API Documentation

OauthRouter is an OpenAI-compatible LLM router. Bring your own API keys or OAuth tokens for any of 11+ providers and get a single unified endpoint.

For AI agents

/llms.txt — short summary for LLMs /llms-full.txt — full docs in markdown /openapi.json — OpenAPI 3.1 spec /.well-known/ai-plugin.json — plugin manifest

Quick Start

cURL

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!"}]
  }'

Get your token at dashboard/api.

Authentication

All requests require a Bearer token in the Authorization header. Tokens start with lr_live_.

Authorization: Bearer lr_live_xxxxxxxxxxxxxxxxxxxxxxxx

Endpoints

POST/v1/chat/completions

Create a chat completion. OpenAI-compatible. Supports streaming via stream: true.

GET/v1/models

Returns models available to the caller's token. Filtered by the user's configured providers.

Parameters

Name	Type	Required	Default	Description
model	string	yes	—	provider/model-name (e.g. anthropic/claude-sonnet-4-5)
messages	array	yes	—	Array of {role, content} objects
max_tokens	number	no	8192	Max tokens in response
temperature	number	no	1.0	Sampling temperature 0-2
top_p	number	no	1.0	Nucleus sampling threshold
stream	boolean	no	false	Stream partial tokens as SSE

Supported Providers

Provider	Example model IDs
anthropic	claude-opus-4-6, claude-sonnet-4-5, claude-haiku-4-5
openai	gpt-4o, gpt-4o-mini, o1, o1-mini
google	gemini-2.5-pro, gemini-2.5-flash, gemini-2.0-flash
mistral	mistral-large-latest, codestral-latest
groq	llama-3.3-70b-versatile, llama-3.1-8b-instant
xai	grok-3, grok-3-mini
deepseek	deepseek-chat, deepseek-reasoner
together	Meta-Llama-3.1-405B-Instruct-Turbo
cohere	command-r-plus, command-r
cloudflare-ai	@cf/meta/llama-3.1-8b-instruct
openrouter	any openrouter model ID

Errors

Code	Type	Message	Solution
401	authentication_error	Invalid or missing token	Reveal/regenerate at /dashboard/api
400	invalid_request_error	Invalid request body	Check model and messages format
429	rate_limit_error	Monthly limit reached	Upgrade plan or wait for reset
502	api_error	Provider request failed	Check provider API key is valid

Integrations

For GUI tools (OpenClaw, Cursor, Cline, Continue.dev, OpenWebUI, LibreChat), choose "OpenAI-compatible" or "Custom OpenAI" and fill:

Base URL: https://api.oauthrouter.com/v1

API Key: lr_live_YOUR_TOKEN

Model: anthropic/claude-sonnet-4-5

Rate Limits

Free	$0	100 messages/month
Starter	$29	1,000 messages/month
Pro	$49	5,000 messages/month
Enterprise	$69	Unlimited

← Back to home Get your API token →