Freellmapi Proxy

If you've ever wanted to stop juggling 14 different free-tier API keys and just hit one endpoint, this is exactly that. It's a self-hosted OpenAI-compatible proxy that routes requests across Google, Groq, Cerebras, SambaNova, NVIDIA, and nine other providers with automatic failover when you hit rate limits. Keys are AES-256 encrypted in SQLite, you get a web dashboard to manage the fallback chain, and it handles tool calling translation for providers like Gemini that don't speak OpenAI's format natively. It's honest infrastructure for prototyping without spending money or writing adapter code for every provider's quirks.

skills.sh installs: 212
GitHub stars: 26
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add aradotso/trending-skills --skill freellmapi-proxy --agent claude-code

Installs into .claude/skills of the current project.

Files

FreeLLMAPI Proxy

Skill by ara.so — Daily 2026 Skills collection.

FreeLLMAPI is a self-hosted OpenAI-compatible proxy that aggregates free-tier API keys from ~14 AI providers (Google, Groq, Cerebras, SambaNova, NVIDIA, Mistral, OpenRouter, GitHub Models, Hugging Face, Cohere, Cloudflare, Zhipu, Moonshot, MiniMax) behind a single /v1/chat/completions endpoint. It handles automatic failover on 429/5xx, per-key rate tracking, sticky sessions for multi-turn conversations, and AES-256-GCM encrypted key storage.

Installation

Prerequisites: Node.js 20+, npm.

git clone https://github.com/tashfeenahmed/freellmapi.git
cd freellmapi
npm install

# Generate encryption key and set up environment
cp .env.example .env
echo "ENCRYPTION_KEY=$(node -e "console.log(require('crypto').randomBytes(32).toString('hex'))")" >> .env

# Development (server + Vite dashboard on :5173)
npm run dev

# Production build
npm run build
node server/dist/index.js   # serves API + dashboard on :3001