Freellmapi

FreeLLMAPI puts the free tiers of dozens of model providers behind a single OpenAI-compatible /v1 endpoint, together with any custom endpoint you add yourself. A router picks an available model per request, fails over to the next provider when one is rate limited, and tracks usage per key so you stay inside each free-tier cap; keys are stored encrypted, and the model catalogue updates itself from a signed feed. The project states plainly that it is for personal experimentation, not production. TypeScript, MIT.