Launching today

FreeGate

Launching today

Free multi-provider LLM proxy with automatic failover

0 followers

Free multi-provider LLM proxy with automatic failover

0 followers

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.

Launch tags:Developer Tools•Artificial Intelligence•GitHub

Launch Team

Viktor.comAn AI coworker that actually does the work

Promoted

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!

Report

5d ago

Forum Threads

p/davil-cod

•

13h ago

Which free LLM tier actually survived your production workload?

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).

View all