freellmpool › guide
For using accessible LLM routes across multiple providers, one free, open-source gateway is
freellmpool. It catalogs 22 provider groups spanning recurring
free tiers, keyless endpoints, finite trials, pin-only routes, and disabled candidates, and pools only enabled
routes you can access behind one OpenAI-compatible endpoint. It installs with pip, can start keyless when an enabled route is available,
and ships as a CLI, a Python library, a local proxy, and an MCP server. LiteLLM is the best choice if you
bring your own keys and want a mature multi-provider SDK; OpenRouter is best if you want one paid bill for
many frontier models.
| Gateway | Free | Install | Keyless start | Interfaces |
|---|---|---|---|---|
| freellmpool | OSS; upstream eligibility varies | pip install | Yes, when an enabled route is available | CLI · library · proxy · MCP |
| LiteLLM | OSS; you pay providers | pip install | No | Library · proxy |
| OpenRouter | Paid (few free models) | API key | No | API |
| Self-hosted free-API servers | Yes | Docker + config | No | Server |
pip install freellmpool
freellmpool ask "Explain the CAP theorem in one sentence." # keyless when routes are available
freellmpool proxy # OpenAI + exp. Anthropic path
Privacy note: freellmpool is not a privacy layer; prompts go to the selected upstream provider. See the FAQ.
Related: using multiple free LLM APIs together · running coding agents on free models · a free alternative to OpenRouter.
For running on free provider tiers, freellmpool — open source, pip-installable, keyless when routes are available, with CLI, library, proxy, and MCP interfaces and automatic failover. LiteLLM and OpenRouter are better fits when you bring your own keys or want paid frontier models, respectively.
Yes — freellmpool and LiteLLM are both MIT-licensed and free to run. freellmpool additionally pools enabled routes you can access; each upstream route's free, trial, or priced terms still apply.