OpenRouter Free Catcher

Web UI + OpenAI-compatible API proxy for OpenRouter free models, auto-selected by Top Weekly ranking.

Features

• Auto model selection — Picks the highest-ranked free model from OpenRouter's weekly leaderboard
• OpenAI-compatible API — Drop-in replacement for /v1/chat/completions and /v1/models
• Web UI — Browse free models, configure API key, test chat in browser
• Streaming support — SSE streaming for real-time responses
• 5-min cache — Model list cached to reduce API calls

Quick Start

pip install -e .

Set your OpenRouter API key:

export OPENROUTER_API_KEY="sk-or-..."

Start the server:

python -m catcher

Open http://localhost:8000

API Usage

List free models

curl http://localhost:8000/v1/models

Chat completion (auto model)

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{"model":"auto","messages":[{"role":"user","content":"Hello!"}]}'

Chat completion (specific model)

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{"model":"qwen/qwen3.6-plus:free","messages":[{"role":"user","content":"Hello!"}]}'

Streaming

curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -d '{"model":"auto","messages":[{"role":"user","content":"Hello!"}],"stream":true}'

Endpoints

Endpoint	Description
GET /	Web UI
GET /api/models	Free models with full details (ranked)
GET /v1/models	OpenAI-compatible model list
POST /v1/chat/completions	OpenAI-compatible chat proxy

Configuration

Variable	Description	Default
OPENROUTER_API_KEY	OpenRouter API key (or pass via Authorization header)	—

Tech Stack

• FastAPI — async web framework
• httpx — async HTTP client
• uvicorn — ASGI server

License

MIT