Deploy OrcaRouter Lite

Deploy and Host OrcaRouter Lite on Railway

OrcaRouter Lite is a self-hosted, OpenAI-compatible LLM router. Bring your own provider keys (OpenAI, Anthropic, Google, Groq, Together, Fireworks, xAI, DeepSeek), send model="auto" and it picks the cheapest model that meets the request's needs (tools, vision, JSON mode). It also speaks the Anthropic and Gemini APIs, streams, and ships a dashboard for providers, keys, routing and savings.

About Hosting OrcaRouter Lite

This template builds the official Dockerfile from the repository and runs a single service:

• SQLite on a persistent volume at /data, so providers, keys and settings survive redeploys
• CREDENTIAL_ENCRYPTION_KEY and API_KEY_PEPPER generated per deployment, so provider keys stored in the dashboard are encrypted with your own key (never the built-in development key)
• a healthcheck on /health; the dashboard API and /v1 require the gateway API key

After deploy:

1. Open the service's Deploy Logs and copy the API key from the line orcarouter-lite ready. API key: sk-orca-....
2. Open the service domain and sign in to the dashboard with that key.
3. Add your provider keys in the dashboard (stored encrypted), or set them as service variables (OPENAI_API_KEY, ANTHROPIC_API_KEY, GOOGLE_API_KEY, ...).
4. Point any OpenAI SDK at https://YOUR-RAILWAY-DOMAIN/v1 with the sk-orca-... key and model="auto".

Keep CREDENTIAL_ENCRYPTION_KEY unchanged after the first deploy: rotating it without the documented migrate step makes stored provider keys undecryptable.

Common Use Cases

• One OpenAI-compatible endpoint for several providers with your own keys
• Automatic cheapest-capable model selection with model="auto"
• Failover between providers when one is down or rate-limited
• Pointing Claude Code or Gemini SDKs at a single self-hosted router

Dependencies for OrcaRouter Lite Hosting

• Source: https://github.com/Continuum-AI-Corp/OrcaRouter-Lite (built from main)
• At least one LLM provider API key

Deployment Dependencies

• Repository: https://github.com/Continuum-AI-Corp/OrcaRouter-Lite
• Environment reference: https://github.com/Continuum-AI-Corp/OrcaRouter-Lite/blob/main/.env.example

Implementation Details

Postgres and Redis are optional upstream; this template uses SQLite on a volume for a single-instance setup. RAILWAY_RUN_UID=0 lets the process write to the volume, which Railway mounts as root.

Why Deploy OrcaRouter Lite on Railway?

Railway is a singular platform to deploy your infrastructure stack. Railway will host your infrastructure so you don't have to deal with configuration, while allowing you to vertically and horizontally scale it.

By deploying OrcaRouter Lite on Railway, you are one step closer to supporting a complete full-stack application with minimal burden. Host your servers, databases, AI agents, and more on Railway.