Skip to content
CCHP is in private betaJoin the waitlist

Hi, here is CCHP.One gateway to align your AI ecosystem.

An experience-first, full-featured LLM gateway — routing, resilience, billing, audit, and observability behind one entry point.

We’re working to officially open-source the CCH Plus project under the AGPL license, in the CCH-HQ organization, this fall. It’s in private beta today — join the waitlist, or take the live demo for a spin.

Scroll to explore
Product

The dashboard, before you deploy anything

This is the overview screen from CCHP itself, rebuilt with the demo dataset. Switch metrics, hover the chart, watch live RPM tick — then open the full live demo.
live-demo.cch-plus.com/appOpen the full demo ↗
Acme Inc.RPM 66Error rate 0.55%TPM 686.4KDemo Super Admin

Dashboard

Edit dashboard
Live RPM
66/min
live
Spend today
$128.45
↑ +14.0%
Requests today
18.7K
↑ +16.3%
Success rate (24h)
99.49%
System health
RPM
66/min
TPM
686.4K/min
Error rate
0.55%
p50 latency
349ms
Usage trend
Users (3/3)Alice WangBob LiCarol Chen
$0.00$0.25$0.5000:0003:0006:0009:0012:0015:0018:0021:0023:00
Top users
  • 1Alice Wang$486.2
  • 2Bob Li$352.8
  • 3Carol Chen$214.6
View full ranking →
Top models
  • 1claude-opus-4$624.1
  • 2claude-sonnet-4$289.4
  • 3gpt-4o$197.3
  • 4gemini-2.5-pro$63.20
View full ranking →
Top providers
  • 1anthropic-prod$913.5
  • 2openai-fallback$197.3
  • 3gemini-experimental$63.20
View full ranking →
Capabilities

Built to end the gateway patchwork

Most solutions only solve one slice — forwarding without smart routing, proxying without isolation and audit, or monitoring without the full decision chain. CCHP covers all six.
High availability

Redesigned so requests keep succeeding

Intelligent fallback and a per-request decision chain keep requests succeeding. CCHP inspects streaming responses chunk by chunk to confirm a request actually returned valid content, and retries the ones that did not.
  • Per-request decision chain with smart model fallback
  • Chunk-by-chunk streaming content inspection
  • Automatic retry that closes the “fake 200” gap
Request transformers

One transformation core, every format

Built with the official SDKs of the three major providers as references. Specify the input and output format for any request and call any model the way you prefer.
  • OpenAI, Anthropic and Gemini formats in and out
  • Chat, image, embeddings, moderation and completions
  • Custom JSON, gRPC / Protobuf and SSE shapes
Privacy & prompt security

Catch leaks before they leave your boundary

Optional guardrails detect and block privacy leaks and prompt-injection attempts before requests ever reach an upstream provider.
  • PII filtering for names, IDs and phone numbers
  • Prompt-injection and jailbreak review
  • Safe content passes through untouched
Commercial capabilities

Run your own model marketplace

Everything you need to monetize access: multidimensional quotas, recharge packages, invitations, invoices and post-paid settlement.
  • Quotas by RPM, concurrency and time-window credits
  • Recharge packages, invitations and invoices
  • Post-paid settlement, OpenRouter-style
Adulteration detection

Make adulteration visible

Cache-hit-rate backtesting and model-probing surface providers with abnormal token usage or responses that do not match the requested model — without sending prompts you did not authorize.
  • 7-day cache-hit-rate anomaly backtesting
  • Model-probing for mismatched responses
  • Token-usage deviation alerts per provider
Plugin ecosystem

Extend CCHP with community plugins

A plugin surface lets the community extend CCHP. Plugin code stays owned by its contributors and may carry its own distribution license, giving community contributions room to grow.
  • Open, community-driven plugin surface
  • Contributors keep ownership of their code
  • Plugins ship with their own distribution license

Frequently asked questions

The things people most often ask — and most often get wrong — about CCHP and its licensing.

See CCHP in action

Explore the live demo, then join the waitlist to get early access and release news.