Every free tier is amazing until the day you actually depend on it: Groq hits RPM, Gemini throttles context, a provider silently degrades quality.
We ended up building a router that chains 25 free providers behind one OpenAI-compatible endpoint circuit breaker, disk cache for repeated prompts, live dashboard of limits. It launched here on PH today as FreeGate (MIT, npm/Docker).
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.
