models

Mistral Small 3.1 (25.03) is now available in GitHub Models.

Mistral Small 3.1 (25.03) is a versatile AI model designed to assist with programming, mathematical reasoning, dialogue, and in-depth document comprehension. Equipped with multimodal capabilities, it processes both text and visual inputs, making it suitable for chat-based interactions and instruction-following tasks.

Try, compare, and implement this model in your code for free in the playground or through the GitHub API. Compare it to other models using side-by-side comparisons in GitHub Models.

To learn more about GitHub Models, check out the docs. You can also join our Community discussions.

You can now use Quick Action Tasks in the GitHub Models playground . This is a new feature that streamlines your experimentation process by helping you choose faster or more cost-effective models, and even includes sources in your responses. This allows you to find the model that best fits your goals, whether you prioritize speed, cost-efficiency, or clarity of information.

Try it out today and take your experimentation to the next level!

GitHub Models makes it easy for every developer to build AI features and products on GitHub.

To learn more about GitHub Models, check out the docs. You can also join our community discussions.

DeepSeek-V3 is now available in GitHub Models.

DeepSeek-V3 is a 671B parameter Mixture-of-Experts model that excels in mathematics and coding, making it suitable for tasks like solving advanced math problems and generating complex code.

GitHub Models makes it easy for every developer to build AI features and products on GitHub.

Try, compare, and implement this model in your code for free in the playground or via the GitHub API. Compare it to other models using side-by-side comparisons in GitHub Models.

To learn more about GitHub Models, check out the docs. You can also join our community discussions.

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.

You can now iterate on your prompt in any user repositories without breaking your flow. With just one click, jump from a prompt in your GitHub-hosted code to the GitHub Models prompt editor:

This feature detects files with “prompt” in the content and uses 10 lines above and below the selected line as context. Once in the prompt editor, you can experiment with models, fine-tune your prompts, and customize parameters.

GitHub Models is a catalog and prompt editor of AI models to help you build AI features and products. You can start using models for free with just your GitHub PAT. This is the first of more features to come that will help with seamless integration between your existing workflow and the GitHub Models prompt editor!

Learn more about GitHub Models or join the discussion in our community forums.

The latest trending AI model DeepSeek-R1 is now available in GitHub Models.

DeepSeek-R1 is a 671B parameter AI model designed to enhance deep learning, natural language processing, and computer vision capabilities. It offers a wide range of possibilities, provides quick insights, and allows users to explore the potential of AI in various applications.

GitHub Models makes it easy for every developer to build AI features and products on GitHub.

Try, compare, and implement this model in your code for free in the playground or via the API. Compare it to other models using side-by-side comparisons in GitHub Models.

To learn more about GitHub Models, check out the docs. You can also join our community discussions.

You can now access a new prompt editor within GitHub Models, purpose-built to help you iterate, refine, and perfect your prompts. This powerful tool is designed to provide a focused and intuitive experience for crafting and testing your inputs, enabling you to optimize prompts for maximum performance and relevance in your projects. Whether you’re fine-tuning for precision or experimenting with different approaches, this editor empowers you to unlock the full potential of the models with ease and efficiency.

This addition empowers you to:
– Quickly test and refine prompts without the complexity of multi-turn interactions.
– Utilize a dedicated space for single-turn message scenarios to ensure consistent results.

Start experimenting with the new prompt editor today!

Learn more about GitHub Models or join the conversation in our community discussions.

GitHub Models makes it easy for every developer to build AI features and products directly on GitHub. Try and compare models for free in the playground, or integrate all 40+ models into your app with just one API key.

In order to improve navigation thorugh our growing catalog of models, you can now sort models by:

• Alphabetical
• Recently added
• Output token limit (maximum text generated by the model)
• Input token limit (maximum text length model can process)

Learn more about GitHub Models or share feedback in our community discussions.

The latest AI model from Phi, Phi-4, is now available in GitHub Models.

Phi-4 is a 14B parameter state-of-the-art small language model (SLM) that excels at complex reasoning and conventional language processing.

GitHub Models makes it easy for every developer to build AI features and products on GitHub.

Easily try, compare, and implement this model in your code for free in the playground or via the API. Compare it to a previous Phi model using the side-by-side feature in GitHub Models.

To learn more about GitHub Models, check out product documentation on GitHub Models. You can also join our community discussions.

The latest AI model from Mistral, Codestral 25.01, is now available in GitHub Models.

Codestral 25.01 is explicitly designed for code generation tasks. It helps developers write and interact with code through a shared instruction and completion API endpoint. As it masters code and can also converse in a variety of languages, it can be used to design advanced AI applications for software developers.

GitHub Models makes it easy for every developer to build AI features and products on GitHub.

Easily try, compare, and implement this model in your code for free in the playground or via the API. Compare it to other code generation models using the side-by-side feature in GitHub Models.

To learn more about GitHub Models, check out the docs. You can also join our community discussions.

You can now specify a custom JSON schema as a response format, alongside the existing text and recently released general JSON option. When JSON schema is selected, an input box will allow you to define your desired schema format directly in the playground.

This enhancement provides more control if you’re working with models that require structured responses, helping to mitigate issues like models outputting unnecessary tokens. You can either specify a single object or an array of objects. Additionally, you can save this JSON schema as a preset so that you can use it again later.

JSON Schema structured outputs are currently only supported for the GPT 4o model, and specifically for the api-version: “2024-08-01-preview”.

GitHub Models is a catalog and playground of AI models to help you build AI features and products. You can start using models for free with just your GitHub PAT.

Learn more about GitHub Models or join the conversation in our community discussions.

GitHub Models makes it easy for every developer on GitHub to build AI features and products, with access to top AI models via a playground, API, and more.

Today, we’ve added access to OpenAI’s brand new o1 model. The new o1 model replaces o1-preview, and offers even better performance in complex tasks. You can learn more about this launch and its availability on both GitHub Models and Copilot in our blog post.

Start working with o1 directly in our GitHub Models playground. You can even compare it side-by-side with GPT-4o to evaluate how they work differently.

If you’re ready to jump in and integrate o1 into your code, check out our API.

Learn more about GitHub Models or join the conversation in our community discussions to share your feedback!