llm-github-models

What it is and what it does

llm-github-models is a plugin that extends the llm command-line tool to access GitHub Models, a free service offering dozens of AI language models including GPT-4o, o3, DeepSeek-R1, and Llama variants. It uses the Azure AI Inference SDK to communicate with the GitHub Models API and requires only a GitHub personal access token or existing GITHUB_TOKEN environment variable for authentication.

The plugin supports text-only and multimodal (image, audio) models, streaming and async outputs, structured schemas, embeddings, and tool use on models that support them. It tracks output token usage and integrates seamlessly with llm's attachment system for vision tasks. All models are prefixed with 'github/' to distinguish them from other llm providers.

Use it for:

• Run GPT-4o or o3 reasoning models from the command line without a paid OpenAI subscription
• Process images with Llama vision models or Phi multimodal models using llm attachments
• Integrate free AI inference into GitHub Actions workflows with automatic GITHUB_TOKEN authentication
• Prototype with multiple model families (Mistral, Cohere, DeepSeek, Phi) to compare outputs
• Build CLI tools or scripts that call structured-output models like gpt-4.1 or gpt-5 with schemas

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

A plugin for the llm command-line tool that provides access to GitHub Models, a free service offering many AI language models via the Azure AI Inference SDK.

Yes. The package offers free access to a large roster of modern AI models through a simple CLI interface, requires minimal setup (just a GitHub token), has low install friction, is actively maintained, carries no security vulnerabilities, and uses a permissive license. Install it if you want to experiment with or integrate GitHub Models into command-line workflows or GitHub Actions without cost.

Install

llm-github-models on PyPI

pip install llm-github-models

uv add llm-github-models

poetry add llm-github-models

Installing llm-github-models

Before you install

Low install friction with a pure Python wheel. The package is actively maintained with recent commits and has 3 runtime dependencies (aiohttp, llm, azure-ai-inference), all standard libraries in the Python ecosystem.

License in practice

Licensed under Apache-2.0 (permissive), which allows commercial use, modification, and distribution with minimal restrictions—suitable for most projects.

Quickstart

pip install llm-github-models
llm keys set github
llm prompt 'top facts about cheese' -m github/gpt-4.1-mini

Requires a GitHub personal access token (PAT) or GITHUB_TOKEN environment variable set; GitHub Models API access must be available on your GitHub account.

Verify before relying

• Exact number of supported models (description says '>30' but the table lists many more—clarify the current count)
• Whether all embedding models listed in the feature set are actually available in the current release
• Rate limits and quota behavior for free tier usage under typical workloads

Package facts

Evidence: llm_github_models-0.18.0-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading