At its annual GitHub Universe conference today, the company announced that it is expanding its Copilot AI coding assistant with new model choices from frontier AI providers. You'll now be able to choose between OpenAI's latest models, Anthropic's Claude 3.5 Sonnet, and Google's Gemini 1.5 Pro when using Copilot's features.
The new models will be rolled out in stages, starting with Copilot Chat. OpenAI's o1-preview and o1-mini are available immediately, while Anthropic's Claude 3.5 Sonnet will roll out over the coming week, and Google’s Gemini 1.5 Pro is expected to follow in the next few weeks. This enhanced flexibility will soon extend across various features of GitHub Copilot, including Copilot Workspace, multi-file editing, code review, security autofix, and command-line integration.
This marks a strategic change for GitHub. Since its launch, GitHub Copilot has been driven by a range of LLMs, starting with Codex—a fine-tuned version of OpenAI's GPT-3—to the more recent GPT-4o models. "It is clear the next phase of AI code generation will not only be defined by multi-model functionality, but by multi-model choice," says GitHub CEO Thomas Dohmke. This is a clear nod to an expanding ecosystem where flexibility and specialization are key.
Each AI model brings distinct capabilities to Copilot. Claude 3.5 Sonnet specializes in complex coding tasks across the entire software development lifecycle. Gemini 1.5 Pro offers a massive two-million-token context window and can process multiple types of input, including code, images, and audio. OpenAI's new o1-series models feature advanced reasoning capabilities for understanding code constraints and nuanced edge cases.
You'll maintain control over which model powers your coding assistance, all under a single subscription and login. GitHub plans to extend this multi-model approach across other Copilot features, including workspace tools, multi-file editing, code review, and security fixes.
Alongside model choice, GitHub also unveiled “GitHub Spark,” an AI-native tool that will let you build fully functional web applications using natural language. The user experience looks very intuitive and it features a creativity feedback loop where you can see live previews of your app as it's built, explore different options for each request, and automatically save versions of your work for easy comparison and iteration. And of course, you control which models you want to use.