FreeLLMAPI

FreeLLMAPI aggregates free tiers from 14 AI providers into one OpenAI-compatible endpoint, totaling ~1.3B tokens/month. Use a single unified API key — the proxy auto-selects the best provider and fails over when one hits rate limits. All API keys are AES-256-GCM encrypted at rest, decrypted in memory only when needed.

Google Gemini Pro/Flash, Groq, Cerebras, SambaNova, NVIDIA NIM, Mistral, OpenRouter, GitHub Models (GPT-4o), HuggingFace, Cohere, Cloudflare Workers AI, Zhipu GLM-4, Moonshot Kimi, MiniMax. Covers GPT-4o level to Llama 3.3 70B and more.

git clone → npm install → cp .env.example .env → generate encryption key → npm run dev. Open localhost:5173, add your provider API keys, set Fallback Chain priority, then use the unified key with your proxy as base_url. Supports model="auto" for automatic routing.