GitHub Copilot expands AI model support

GitHub has expanded Copilot's model support to new Anthropic, Google, and OpenAI models and introduced GitHub Spark, an AI-powered tool for building natural language web apps.

GitHub is bringing multi-model support to GitHub Copilot, its AI-powered coding assistant, allowing developers to choose from multiple generative AI models including Google Gemini 1.5 Pro , OpenAI GPT-4o , OpenAI o1 preview , OpenAI o1-mini and Anthropic Claude 3.5 sonnet . Support for multiple models is only available in GitHub Copilot Chat initially, but will be enabled elsewhere in Copilot soon, GitHub said.

This model list was unveiled on October 29. In addition to announcing support for multiple models, GitHub also unveiled GitHub Spark, an AI-native tool for building fully functional web applications in natural language, on the same day.

Developers using GitHub Copilot in github.com or Visual Studio Code can switch between models during a conversation with Copilot Chat to choose the right model for the right use case. Or, they can continue to let GitHub Copilot use its powerful standard, GitHub said. With its multi-model approach, GitHub is enabling developers to use a range of leading models in workflows they are familiar with. Anthropic Claude 3.5 Sonnet is available through GitHub Copilot starting today, while Google Gemini 1.5 Pro will be available in the coming weeks. Access to the new OpenAI models is available now. GitHub will continue to enable developer choice in partnership with leading model providers and will offer multi-model choice across more of Copilot’s surfaces and features soon, the company said.

GitHub Spark, meanwhile, makes it easy for developers of all skill levels to bring ideas to life by using natural language to build microapps called “sparks,” GitHub said. Sparks are fully functional microapps that can integrate AI capabilities into external data sources without having to manage cloud resources. Using a feedback loop for creativity, users start with a first call with both OpenAI and Anthropic models, see live previews of their app as it’s built, and save versions of each iteration so they can compare builds. A Spark can then be run on desktop, tablet, or mobile. GitHub plans to iterate on Spark to make the tool as intuitive as possible for consumers and developers of all skill levels, the company said.

GitHub also said that they have made significant updates to GitHub Copilot for use in Visual Studio Code editor , GitHub Copilot Workspace , GitHub models to build generative AI applications and GitHub Copilot Autofix code scan . Users of GitHub Copilot Chat in VS Code can now make changes to multiple files at once. With this new editing mode, available November 1, GitHub Copilot allows users to make complex changes to a variety of files within a project based on natural language prompts. GitHub Copilot Autofix now includes security campaigns to help developers and security teams fix vulnerabilities “at scale,” GitHub says, with the ability to triage as many as 1,000 alerts at a time.

Finally, GitHub announced that GitHub Copilot Extensions will be generally available in early 2025. GitHub Copilot Extensions, now in preview, will allow developers to ask questions about any Copilot-integrated developer tool or service, such as Atlassian Rovo, Docker, Sentry, and Stack Overflow. Additionally, the company said that code completion features in GitHub Copilot are now available in public preview. Apple's Xcode IDE .