GitHub Launches AI Model Playground for Developers

GitHub, the world’s leading AI-powered developer platform, today announced the launch of GitHub Models, enabling more than 100 million developers to become AI engineers and build with industry-leading AI models. 

From Llama 3.1, to GPT-4o and GPT-4o mini, to Phi 3 or Mistral Large 2, developers can access each model via a built-in playground that lets them test different prompts and model parameters, for free right in GitHub. 

In the new interactive model playground, students, hobbyists, startups, and more can explore the most popular private and open models from Meta, Mistral, Azure OpenAI Service, Microsoft, and others with just a few clicks and keystrokes. Developers can experiment, compare, test, and deploy AI applications right where they manage their source code. 

In alignment with GitHub and Microsoft’s continued commitment to privacy and security, no prompts or outputs in GitHub Models will be shared with model providers, nor used to train or improve the models. 

“Today, we democratise AI for the many. With GitHub Models, more than 100 million developers can now access and experiment with new AI models where their workflow is—directly on GitHub,” said GitHub CEO, Thomas Dohmke.“This means that every developer in India on GitHub can become an AI engineer, generating a new wave of AI applications that stand to accelerate India’s competitive advantage in the age of AI.

“In the years ahead, we will continue to democratise access to AI technologies to generate a groundswell of one billion developers. By doing so, we will enable 10% of the world’s population to build and advance breakthroughs that will accelerate human progress for us all,” added Dohmke. 

GitHub has also created a glide path to bring the models to a developer’s environment in Codespaces and VS Code. Once a developer is ready to go to production, Azure AI offers built-in responsible AI, enterprise-grade security & data privacy, and global availability, with provisioned throughput and availability in over 25 Azure regions for some models.

Test and compare different models

Every piece of software is unique. And likewise, every model is unique in its capabilities, performance, and cost. Mistral offers low latency, while GPT-4o is excellent at building multimodal applications that might demand audio, vision, and text in real time. Some advanced scenarios might require the integration of different modes, such as an embeddings model for Retrieval Augmented Generation (RAG).

With the suite of models, developers will have all the options they need to stay in the flow, experiment more, and learn faster than ever before. And this is just the first wave. In the months ahead, as the general availability of GitHub Models approaches, GitHub will continue to add more language, vision, and other models to  the platform. 

Spin up Codespaces to bring ideas to life

With the power of Codespaces, GitHub has created a zero-friction path for users to experiment with the model inference code before dropping it into the project. With sample code for a variety of languages and frameworks of all types ready to go, developers can try out various scenarios without ever hitting “works on my machine” problems. 

Then, once a developer is ready, it's a breeze to get things running in the project. They can use the knowledge gained from the playground and Codespaces to set up a prototype or proof-of-concept within their own applications. Run prompt evals in GitHub Actions with a series of JSON files that users just pipe in the GitHub Models command within the GitHub CLI. Or they can leverage GitHub Models to build a GitHub Copilot Extension, extending GitHub’s platform ecosystem for every stage of software development. And finally, developers go to production with Azure AI by replacing their GitHub personal access token with an Azure subscription and credential.

“As an AI startup founder and open source maintainer, GitHub Models enables my team to access and experiment with various LLMs in one place. This streamlines our development and lowers the entry barrier for building AI apps,” said Anand Chowdhary, Co-founder of FirstQuadrant.

The creator network for the age of AI

From the creation of AI through open source collaboration, to the creation of software with the power of AI, to enabling the rise of the AI engineer with GitHub Models–GitHub is the creator network for the age of AI. 

The path to artificial general intelligence (AGI) will not be built without the source code and collaboration of the interconnected community on GitHub. 

GitHub Copilot is foundationally changing the speed of software production, already writing nearly 50% of code in files where it’s enabled. With GitHub Copilot Workspace, GitHub envisions a world where millions of novice, hobbyist, and professional developers alike can code with entirely human language.

And now with GitHub Models, more than 100 million developers can access and experiment with new AI models where they already manage their source code, issues, pull requests, workflows, and repositories—directly on GitHub. 

Today, GitHub begins the limited public beta for GitHub Models. Developers can sign up now here.