freellmapi

Why we included this project

Free LLM tiers are scattered across a dozen provider dashboards, each with its own SDK and rate limits. FreeLLMAPI pools the free allowances of 28 providers, roughly 4 billion tokens a month, and serves them through a single OpenAI-compatible /v1 endpoint. A router picks the best available model for each request, and when one provider is rate-limited it falls over to the next. It also tracks per-key usage so you stay under each free-tier cap. Because it exposes Anthropic and Gemini surfaces as well, existing tools like Claude Code, Codex, Aider, or Cursor can point at it with a one-command setup. The router refreshes its model catalog from a signed feed, so new free models and quota changes arrive without a manual pull. It's built for personal experimentation rather than production traffic, which makes it a cheap sandbox for developers who want broad model access without paying for every API.