GoModel is the fastest and the most resource-efficient AI Gateway (the self-reproducible benchmarks). It's an alternative to LiteLLM (which was hacked recently) and Portkey (which is no longer maintained on GitHub).
(click on the animation â to see the live demo)
GoModel saves you money and nerves.
Money - because you can remember the responses on this layer (caching), track your spending and do tricks like prompt compression and intelligent routing.
Nerves - because we strive to achieve good quality and reliability. Our ambition is to be the last AI gateway you will need - the most reliable, resource-optimal, feature-rich and fast.
## Quick Start **Step 1:** Install and start GoModel **macOS / Linux** ```bash curl -fsSL https://gomodel.enterpilot.io/install.sh | sh # OPENAI_API_KEY="your-openai-key" # (optional) gomodel ``` **Windows (PowerShell)** ```powershell irm https://gomodel.enterpilot.io/install.ps1 | iex # $env:OPENAI_API_KEY = "your-openai-key" # (optional) gomodel ``` **Docker** ```bash docker run --rm -p 8080:8080 \ -e OPENAI_API_KEY="your-openai-key" \ enterpilot/gomodel ``` âšī¸ Configure GoModel with `.env`, a `config.yaml` file, or manage the most important settings directly in the dashboard. âšī¸ See [`.env.template`](https://github.com/ENTERPILOT/GoModel/blob/HEAD/.env.template) for the complete list of environment variables, including all available providers. **Step 2:** Open the dashboard ```text http://localhost:8080/admin/dashboard ``` **Step 3:** Make an API call ```bash curl http://localhost:8080/v1/responses \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-5-chat-latest", "input": "Hello!" }' ``` ## GoModel and official SDKs GoModel accepts requests in two compatible formats: - OpenAI-compatible at `/v1` - Anthropic-compatible at `/v1/messages` The official SDKs therefore work unchanged. Configure their base URLs as follows: - OpenAI SDK: `http://localhost:8080/v1` - Anthropic SDK: `http://localhost:8080` (the SDK appends `/v1/messages`) ## List of Supported LLM Providers - OpenAI - Anthropic - xAI (Grok) - Google Gemini - Cohere - Vertex AI - DeepSeek - Groq - Fireworks AI - Meta (Muse Spark) - OpenRouter - Z.ai - Alibaba Cloud Model Studio (Bailian) - Kilo AI - MiniMax - Xiaomi MiMo - OpenCode Go - Azure OpenAI - Oracle - Ollama - SGLang - vLLM - llm-d - Amazon Bedrock Runtime and Bedrock Mantle - ChatGPT (the Codex backend) and Claude - ElevenLabs (text-to-speech and speech-to-text) - Jev (TypeSafe System One decision API) and self-hosted Kev - All OpenAI-compatible providers See the [Providers Overview](https://gomodel.enterpilot.io/docs/providers/overview?utm_source=readme) for the full per-provider feature matrix. --- ## Docker Compose **Infrastructure only** (Redis, PostgreSQL, MongoDB, Adminer - no image build): ```bash cp .env.template .env # Add your API keys to .env docker compose up -d # or: make infra ``` **Full stack** (adds GoModel + Prometheus; builds the app image): ```bash docker compose --profile app up -d # or: make image ``` --- ## API docs - [API Endpoints](https://gomodel.enterpilot.io/docs/advanced/api-endpoints?utm_source=readme) - [Admin API Endpoints](https://gomodel.enterpilot.io/docs/advanced/admin-endpoints?utm_source=readme) --- ## Gateway Configuration GoModel resolves configuration in the following order, with each source overriding those to its left: [Good defaults](https://gomodel.enterpilot.io/docs/about/technical-philosophy#good-defaults) â [`config.yaml`](https://github.com/ENTERPILOT/GoModel/blob/HEAD/config/config.example.yaml) â [`.env`](https://github.com/ENTERPILOT/GoModel/blob/HEAD/.env.template) â exported environment variables See the [Configuration reference](https://gomodel.enterpilot.io/docs/advanced/configuration?utm_source=readme) for the full list of settings. --- ## Features - [Caching](https://gomodel.enterpilot.io/docs/features/cache?utm_source=readme) - exact and semantic response caching, so repeated prompts cost nothing - [Cost tracking](https://gomodel.enterpilot.io/docs/features/cost-tracking?utm_source=readme) - per-request cost estimates, usage analytics, and spending breakdowns in the dashboard - [Budgets](https://gomodel.enterpilot.io/docs/features/budgets?utm_source=readme) - hard spend limits per user, team, or key - [Rate limits](https://gomodel.enterpilot.io/docs/features/rate-limits?utm_source=readme) - requests, tokens, and concurrency caps per user path, provider, or model - [Usage API](https://gomodel.enterpilot.io/docs/advanced/usage-api?utm_source=readme) - clients check their own usage, remaining budget, and rate-limit headroom with the key they already use for inference - [Virtual models](https://gomodel.enterpilot.io/docs/features/virtual-models?utm_source=readme) - aliases and load balancing (round-robin or cost-based) behind stable model names - [Session keeping](https://gomodel.enterpilot.io/docs/features/session-keeping?utm_source=readme) - detect a client session and pin it to one target and provider key, so provider prompt caches stay warm and audit logs read as threads - [Failover](https://gomodel.enterpilot.io/docs/features/failover?utm_source=readme) - automatic rerouting to backup providers, with [retries and circuit breakers](https://gomodel.enterpilot.io/docs/advanced/resilience?utm_source=readme) - [Labelling](https://gomodel.enterpilot.io/docs/features/labelling?utm_source=readme) - tag requests from HTTP headers or API keys and break down usage by label - [User paths](https://gomodel.enterpilot.io/docs/features/user-path?utm_source=readme) - hierarchical scoping of keys, model access, budgets, usage, and audit logs - [Model access control](https://gomodel.enterpilot.io/docs/features/users?utm_source=readme) - per-group, per-user, and per-key model allowlists that intersect down the user-path tree - [MCP gateway](https://gomodel.enterpilot.io/docs/features/mcp-gateway?utm_source=readme) - aggregate your MCP servers behind one authenticated endpoint - [Passthrough API](https://gomodel.enterpilot.io/docs/features/passthrough-api?utm_source=readme) - provider-native APIs under `/p/{provider}/...`, with GoModel auth and tracking - [Audio and image APIs](https://gomodel.enterpilot.io/docs/advanced/audio-api?utm_source=readme) - OpenAI-compatible text-to-speech, transcription, and [image generation and editing](https://gomodel.enterpilot.io/docs/advanced/images-api?utm_source=readme) with the same access rules, budgets, and cost tracking as chat - [Provider replay state](https://gomodel.enterpilot.io/docs/advanced/extra-content?utm_source=readme) - preserves Gemini thought signatures and Anthropic thinking blocks across turns, APIs, and providers - [Guardrails](https://gomodel.enterpilot.io/docs/advanced/guardrails?utm_source=readme) - request and response policies enforced at the gateway - [Plugins](https://gomodel.enterpilot.io/docs/advanced/plugins?utm_source=readme) - one contract for guardrails, response and stream filters, header edits, and routing strategies; built in, compiled in, or loaded from a `.so` at startup - [Workflows](https://gomodel.enterpilot.io/docs/advanced/workflows?utm_source=readme) - versioned per-request policies that scope cache, budgets, audit logging, guardrail phases, and failover by user path, provider, or model - [Provider key rotation](https://gomodel.enterpilot.io/docs/providers/key-rotation?utm_source=readme) - round-robin over multiple API keys to lift per-key rate limits - [Observability](https://gomodel.enterpilot.io/docs/guides/prometheus-metrics?utm_source=readme) - Prometheus metrics, [OpenTelemetry](https://gomodel.enterpilot.io/docs/guides/opentelemetry?utm_source=readme) traces, audit logs, and live request streaming in the dashboard - [Playground](https://gomodel.enterpilot.io/docs/features/playground?utm_source=readme) - try any model or virtual model from the dashboard and inspect the exact request and response JSON ## GoModel Pro [GoModel Pro](https://gomodel.enterpilot.io/docs/pro/overview?utm_source=readme) is the commercial build: the same gateway, configuration, and dashboard, with licensed extensions. - [Prompt compression](https://gomodel.enterpilot.io/docs/pro/compression?utm_source=readme) - remove repeated and structural context before it reaches the provider, without changing the request shape - [Intelligent routing](https://gomodel.enterpilot.io/docs/pro/intelligent-routing?utm_source=readme) - classify each request as easy or hard, then pick the healthiest and cheapest provider in that tier - [OIDC single sign-on](https://gomodel.enterpilot.io/docs/pro/sso?utm_source=readme) - protect the dashboard with your identity provider using Authorization Code flow with PKCE More in the documentation... ## Roadmap See the [roadmap](https://gomodel.enterpilot.io/docs/about/roadmap?utm_source=readme) for GoModel Pro and the upcoming 0.2.0 release. ## Sponsors
## Community
We are on [Discord](https://discord.gg/gaEB9BQSPH). Feel free to stop by and tell us what you think about GoModel.