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).
Every copy-trading tool shows you winners. The hard question is what happens to everyone who copied the losers and whether the numbers you're shown can be checked at all.
We compute PnL and win rates directly from public on-chain data, so any trader's track record is verifiable before you follow them. But I'm genuinely curious what the community considers trustworthy:
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.
