# OauthRouter

> LLM router with OAuth — route AI models from Anthropic, OpenAI, Google, Mistral, Groq, xAI, DeepSeek, Together, Cohere, Cloudflare AI and OpenRouter through a single OpenAI-compatible API using your own API keys or OAuth tokens. No markup on tokens.

## Quick start

Base URL: `https://api.oauthrouter.com/v1`
Auth: Bearer token starting with `lr_live_` (sign up at https://oauthrouter.com to get one)

```bash
curl https://api.oauthrouter.com/v1/chat/completions \
  -H "Authorization: Bearer lr_live_YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-sonnet-4-5","messages":[{"role":"user","content":"Hello"}]}'
```

## Endpoints

- `POST /v1/chat/completions` — OpenAI-compatible chat completions (streaming and non-streaming)
- `GET /v1/models` — list models available to the caller's token (filtered by configured providers)

## Model format

`provider/model-name` — e.g. `anthropic/claude-sonnet-4-5`, `openai/gpt-4o`, `google/gemini-2.5-pro`. The plain model name without prefix also works (e.g. `claude-sonnet-4-5`).

## Docs

- Full docs (markdown): https://oauthrouter.com/llms-full.txt
- Human docs (HTML): https://oauthrouter.com/docs
- OpenAPI spec: https://oauthrouter.com/openapi.json
- Dashboard: https://oauthrouter.com/dashboard