# AI Model Gateway

AI Model Gateway is a self-hosted LLM operations gateway for teams that want routing, provider fallback, telemetry, benchmarks, config publishing, diagnostics, updates, and rollback inside their own environment.

It is not a hosted model marketplace. The project is built for local control over provider keys, routing policy, traffic telemetry, audit records, and operational workflows.

## Primary Links

- Website: https://ssc-studio.github.io/Ai-Model-Gateway/
- Website review evidence: https://ssc-studio.github.io/Ai-Model-Gateway/#review-evidence
- OpenAI-compatible LLM gateway page: https://ssc-studio.github.io/Ai-Model-Gateway/openai-compatible-llm-gateway.html
- LLM client integrations page: https://ssc-studio.github.io/Ai-Model-Gateway/client-integrations.html
- Codex CLI gateway page: https://ssc-studio.github.io/Ai-Model-Gateway/codex-cli-gateway.html
- Claude Code gateway page: https://ssc-studio.github.io/Ai-Model-Gateway/claude-code-gateway.html
- LLM gateway adoption checklist: https://ssc-studio.github.io/Ai-Model-Gateway/llm-gateway-adoption-checklist.html
- OpenAI Anthropic gateway page: https://ssc-studio.github.io/Ai-Model-Gateway/openai-anthropic-gateway.html
- LLM provider fallback gateway page: https://ssc-studio.github.io/Ai-Model-Gateway/llm-provider-fallback-gateway.html
- Self-hosted LLM gateway page: https://ssc-studio.github.io/Ai-Model-Gateway/self-hosted-llm-gateway.html
- Chinese self-hosted LLM gateway page: https://ssc-studio.github.io/Ai-Model-Gateway/self-hosted-llm-gateway-zh.html
- LLM gateway comparison page: https://ssc-studio.github.io/Ai-Model-Gateway/llm-gateway-comparison.html
- Share kit: https://ssc-studio.github.io/Ai-Model-Gateway/share-kit.html
- Chinese share kit: https://ssc-studio.github.io/Ai-Model-Gateway/share-kit-zh.html
- GitHub repository: https://github.com/SSC-STUDIO/Ai-Model-Gateway
- Latest release: https://github.com/SSC-STUDIO/Ai-Model-Gateway/releases/tag/v1.4.4
- Current release summary: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/release-v1.4.4.md
- Documentation index: https://github.com/SSC-STUDIO/Ai-Model-Gateway/tree/main/docs
- Maintainer discussion: https://github.com/SSC-STUDIO/Ai-Model-Gateway/discussions/25

## Evaluation

- 15-minute evaluation path: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/evaluate-in-15-minutes.md
- Self-hosted LLM gateway checklist: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/self-hosted-llm-gateway-checklist.md
- LLM gateway adoption checklist: https://ssc-studio.github.io/Ai-Model-Gateway/llm-gateway-adoption-checklist.html
- Installation guide: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/installation.md
- Release archive install path: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/installation.md#install-from-a-release-archive
- Deployment guide: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/deployment.md
- Troubleshooting guide: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/troubleshooting.md
- LLM gateway comparison guide: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/llm-gateway-comparison.md
- LLM gateway comparison landing page: https://ssc-studio.github.io/Ai-Model-Gateway/llm-gateway-comparison.html
- OpenAI Anthropic gateway landing page: https://ssc-studio.github.io/Ai-Model-Gateway/openai-anthropic-gateway.html
- Quality evidence: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/quality-evidence.md
- Security and trust model: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/security-trust-model.md

## Technical Proof Points

- Provider fallback and health operations: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/provider-fallback-health.md
- Provider fallback gateway landing page: https://ssc-studio.github.io/Ai-Model-Gateway/llm-provider-fallback-gateway.html
- Self-hosted LLM gateway landing page: https://ssc-studio.github.io/Ai-Model-Gateway/self-hosted-llm-gateway.html
- Chinese self-hosted LLM gateway landing page: https://ssc-studio.github.io/Ai-Model-Gateway/self-hosted-llm-gateway-zh.html
- OpenAI Anthropic gateway landing page: https://ssc-studio.github.io/Ai-Model-Gateway/openai-anthropic-gateway.html
- Executable provider fallback demo: https://github.com/SSC-STUDIO/Ai-Model-Gateway/tree/main/examples/provider-fallback
- Config publish and rollback: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/config-publish-rollback.md
- OpenAI-compatible upstreams: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/openai-compatible-upstreams.md
- Client integrations: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/client-integrations.md
- LLM client integrations landing page: https://ssc-studio.github.io/Ai-Model-Gateway/client-integrations.html
- Codex CLI gateway landing page: https://ssc-studio.github.io/Ai-Model-Gateway/codex-cli-gateway.html
- Claude Code gateway landing page: https://ssc-studio.github.io/Ai-Model-Gateway/claude-code-gateway.html
- LLM gateway adoption checklist landing page: https://ssc-studio.github.io/Ai-Model-Gateway/llm-gateway-adoption-checklist.html
- Project roadmap: https://github.com/SSC-STUDIO/Ai-Model-Gateway/blob/main/docs/roadmap.md
- Copy-ready share kit: https://ssc-studio.github.io/Ai-Model-Gateway/share-kit.html
- Copy-ready Chinese share kit: https://ssc-studio.github.io/Ai-Model-Gateway/share-kit-zh.html

## Capabilities

- OpenAI-compatible, Anthropic-compatible, and Responses-compatible entry points.
- Provider routing, fallback, health checks, cooldowns, and local routing policy.
- Telemetry for traffic, latency, model usage, provider health, request logs, and cost signals.
- Benchmarking with exact, judge, JSON, tool, and stream scoring.
- Config preview, diff, validation, publish, audit, and rollback.
- Manifest-verified update and rollback workflow for local runtime bundles.

## Suggested Summary

AI Model Gateway is a self-hosted LLM operations gateway for teams that need local control over routing, provider fallback, telemetry, benchmarking, config publishing, diagnostics, updates, and rollback.