FreeGate - Free multi-provider LLM proxy with automatic failover

by
Free open-source (MIT) LLM proxy that rotates 13+ free model providers (Groq, Mistral, Gemini, NVIDIA NIM, OpenRouter, ZAI) behind a single OpenAI-compatible endpoint. If one provider dies or burns its daily limit, your request automatically falls through to the next. Works with any OpenAI-compatible client — opencode, Cursor, or your own scripts. Dashboard with provider status, RPM graphs and limits, plus disk cache so repeated prompts don't cost twice. Install: npx freegate start.

Add a comment

Replies

Best
Maker
📌
Hey PH! I built DAVIL Cod because I was tired of my LLM bill growing while free tiers sat unused. It chains free models from Groq, Mistral, Gemini, NVIDIA NIM, OpenRouter and more behind one OpenAI-compatible endpoint — with a circuit breaker so a dead provider never kills your app. Disk cache means identical prompts don't cost you twice. It's MIT, runs anywhere (npm or Docker), and works with any OpenAI-compatible client including opencode and Cursor. Ask me anything!