Loading page
Loading page
AI · OpenRouter alternative
Combine free tiers from many LLM providers behind one OpenAI-compatible endpoint, with routing and automatic failover.
FreeLLMAPI is a router for LLM free tiers. Many AI labs offer a free tier with a limited number of tokens or requests. FreeLLMAPI stacks those tiers behind a single OpenAI-compatible endpoint. A router picks the best available model for each request, moves to the next provider when one hits a rate limit and tracks use per key.
It also accepts custom OpenAI-compatible chat, embedding, image and audio endpoints. A dashboard lets you manage keys, reorder the fallback chain, try models in a playground and read latency stats. The model catalog updates from a signed feed. Free installs get a monthly snapshot, and a paid tier gets updates the same day.
It is for developers who want to experiment with many models on a small budget. It suits hobby projects, coding agents for personal use and learning. It is single-user by design.
Your provider keys stay in your own database, encrypted at rest. Requests go from your server straight to the providers you enabled.
The project is open about the trade-offs. Free tiers are not stable infrastructure. There are no frontier models, latency varies and there is no SLA. Read each provider's terms. You keep the app updated and protect its dashboard login.
Containers: ghcr.io/tashfeenahmed/freellmapi:v0.8.4
Step 1
Choose the Starter plan. It costs $20 a month and runs up to 3 apps.
Step 2
Open App templates in the dashboard, choose FreeLLMAPI, and click Deploy. We set up the containers, secrets and domain.
Step 3
Wait a few minutes for the first deploy, then open your new URL and finish the FreeLLMAPI setup screen.