Changing the AI model for Copilot Chat

Learn how to change the default LLM for Copilot Chat to a different model.

In this article

By default, Copilot Chat uses GPT-4.1 to provide fast, capable responses for a wide range of tasks, such as summarization, knowledge-based questions, reasoning, math, and coding.

However, you are not limited to using this model. You can choose from a selection of other models, each with its own particular strengths. You may have a favorite model that you like to use, or you might prefer to use a particular model for inquiring about a specific subject.

Note

Different models have different premium request multipliers, which can affect how much of your monthly usage allowance is consumed. For details, see Understanding and managing requests in Copilot.

Copilot allows you to change the model during a chat and have the alternative model used to generate responses to your prompts.

Changing the model that's used by Copilot Chat does not affect the model that's used for Copilot code completion. See Changing the AI model for Copilot code completion.

Note

  • Support for GPT-4.5, Claude Opus 4, and o3 are only available on Copilot Pro+ and Copilot Enterprise.
  • You can only use an alternative AI model in the immersive view of Copilot Chat on GitHub.com. This is the full-page version of Copilot Chat that's displayed at https://github.com/copilot. The Copilot Chat panel always uses the default model.

AI models for Copilot Chat

The following models are currently available in the immersive mode of Copilot Chat:

  • GPT-4o
  • GPT-4.1
  • GPT-4.5 (preview)
  • Claude Sonnet 3.5
  • Claude Sonnet 3.7
  • Claude Sonnet 3.7 Thinking
  • Claude Sonnet 4 (preview)
  • Claude Opus 4 (preview)
  • Gemini 2.0 Flash
  • Gemini 2.5 Pro (preview)
  • o1 (preview)
  • o3 (preview)
  • o3-mini
  • o4-mini (preview)

For more information about these models, see Choosing the right AI model for your task.

Limitations of AI models for Copilot Chat

Experimental pre-release versions of the models may not interact with all filters correctly, including the setting to block suggestions matching public code (see Managing Copilot policies as an individual subscriber).

Changing the AI model

These instructions are for Copilot on the GitHub website. For instructions on different clients, click the appropriate tab at the top of this page.

If you access Copilot Chat through a Copilot Business or Copilot Enterprise subscription, your organization or enterprise must grant members the ability to switch to a different model. See Managing policies for Copilot in your organization or Managing policies and features for Copilot in your enterprise.

Note

If you use Copilot Extensions, they may override the model you select.

  1. In the top right of any page on GitHub, click the icon.

    Screenshot of the 'Copilot' button, highlighted with a dark orange outline.

  2. At the bottom of the immersive view, select the CURRENT-MODEL dropdown menu, then click the AI model of your choice.

  3. Optionally, after submitting a prompt, you can regenerate the same prompt using a different model by clicking the retry icon () below the response. The new response will use your selected model and maintain the full context of the conversation.

Further reading