The latest AI models from Phi, 4-mini-instruct and 4-multimodal-instruct, are now available in GitHub Models.
Phi-4-mini-instruct is a 3.8B parameter lightweight model designed for chat-completion prompts and strong reasoning, particularly in math and logic. Its efficiency makes it well-suited for memory- and compute-constrained environments.
Phi-4-multimodal-instruct is a 5.6B parameter multimodal model that excels at generating text outputs from various inputs including text, images, and audio. This model demonstrates strength in reasoning across multiple modalities.
GitHub Models makes it easy for every developer to build AI features and products on GitHub.
Try, compare, and implement these models in your code for free in the playground (Phi-4-mini-instruct and Phi-4-multimodal-instruct) or via the API.
To learn more about GitHub Models, check out the docs. You can also join our community discussions.
With the latest stable release of the extension (v1.5.35 or above), OpenAI o3-mini (Preview) and Google Gemini 2.0 Flash (Preview) are now available to all JetBrains users of GitHub Copilot Chat.
Click the Copilot Chat icon in the JetBrains IDE, and you will have a Copilot chat model picker to choose which model version to use for your chat conversations.
Following our opt-in preview last October, we’re excited to expand item limits for all projects — increasing from 1,200 to 50,000 items per project.
Since the last release, we’ve added support for project insights and mobile, addressed your top bug reports, and delivered key performance improvements.
We’re rolling out increased limits incrementally over the next week. If you see the Increased items preview pill in your project, you’re now in the preview.
With this release, we’re also making project insights fully accessible to all plans—removing paid gating entirely. All plans now have access to both current state and historical charts in public and private repositories, with no feature restrictions. Learn more about insights for projects.
For questions and feedback, join the discussion within the GitHub Community.