Reading the repo
Reading the repo
Assembly instructions
7.4 billion tokens per month. 34 free LLM providers. 635 free model endpoints. All behind one /v1 endpoint, plus any custom OpenAI-compatible endpoint. Smart routing, automatic failover, encrypted keys. Personal experimentation only.
Saved setup from 12 h ago
Will it work on my device?
<i>… plus Continue, Goose, Qwen Code, Kilo Code, Crush, Zed, JetBrains AI, DeepSeek Harness, MiMo Code, AtomCode, OpenClaw, Hermes Agent, Pi, Reasonix, ZCode and any OpenAI-compatible, Anthropic, Gemini or Ollama client</i>
</div>Most agents configure themselves with one command that reads your live catalog, backs up the existing config and merges into it:
npx freellmapi setup-claude --url http://localhost:3001 --api-key <unified-key>
All supported agents and their setup commands → · Per-tool recipes, MCP server and URL tokens →
curl -LO "https://github.com/tashfeenahmed/freellmapi/releases/download/v0.16.20/FreeLLMAPI-0.16.20-arm64.dmg" open "FreeLLMAPI-0.16.20-arm64.dmg"
curl -LO "https://github.com/tashfeenahmed/freellmapi/releases/download/v0.16.20/FreeLLMAPI-0.16.20-x64.dmg" open "FreeLLMAPI-0.16.20-x64.dmg"
curl -fsSL https://freellmapi.co/install.sh | bash
From the README, exactly as the maintainers wrote it.
No reports for macOS yet.
Opens a chat with this manual already filled in, for macOS. It uses your own account; gitmanual sends nothing.