GitHub Copilot now supports Gemini, Claude, and GPT models
Users will be able to toggle between AI models during conversations
The announcements were made during the GitHub Universe 2024 event
GitHub Copilot is a paid service for developers starting at $10 (roughly Rs. 840) a month
Photo Credit: GitHub
GitHub announced a major update to Copilot, the artificial intelligence (AI) coding assistant service, on Tuesday. The announcement was made at the GitHub Universe 2024 event, which is being held in San Francisco. The update introduces multi-model support for Copilot, allowing developers to pick between various AI models by Anthropic, Google, and OpenAI. The company said the flexibility in choice will empower developers to freely use their preferred models for various projects. Alongside, a new AI tool dubbed GitHub Spark was also introduced.
GitHub Copilot Gets Upgraded
Launched in 2021, GitHub Copilot was the first AI-powered platform with the Copilot branding. The AI assistant was introduced just months after Microsoft invested in OpenAI, forming a partnership with the AI firm. GitHub Copilot allows developers to use AI models in writing codes, assisting with finding bugs, running debug and security remediation, and more.
At the event, the Microsoft-owned coding and file hosting platform introduced the GitHub Copilot will now offer developers a wider choice in the AI models they want to use. Those using the AI assistant in Visual Studio Code and on the official website will now get to pick Anthropic's Claude 3.5 Sonnet, Google's Gemini 1.5 Pro, and OpenAI's GPT-4o, o1-preview, and o1-mini models. While Claude 3.5 Sonnet is currently available, Gemini 1.5 Pro will be added in the coming weeks.
Developers will be able to switch between models during a conversation with Copilot Chat to test and check which is a better fit. Users can also set a preferred AI model and start their project on it from the get-go.
GitHub Spark Introduced
GitHub Spark is an AI-native tool that can be used to by all developers, regardless of their skill range, to generate micro apps called a “spark”. These micro apps are fully functional and can integrate AI capabilities and external data sources into larger apps, reducing the reliance on cloud servers.
Generating a micro app is also easy as developers can simply type a natural language prompt detailing their requirements and see a preview of the app. Developers will have the freedom to either directly work on the app code to make desired changes or add follow-up prompts to make the AI do the work. The tool supports both Anthropic and OpenAI models.
Once a spark is created, it can automatically be run on desktops, tablets, or smartphones. Users can also share the spark with others — either with customised access control or to give them full control to remix the spark or build on top of it.
ChatGPT’s Deep Research Feature Can Now Connect With GitHub Repositories12 May 2025
Search
