { "unit": "per_M_tokens", "price": "0.4" }, "discarded_charge": { "unit": "per_M_tokens", "price": "3", "currency": "CNY" }, "message": "completion from lobehub-modelbank conflicts with models-dev; the higher-priority value was kept." } ], "verification_status": "conflicting" } } ], "intro": "Efficient GLM model for fast reasoning, coding, and agent workflows", "released_at": "2026-01-19", "knowledge_cutoff": "2025-04", "max_input_tokens": 200000, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm-flash", "capabilities": { "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "web_search": true, "stream": true }, "model_type": "deep_thinking", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "z-ai/glm-4.7-flashx", "zai/glm-4.7-flashx" ], "intro_i18n": { "zh-CN": "GLM-4.7-Flash 是一款 30B 级别的 SOTA 模型，在性能与效率之间实现平衡。它提升了编程能力、长期任务规划和工具协作能力，适用于 Agentic Coding 场景，在多个当前基准排行榜中，在同体量开源模型中表现领先。在执行复杂智能体任务时，工具调用的指令遵循性更强，进一步提升了 Artifacts 和 Agentic Coding 的前端美学和长期任务完成效率。", "zh-TW": "GLM-4.7-Flash 作為 30B 級別的 SOTA 模型，提供在效能與效率間取得平衡的新選擇。它強化了程式能力、長期任務規劃與工具協作，適用於 Agentic Coding 場景，在多項當前基準排行榜中於同級開源模型中表現領先。在執行複雜智慧代理任務時，其工具調用的指令遵循能力更強，並進一步提升 Artifacts 與 Agentic Coding 前端的美學與長期任務完成效率。", "ja-JP": "GLM-4.7-Flashは、30BクラスのSOTAモデルとして、性能と効率のバランスを実現する新たな選択肢です。Agentic Codingシナリオにおけるコーディング能力、長期タスク計画、ツール連携を強化し、同規模のオープンソースモデルの中でベンチマーク上位の性能を発揮します。複雑なインテリジェントエージェントタスクの実行時には、ツール呼び出し時の指示遵守が強化され、フロントエンドの美的品質や長期タスク完了効率も向上しています。", "ru-RU": "GLM-4.7-Flash — модель уровня 30B SOTA, предлагающая баланс между производительностью и эффективностью. Улучшает программирование, долгосрочное планирование задач и взаимодействие с инструментами в сценариях Agentic Coding, достигая лидирующих результатов среди моделей аналогичного размера с открытым исходным кодом. При выполнении сложных задач интеллектуальных агентов демонстрирует лучшее следование инструкциям при вызове инструментов, а также улучшает эстетику интерфейса и эффективность выполнения долгосрочных задач в Artifacts и Agentic Coding." }, "price_history": [ { "date": "2026-07-02", "kind": "capability", "note": "structured_output: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-07-02", "kind": "capability", "note": "stream: false→true" } ] }, { "slug": "zhipuai/glm-4v", "model_name": "glm-4v", "display_name": "GLM-4V", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "7.352941" }, "completion": { "unit": "per_M_tokens", "price": "7.352941" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 4096, "max_output_tokens": 1024, "model_type": "vision_understanding", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4V 在视觉任务中具备强大的图像理解与推理能力。", "zh-TW": "GLM-4V 在各類視覺任務中展現強大的圖像理解與推理能力。", "ja-JP": "GLM-4V は、視覚タスクにおける画像理解と推論に優れた性能を発揮します。", "ru-RU": "GLM-4V обеспечивает высокое качество понимания изображений и логического вывода в визуальных задачах." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-4V" } ] }, { "slug": "zhipuai/glm-4v-flash", "model_name": "glm-4v-flash", "display_name": "GLM-4V-Flash", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2024-12-09", "max_input_tokens": 4096, "max_output_tokens": 1024, "model_type": "vision_understanding", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4V-Flash 专注于高效的单图像理解，适用于实时或批量图像处理等快速分析场景。", "zh-TW": "GLM-4V-Flash 專注於單張圖像的高效理解，適用於即時或批次圖像處理等快速分析場景。", "ja-JP": "GLM-4V-Flash は、リアルタイムやバッチ画像処理などの高速分析シナリオに適した、単一画像理解に特化したモデルです。", "ru-RU": "GLM-4V-Flash ориентирована на эффективное понимание одиночных изображений в сценариях быстрого анализа, таких как обработка изображений в реальном времени или пакетная обработка." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-4V-Flash" } ] }, { "slug": "zhipuai/glm-4v-plus-0111", "model_name": "glm-4v-plus-0111", "display_name": "GLM-4V-Plus-0111", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.588235" }, "completion": { "unit": "per_M_tokens", "price": "0.588235" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 16000, "max_output_tokens": 8192, "model_type": "vision_understanding", "capabilities": { "vision": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-4V-Plus 支持视频与多图像理解，适用于多模态任务。", "zh-TW": "GLM-4V-Plus 能理解影片與多張圖像，適合多模態任務。", "ja-JP": "GLM-4V-Plus は、動画や複数画像の理解に対応し、マルチモーダルタスクに適しています。", "ru-RU": "GLM-4V-Plus понимает видео и несколько изображений, подходит для мультимодальных задач." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-4V-Plus-0111" } ] }, { "slug": "zhipuai/glm-5", "model_name": "glm-5", "display_name": "GLM-5", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev+llmdb+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1" }, "completion": { "unit": "per_M_tokens", "price": "3.2" }, "cache_read": { "unit": "per_M_tokens", "price": "0.2" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.147059" }, "cache_read_0_032_infinity": { "unit": "per_M_tokens", "price": "0.220588" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.588235" }, "prompt_0_032_infinity": { "unit": "per_M_tokens", "price": "0.882353" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "2.647059" }, "completion_0_032_infinity": { "unit": "per_M_tokens", "price": "3.235294" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_infinity": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_infinity": "lobehub-modelbank" }, "verification_status": "cross_checked" } } ], "intro": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows", "released_at": "2026-02-11", "max_input_tokens": 204800, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "stream": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "knowledge_cutoff": "2025-12", "deprecated": true, "status": "deprecated", "reasoning_config": { "mandatory": false, "budget_min": 128 }, "docs_url": "https://openrouter.ai/z-ai/glm-5", "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "GLM-5", "Pro/zai-org/GLM-5", "accounts/fireworks/models/glm-5", "glm-5-free", "novita/GLM-5", "novita/glm-5", "z-ai/glm-5", "zai-org/GLM-5", "zai-org/glm-5", "zai-org/glm-5:thinking", "zai/GLM-5", "zai/glm-5" ], "intro_i18n": { "zh-CN": "GLM-5 是智谱面向 Agentic Engineering 打造的下一代旗舰基础模型，可在复杂系统工程与长周期智能体任务中提供可靠生产力。在编码与智能体能力方面，GLM-5 在开源模型中表现领先。在真实编程场景中的使用体验已接近 Claude Opus 4.5。它擅长复杂系统工程与长期智能体任务，是构建通用型智能体助手的理想基础模型。", "zh-TW": "GLM-5 是智譜推出的下一代旗艦級基礎模型，專為 Agentic Engineering 打造，能在複雜系統工程與長時序智能體任務中提供可靠效能。在程式能力與智能體表現上位居開源模型最前列，於真實編程情境中的體驗接近 Claude Opus 4.5。其擅長複雜系統工程與長鏈任務，是通用型智能體助手的理想基礎模型。", "ja-JP": "GLM-5 は Zhipu の次世代フラッグシップ基盤モデルで、エージェント工学向けに設計されています。複雑なシステムエンジニアリングや長期的なエージェントタスクにおいて高い生産性を発揮します。コーディングやエージェント能力ではオープンソースモデルの中で最先端の性能を示し、実際のプログラミング環境では Claude Opus 4.5 に匹敵するユーザー体験を提供します。汎用エージェントアシスタントの基盤モデルとして理想的です。", "ru-RU": "GLM-5 — флагманская модель нового поколения от Zhipu, созданная специально для Agentic Engineering. Обеспечивает надёжную продуктивность в задачах сложной системной инженерии и долгосрочных агентных сценариях. В программировании и агентных возможностях GLM-5 достигает уровня SOTA среди открытых моделей. В реальных условиях кодирования пользовательский опыт приближается к Claude Opus 4.5. Отличается высокой эффективностью в сложной инженерии и длительных агентных задачах, что делает её идеальной базовой моделью для универсальных агент-ассистентов." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "3.15", "new": "7.06" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "0.95", "new": "1.57" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.39", "new": "0.38" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "completion", "old": "2.528", "new": "2.356" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.78", "new": "0.76" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.6682147", "new": "2.66906898" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.5929366", "new": "0.59312644" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.385", "new": "0.39" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "2.366", "new": "2.528" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.77", "new": "0.78" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "completion", "old": "3.2", "new": "2.55" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "1", "new": "0.95" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.66863194", "new": "2.6682147" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59302932", "new": "0.5929366" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.41", "new": "0.385" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "completion", "old": "2.548", "new": "2.366" }, { "date": "2026-08-12", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "0.82", "new": "0.77" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "completion", "old": "2.66841504", "new": "2.66863194" }, { "date": "2026-08-12", "kind": "price", "provider": "moark", "charge": "prompt", "old": "0.59298112", "new": "0.59302932" }, { "date": "2026-08-11", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.39", "new": "0.41" } ] }, { "slug": "zhipuai/GLM-5-Turbo", "model_name": "GLM-5-Turbo", "display_name": "GLM-5-Turbo", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.176471" }, "cache_read_0_032_infinity": { "unit": "per_M_tokens", "price": "0.264706" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.735294" }, "prompt_0_032_infinity": { "unit": "per_M_tokens", "price": "1.029412" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "3.235294" }, "completion_0_032_infinity": { "unit": "per_M_tokens", "price": "3.823529" } }, "provenance": { "base_charges": { "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_infinity": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_infinity": "lobehub-modelbank" }, "verification_status": "aggregator_only" }, "provider_model_id": "glm-5-turbo" } ], "released_at": "2026-03-15", "max_input_tokens": 200000, "max_output_tokens": 131072, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "pdf_input": true, "prompt_caching": true, "open_weights": true }, "intro": "Faster GLM-5 lane for coding agents that need lower latency", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "knowledge_cutoff": "2025-01", "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "reasoning_config": { "mandatory": false }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "glm-5-turbo", "z-ai/glm-5-turbo", "zai-org/glm-5-turbo", "zai/glm-5-turbo" ], "intro_i18n": { "zh-CN": "GLM-5-Turbo 是一款为智能体场景深度优化的基础模型，从训练阶段即面向智能体任务的核心需求进行优化，加强了工具调用、指令遵循与长链执行等关键能力，非常适合构建高性能智能助手。", "zh-TW": "GLM-5-Turbo 是針對智能體情境深度優化的基礎模型，自訓練階段便面向智能體任務需求調校，加強工具調用、指令跟隨與長鏈執行等能力，是打造高效能智能體助手的理想選擇。", "ja-JP": "GLM-5-Turbo はエージェントシナリオに最適化された基盤モデルです。学習段階からツール呼び出し、コマンド実行、長いタスクチェーン処理など、エージェントに必要な能力を強化しており、高性能なエージェントアシスタントの構築に最適です。", "ru-RU": "GLM-5-Turbo — базовая модель, глубоко оптимизированная для агентных сценариев. Специально улучшена под ключевые требования агентных задач ещё на этапе обучения, усиливая такие возможности, как вызов инструментов, следование командам и выполнение длинных цепочек действий. Идеально подходит для создания высокопроизводительных агент-ассистентов." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-08-03", "kind": "capability", "note": "open_weights: true→false" }, { "date": "2026-07-03", "kind": "listed", "note": "GLM-5-Turbo" } ] }, { "slug": "zhipuai/glm-5.1", "model_name": "glm-5.1", "display_name": "GLM-5.1", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.4" }, "completion": { "unit": "per_M_tokens", "price": "4.4" }, "cache_read": { "unit": "per_M_tokens", "price": "0.26" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.191176" }, "cache_read_0_032_infinity": { "unit": "per_M_tokens", "price": "0.294118" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.882353" }, "prompt_0_032_infinity": { "unit": "per_M_tokens", "price": "1.176471" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "3.529412" }, "completion_0_032_infinity": { "unit": "per_M_tokens", "price": "4.117647" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_infinity": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_infinity": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "intro": "Strong GLM coding model for agentic engineering, terminals, and repository generation", "released_at": "2026-03-27", "max_input_tokens": 200000, "max_output_tokens": 131072, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "structured_output": true, "open_weights": true, "pdf_input": true, "web_search": true, "parallel_function_calling": true }, "model_type": "deep_thinking", "deprecated": true, "status": "deprecated", "knowledge_cutoff": "2025-04", "reasoning_config": { "mandatory": false, "budget_min": 128 }, "docs_url": "https://openrouter.ai/z-ai/glm-5.1", "benchmarks": { "intelligence_index": 41, "coding_index": 55.8, "agentic_index": 30.6 }, "parameters": { "supported": [ "frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "GLM-5.1", "Pro/zai-org/GLM-5.1", "Pro/zai-org/glm-5.1", "TEE/glm-5.1", "deepinfra/zai-org/GLM-5.1", "fireworks/glm-5.1", "glm-5-1", "nebius/zai-org/glm-5.1", "novita/zai-org/glm-5.1", "z-ai/glm-5.1", "zai-org/GLM-5.1", "zai-org/glm-5.1", "zai-org/glm-5.1:thinking", "zai/GLM-5.1", "zai/glm-5.1" ], "intro_i18n": { "zh-CN": "GLM-5.1 是智谱最新的旗舰模型，是 GLM-5 的增强迭代版本，具备更强的代理工程能力，能够处理复杂系统工程和长周期任务。", "zh-TW": "GLM-5.1 是智譜最新的旗艦模型，是 GLM-5 的增強版，具備更強的代理工程能力，能應對複雜系統工程和長期任務。", "ja-JP": "GLM-5.1はZhipuの最新フラッグシップモデルであり、GLM-5の強化版です。複雑なシステムエンジニアリングや長期的なタスクにおけるエージェント工学能力が向上しています。", "ru-RU": "GLM-5.1 — это новейшая флагманская модель Zhipu, улучшенная версия GLM-5 с расширенными возможностями агентной инженерии для сложных системных разработок и задач с длинным горизонтом." }, "price_history": [ { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "cache_read", "old": "0.29", "new": "0.08" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "completion", "old": "3.96", "new": "9.41" }, { "date": "2026-08-14", "kind": "price", "provider": "api-airforce", "charge": "prompt", "old": "1.15", "new": "2.36" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.645", "new": "0.605" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "completion", "old": "4.22", "new": "3.98" }, { "date": "2026-08-14", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "1.29", "new": "1.21" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "completion", "old": "4.1505562", "new": "4.15188508" }, { "date": "2026-08-14", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.1858732", "new": "1.18625288" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.1768", "new": "0.26" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "2.992", "new": "4.4" }, { "date": "2026-08-14", "kind": "price", "provider": "openrouter", "charge": "prompt", "old": "0.952", "new": "1.4" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "cache_read", "old": "0.605", "new": "0.645" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "completion", "old": "3.98", "new": "4.22" }, { "date": "2026-08-13", "kind": "price", "provider": "io-net", "charge": "prompt", "old": "1.21", "new": "1.29" }, { "date": "2026-08-13", "kind": "price", "provider": "kilo", "charge": "prompt", "old": "1.38", "new": "1.4" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "completion", "old": "4.15120524", "new": "4.1505562" }, { "date": "2026-08-13", "kind": "price", "provider": "moark", "charge": "prompt", "old": "1.18605864", "new": "1.1858732" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.1768", "new": "0.26" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "cache_read", "old": "0.26", "new": "0.1768" }, { "date": "2026-08-13", "kind": "price", "provider": "openrouter", "charge": "completion", "old": "2.992", "new": "4.4" } ] }, { "slug": "zhipuai/glm-5.3", "model_name": "glm-5.3", "display_name": "GLM-5.3", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "cache_read": { "unit": "per_M_tokens", "price": "0.294118" }, "prompt": { "unit": "per_M_tokens", "price": "1.176471" }, "completion": { "unit": "per_M_tokens", "price": "4.117647" } }, "provenance": { "base_charges": { "cache_read": "lobehub-modelbank", "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-08-14", "max_input_tokens": 1048576, "max_output_tokens": 131072, "model_type": "deep_thinking", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "prompt_caching": true }, "intro": "Flagship GLM model for long-horizon coding, agents, and complex project delivery", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "price_history": [ { "date": "2026-08-14", "kind": "capability", "note": "web_search: false→true" }, { "date": "2026-08-14", "kind": "limit", "old": "1000000", "new": "1048576", "note": "max_input_tokens" }, { "date": "2026-08-14", "kind": "listed", "note": "GLM-5.3" } ] }, { "slug": "zhipuai/glm-5v-turbo", "model_name": "glm-5v-turbo", "display_name": "GLM-5V-Turbo", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "provider_name": "Zhipu AI", "official": true, "source": "models-dev+lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "5" }, "completion": { "unit": "per_M_tokens", "price": "22" }, "cache_read": { "unit": "per_M_tokens", "price": "1.2" }, "cache_write": { "unit": "per_M_tokens", "price": "0" }, "cache_read_0_0_032": { "unit": "per_M_tokens", "price": "0.176471" }, "cache_read_0_032_infinity": { "unit": "per_M_tokens", "price": "0.264706" }, "prompt_0_0_032": { "unit": "per_M_tokens", "price": "0.735294" }, "prompt_0_032_infinity": { "unit": "per_M_tokens", "price": "1.029412" }, "completion_0_0_032": { "unit": "per_M_tokens", "price": "3.235294" }, "completion_0_032_infinity": { "unit": "per_M_tokens", "price": "3.823529" } }, "provenance": { "base_charges": { "prompt": "models-dev", "completion": "models-dev", "cache_read": "models-dev", "cache_write": "models-dev", "cache_read_0_0_032": "lobehub-modelbank", "cache_read_0_032_infinity": "lobehub-modelbank", "prompt_0_0_032": "lobehub-modelbank", "prompt_0_032_infinity": "lobehub-modelbank", "completion_0_0_032": "lobehub-modelbank", "completion_0_032_infinity": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "intro": "Fast GLM vision model for screenshots, documents, and multimodal agent tasks", "released_at": "2026-04-01", "max_input_tokens": 200000, "max_output_tokens": 131072, "modalities": { "input": [ "text", "image", "video", "pdf" ], "output": [ "text" ] }, "family": "glm", "capabilities": { "vision": true, "function_calling": true, "reasoning": true, "prompt_caching": true, "audio_input": true, "video_input": true, "structured_output": true, "open_weights": true, "pdf_input": true, "web_search": true }, "model_type": "deep_thinking", "reasoning_config": { "mandatory": false, "budget_min": 128 }, "parameters": { "supported": [ "include_reasoning", "max_tokens", "reasoning", "response_format", "temperature", "tool_choice", "tools", "top_k", "top_p" ], "defaults": { "temperature": 1, "top_p": 0.95 } }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "aliases": [ "z-ai/glm-5v-turbo", "z-ai/glm-5v-turbo:thinking", "zai-org/GLM-5V-Turbo", "zai-org/glm-5v-turbo", "zai/glm-5v-turbo" ], "intro_i18n": { "zh-CN": "GLM-5V-Turbo是智谱推出的多模态编码基础模型，专为视觉编程任务设计。它原生支持图像、视频、文本和文件处理，并针对长时间规划、复杂编码和多模态工作流中的代理执行进行了优化。", "zh-TW": "GLM-5V-Turbo 是智譜推出的多模態編程基礎模型，專為視覺編程任務設計。它原生支持影像、視頻、文本和文件，並針對長期規劃、複雜編程和代理執行進行優化。", "ja-JP": "GLM-5V-Turboは、視覚的プログラミングタスク向けに設計されたZhipuのマルチモーダルコーディング基盤モデルです。画像、動画、テキスト、ファイルをネイティブに処理し、長期的な計画、複雑なコーディング、マルチモーダルワークフローにおけるエージェント実行に最適化されています。", "ru-RU": "GLM-5V-Turbo — это мультимодальная модель кодирования от Zhipu для задач визуального программирования. Она нативно обрабатывает изображения, видео, текст и файлы, оптимизирована для долгосрочного планирования, сложного кодирования и выполнения агентных задач в мультимодальных рабочих процессах." }, "price_history": [ { "date": "2026-08-10", "kind": "capability", "note": "open_weights: false→true" }, { "date": "2026-08-03", "kind": "capability", "note": "open_weights: true→false" }, { "date": "2026-07-02", "kind": "capability", "note": "web_search: false→true" } ] }, { "slug": "zhipuai/glm-image", "model_name": "glm-image", "display_name": "GLM-Image", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "image_output": { "unit": "per_image", "price": "0.014706" } }, "provenance": { "base_charges": { "image_output": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "released_at": "2026-01-14", "model_type": "image_generation", "capabilities": {}, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-Image 是智谱推出的新一代旗舰图像生成模型。该模型基于国产芯片进行端到端训练，采用原创的混合架构，将自回归建模与扩散解码器相结合。这种设计既能实现强大的全局指令理解，又能呈现细腻的局部细节，克服了生成知识密集型内容（如海报、演示文稿和教育图表）中的长期挑战。它代表了向新一代“认知生成”技术范式（以 Nano Banana Pro 为例）的重要探索。", "zh-TW": "GLM-Image 是智譜最新的旗艦圖像生成模型。該模型基於國產芯片進行端到端訓練，採用原創的混合架構，結合自回歸建模與擴散解碼器。此設計能夠實現強大的全局指令理解以及細緻的局部細節渲染，克服了生成知識密集型內容（如海報、演示文稿和教育圖表）中的長期挑戰。它代表了向新一代「認知生成」技術範式的重要探索，典範為 Nano Banana Pro。", "ja-JP": "GLM-Imageは、Zhipuの新しいフラッグシップ画像生成モデルです。このモデルは国内製のチップでエンドツーエンドでトレーニングされ、自己回帰モデリングと拡散デコーダーを組み合わせた独自のハイブリッドアーキテクチャを採用しています。この設計により、グローバルな指示理解能力と細かい局所的な詳細描写能力を両立し、ポスター、プレゼンテーション、教育用図表などの知識密度の高いコンテンツ生成における長年の課題を克服します。Nano Banana Proに代表される新世代の「認知生成」技術パラダイムへの重要な探求を示しています。", "ru-RU": "GLM-Image — это новая флагманская модель генерации изображений от Zhipu. Модель была обучена на отечественных чипах и использует оригинальную гибридную архитектуру, которая сочетает авторегрессионное моделирование с диффузионным декодером. Этот дизайн обеспечивает сильное понимание глобальных инструкций наряду с детальной проработкой локальных элементов, преодолевая давние проблемы в создании контента, насыщенного знаниями, такого как постеры, презентации и образовательные диаграммы. Это представляет собой важное исследование в направлении нового поколения парадигм «когнитивной генерации», примером которых является Nano Banana Pro." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-Image" } ] }, { "slug": "zhipuai/glm-z1-air", "model_name": "glm-z1-air", "display_name": "GLM-Z1-Air", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.073529" }, "completion": { "unit": "per_M_tokens", "price": "0.073529" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-04-15", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "具备强大推理能力的模型，适用于需要深度推理的任务。", "zh-TW": "具備強大推理能力的模型，適用於需要深度推理的任務。", "ja-JP": "深い推論が求められるタスクにおいて強力な推論能力を発揮するモデルです。", "ru-RU": "Модель логического вывода с высокой точностью для задач, требующих глубокого анализа." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "GLM-Z1-Air" } ] }, { "slug": "zhipuai/glm-z1-airx", "model_name": "glm-z1-airx", "display_name": "GLM-Z1-AirX", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.735294" }, "completion": { "unit": "per_M_tokens", "price": "0.735294" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 32768, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "function_calling": true, "reasoning": true, "web_search": true, "structured_output": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2025-04-15", "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "超快推理，兼具高质量推理表现。", "zh-TW": "超高速推理，兼具高品質推理表現。", "ja-JP": "高品質な推論を超高速で実現します。", "ru-RU": "Ультрабыстрая модель логического вывода с высоким качеством рассуждений." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "GLM-Z1-AirX" } ] }, { "slug": "zhipuai/glm-z1-flash", "model_name": "glm-z1-flash", "display_name": "GLM-Z1-Flash", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0" }, "completion": { "unit": "per_M_tokens", "price": "0" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "reasoning": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-Z1 系列具备强大的复杂推理能力，在逻辑、数学与编程方面表现出色。", "zh-TW": "GLM-Z1 系列具備強大的複雜推理能力，擅長邏輯、數學與程式任務。", "ja-JP": "GLM-Z1 シリーズは、論理、数学、プログラミングにおいて優れた複雑推論能力を発揮します。", "ru-RU": "Серия GLM-Z1 обеспечивает мощный логический вывод, особенно в задачах логики, математики и программирования." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-Z1-Flash" } ] }, { "slug": "zhipuai/glm-z1-flashx", "model_name": "glm-z1-flashx", "display_name": "GLM-Z1-FlashX", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "0.014706" }, "completion": { "unit": "per_M_tokens", "price": "0.014706" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 131072, "max_output_tokens": 32768, "model_type": "text_generation", "capabilities": { "reasoning": true, "web_search": true }, "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "快速且低成本：Flash 增强版，具备超快推理与更高并发能力。", "zh-TW": "快速且低成本：Flash 增強版，具備超快推理與高併發能力。", "ja-JP": "高速かつ低コスト：Flash による強化で超高速推論と高い同時実行性を実現します。", "ru-RU": "Быстрая и экономичная модель: ускоренная версия Flash с ультрабыстрым выводом и высокой параллельностью." }, "price_history": [ { "date": "2026-07-03", "kind": "listed", "note": "GLM-Z1-FlashX" } ] }, { "slug": "zhipuai/glm-zero-preview", "model_name": "glm-zero-preview", "display_name": "GLM-Zero-Preview", "vendor": "zhipuai", "pricing": [ { "provider": "zhipuai", "official": true, "source": "lobehub-modelbank", "charges": { "prompt": { "unit": "per_M_tokens", "price": "1.470588" }, "completion": { "unit": "per_M_tokens", "price": "1.470588" } }, "provenance": { "base_charges": { "prompt": "lobehub-modelbank", "completion": "lobehub-modelbank" }, "verification_status": "aggregator_only" } } ], "max_input_tokens": 16384, "model_type": "text_generation", "capabilities": { "reasoning": true, "prompt_caching": true }, "intro": "Compact GPT model for low-latency assistance and high-volume workloads", "released_at": "2024-12-20", "max_output_tokens": 4096, "modalities": { "input": [ "text" ], "output": [ "text" ] }, "family": "glm", "endpoints": { "inbound": [ "openai-compatible", "anthropic-messages" ], "outbound": [ "openai-compatible" ] }, "intro_i18n": { "zh-CN": "GLM-Zero-Preview 具备强大的复杂推理能力，在逻辑、数学与编程方面表现出色。", "zh-TW": "GLM-Zero-Preview 具備強大的複雜推理能力，擅長邏輯、數學與程式任務。", "ja-JP": "GLM-Zero-Preview は、論理、数学、プログラミングにおいて優れた複雑推論能力を発揮します。", "ru-RU": "GLM-Zero-Preview демонстрирует сильные способности к логическому выводу, особенно в логике, математике и программировании." }, "price_history": [ { "date": "2026-08-03", "kind": "capability", "note": "prompt_caching: false→true" }, { "date": "2026-07-03", "kind": "listed", "note": "GLM-Zero-Preview" } ] } ] }