Quick Start
This guide gets Routeplane routing for your agent in under a minute. Routeplane runs as a local proxy, a single binary on your machine that routes LLM requests through your existing subscriptions.
Prerequisites
Section titled “Prerequisites”- The Routeplane binary. The source is in private preview — request access and I’ll get back to you personally. The rest of this guide assumes you have it installed.
Authenticate Providers
Section titled “Authenticate Providers”Login to the providers you subscribe to:
routeplane providers login github-copilotrouteplane providers login xairouteplane providers login openrouterUse routeplane providers list to see all available providers and their auth status.
Start the Proxy
Section titled “Start the Proxy”routeplane serveThe daemon starts on http://127.0.0.1:4356. It stays running in the background. Open a new terminal for the next step.
Test It
Section titled “Test It”curl http://127.0.0.1:4356/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "@fast", "messages": [{"role": "user", "content": "Hello!"}] }'Use model presets (@fast, @standard, @heavy) for automatic best-provider routing, or specify a provider directly like openai/gpt-4o.
Use With Any Agent
Section titled “Use With Any Agent”Point any OpenAI-compatible runtime at http://127.0.0.1:4356/v1 to route through Routeplane:
# Claude Codeclaude --proxy http://127.0.0.1:4356
# OpenCodeopencode --api-base http://127.0.0.1:4356
# Any OpenAI-compatible clientOPENAI_BASE_URL=http://127.0.0.1:4356/v1Next Steps
Section titled “Next Steps”- Model Presets — Learn about
@fast,@standard,@heavyand more - Integrations — Step-by-step guides for every supported agent runtime
- Provider Selection — How Routeplane routes to the best provider