freellmpool
A free LLM gateway that pools 22 providers and 178 keyless / free-tier chat routes behind one OpenAI-compatible endpoint — as a CLI, a Python library or a local proxy — with automatic failover and per-day usage tracking.
Installation & usage
README summary
A free LLM gateway that pools 22 providers and 178 keyless / free-tier chat routes behind one OpenAI-compatible endpoint — as a CLI, a Python library or a local proxy — with automatic failover and per-day usage tracking.
A free LLM gateway: one OpenAI-compatible endpoint over 22 providers, 178 enabled chat routes and 431 cataloged models — recurring free tiers, keyless endpoints and finite trials. Use it as a CLI (freellmpool ask), a Python library, or a local proxy. Keyless start when an enabled keyless route is up; add keys to unlock more. Automatic failover when a route is rate-limited or down, with local per-day usage tracking. Init wizard for wiring agent CLIs (OpenCode, Hermes) and an MCP server. Running agents and prototypes against free models without managing provider keys or quota walls one at a time.
Auto-extracted from the repository README. The authoritative steps live in the repository on GitHub.
Full README
freellmpool
A free LLM gateway: one OpenAI-compatible endpoint over 22 providers, 178 enabled chat routes and 431 cataloged models — recurring free tiers, keyless endpoints and finite trials.
What's inside
- Use it as a CLI (
freellmpool ask), a Python library, or a local proxy - Keyless start when an enabled keyless route is up; add keys to unlock more
- Automatic failover when a route is rate-limited or down, with local per-day usage tracking
- Init wizard for wiring agent CLIs (OpenCode, Hermes) and an MCP server
Use it for
Running agents and prototypes against free models without managing provider keys or quota walls one at a time.