Self-hostable router that aggregates free tiers from 34 LLM providers and 635 free model endpoints behind one OpenAI-compatible /v1 API.

FreeLLMAPI works by combining Unified OpenAI-Compatible Endpoint: Exposes 635 free model endpoints from 34 providers behind a single /v1 API that existing OpenAI clients can use unchanged., Smart Model Router: Selects the best available model per request and automatically falls over to another provider when one returns a rate limit., Per-Key Quota Tracking: Monitors usage against each provider's free tier cap so requests are spread out and no individual key is exhausted., Encrypted Key Storage: Provider API keys are stored encrypted rather than in plaintext configuration files., Custom Endpoint Support: Any additional OpenAI-compatible chat, embedding, image or audio endpoint can be registered alongside the built-in providers. to help users with Zero-Cost Prototyping: Build and test an LLM application against free provider tiers before committing to a paid API contract., Rate Limit Resilience: Keep a coding agent or chatbot running through provider rate limits by automatically failing over to another free endpoint., Coding Agent Backend: Point Cursor, Claude Code or any OpenAI-compatible CLI at a single local endpoint instead of juggling provider keys per tool., Model Comparison: Evaluate responses across hundreds of models from different labs through one consistent API surface., Private Gateway Deployment: Self-host the router inside a network so provider keys and prompts never pass through a third-party proxy..

Key features include Unified OpenAI-Compatible Endpoint: Exposes 635 free model endpoints from 34 providers behind a single /v1 API that existing OpenAI clients can use unchanged., Smart Model Router: Selects the best available model per request and automatically falls over to another provider when one returns a rate limit., Per-Key Quota Tracking: Monitors usage against each provider's free tier cap so requests are spread out and no individual key is exhausted., Encrypted Key Storage: Provider API keys are stored encrypted rather than in plaintext configuration files., Custom Endpoint Support: Any additional OpenAI-compatible chat, embedding, image or audio endpoint can be registered alongside the built-in providers..

FreeLLMAPI is useful for anyone interested in Zero-Cost Prototyping: Build and test an LLM application against free provider tiers before committing to a paid API contract., Rate Limit Resilience: Keep a coding agent or chatbot running through provider rate limits by automatically failing over to another free endpoint., Coding Agent Backend: Point Cursor, Claude Code or any OpenAI-compatible CLI at a single local endpoint instead of juggling provider keys per tool., Model Comparison: Evaluate responses across hundreds of models from different labs through one consistent API surface., Private Gateway Deployment: Self-host the router inside a network so provider keys and prompts never pass through a third-party proxy..

FreeLLMAPI offers a free tier with paid plans for advanced features.

Visit https://github.com/tashfeenahmed/freellmapi to sign up and explore FreeLLMAPI.