Deploy and Host FreeLLMAPI on Railway

FreeLLMAPI is a self-hosted router that puts many LLM providers' free tiers behind a single OpenAI-compatible /v1 endpoint. You add your own provider keys, and it picks a model for each request and falls over to the next provider when one is rate-limited.

About Hosting FreeLLMAPI

This template runs the official ghcr.io/tashfeenahmed/freellmapi:latest image with a persistent volume at /app/server/data (SQLite database). A random ENCRYPTION_KEY is generated for you; it encrypts the provider keys stored in the database, so do not change or delete it after first start. On first visit, create the dashboard account (the first visitor becomes the owner, so do it right after the deploy), add your provider keys on the Keys page and copy the unified API key from the page header. Point your OpenAI client at https:///v1 with that key.

Common Use Cases

Give coding agents and OpenAI SDK clients one endpoint backed by several free tiers
Fail over automatically when a provider hits its rate limit
Track per-key usage against free-tier caps

Dependencies for FreeLLMAPI Hosting

One service with a volume; nothing else. You bring your own provider API keys.

Deployment Dependencies

Why Deploy FreeLLMAPI on Railway?

Railway gives you a public HTTPS URL, a persistent volume and automatic restarts with no server to maintain. Keep the dashboard account password safe: anyone with the unified API key can spend your free-tier quotas.