GitHub Models launches, allowing developers to find and test AI models for free

The service is expected to bring the power of the leading large and small language models currently on the market directly to GitHub's more than 100 million users.

At the initial deployment stage, GitHub Models will provide access to today's popular models, including OpenAI's GPT-4o and mini GPT-4o, Microsoft's Phi 3, Meta's Llama 3.1, and Mistral Large 2. In the coming months, GitHub will add more language models at richer levels and scales.

'Now with GitHub Models, over 100 million developers can access and test new AI models where they already manage their source code, issues, pull requests, workflows, and repositories - live on GitHub'.

Through GitHub Models, developers can access these language models through an integrated 'playground' where they can inspect and experiment with different model statements and parameters. From GitHub Models, developers can move their projects to Codespaces and VS Code for further development. When they're ready to operate with Azure AI, they simply replace their GitHub personal access token with their Azure subscription and credentials.

GitHub commits that no data from GitHub Models will be shared with model providers, nor will that data be used to train or improve any AI models.

You can sign up for the limited public beta of GitHub Models HERE.

David Pac

Update 02 August 2024