Use free LLMs in Simon Willison's llm CLI via freellmpool — pool 16 free providers, works with zero API keys.
Project description
llm-freellmpool
A plugin for llm that lets you run free LLMs through freellmpool — which pools the free tiers of 16 providers (Groq, Cerebras, NVIDIA NIM, Gemini, OpenRouter, Cloudflare, …) with automatic failover. It works with zero API keys thanks to freellmpool's keyless providers.
Install
llm install llm-freellmpool
Use
llm -m freellmpool "Explain the CAP theorem in one sentence."
That's it — no key required. Pipe context in like any llm model:
cat error.log | llm -m freellmpool "What's the root cause?"
Pick a specific free provider or model with the target option:
llm -m freellmpool -o target groq "Say hi"
llm -m freellmpool -o target groq/llama-3.3-70b-versatile "Say hi"
More providers
Add provider keys as environment variables (GROQ_API_KEY, CEREBRAS_API_KEY, …)
to unlock more models and higher limits. See the
freellmpool docs.
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file llm_freellmpool-0.1.0.tar.gz.
File metadata
- Download URL: llm_freellmpool-0.1.0.tar.gz
- Upload date:
- Size: 3.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
dc5e17c59cdebb9a4a42566e26165a245cf6841406e91f7547ad5fdfc9449536
|
|
| MD5 |
ccd9095182089b9f3916044afb5ff473
|
|
| BLAKE2b-256 |
af6617b317c468e833f7db1f68402817324f2d515fec0e2b99b641bcf8593623
|
File details
Details for the file llm_freellmpool-0.1.0-py3-none-any.whl.
File metadata
- Download URL: llm_freellmpool-0.1.0-py3-none-any.whl
- Upload date:
- Size: 3.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.12.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d9e1d191c794aea91db0d283c33bd1cce0fe5cd0e72d3b8b67942a8f3f36555b
|
|
| MD5 |
919c0d6d151e59093394d78f403925be
|
|
| BLAKE2b-256 |
3e8d18d32293117316fa4207e7470431473541f26f8ab683ffa934b8d71f1917
|