Changing the AI model for Copilot Chat

By default, Copilot Chat uses OpenAI's GPT 4o large language model. This is a highly proficient model that performs well for text generation tasks, such as summarization and knowledge-based chat. The model is also capable of reasoning, solving complex math problems 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.

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

Multiple model support in Copilot Chat is in public preview and is subject to change.
You can only use an alternative AI model in the immersive view of Copilot Chat. 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 through multi-model Copilot Chat:

GPT 4o: This is the default Copilot Chat model. It is a versatile, multimodal model that excels in both text and image processing and is designed to provide fast, reliable responses. It also has superior performance in non-English languages. Learn more about the model's capabilities and review the model card. GPT 4o is hosted on Azure.
Claude 3.5 Sonnet: This model excels at coding tasks across the entire software development lifecycle, from initial design to bug fixes, maintenance to optimizations. Learn more about the model's capabilities or read the model card. GitHub Copilot uses Claude 3.5 Sonnet hosted on Amazon Web Services.
Gemini 2.0 Flash: This model has strong coding, math, and reasoning capabilities that makes it well suited to assist with software development. For information about the capabilities of Gemini 2.0 Flash, see the Google for developers blog and the Google Cloud documentation. For details of Google's data handling policy, see Generative AI and data governance on the Google website.
o1: This model is focused on advanced reasoning and solving complex problems, in particular in math and science. It responds more slowly than the GPT 4o model. You can make 10 requests to this model per day. Learn more about the model's capabilities and review the model card. o1 is hosted on Azure.
o3-mini: This model is the next generation of reasoning models, following from o1 and o1-mini. The o3-mini model outperforms o1 on coding benchmarks with response times that are comparable to o1-mini, providing improved quality at nearly the same latency. It is best suited for code generation and small context operations. You can make 50 requests to this model every 12 hours. Learn more about the model's capabilities and review the model card. o3-mini is hosted on Azure.

For more information about these models, see:

OpenAI's GPT 4o, o1, and o3-mini models: Models in the OpenAI Platform documentation.
Anthropic's Claude 3.5 Sonnet model: Using Claude 3.5 Sonnet in Copilot Chat.
Google's Gemini 2.0 Flash model: Using Gemini 2.0 Flash in Copilot Chat.

Limitations of AI models for Copilot Chat

If you want to use the skills listed in the table above, or knowledge bases, on the GitHub website, only the GPT 4o, Claude 3.5 Sonnet, and Gemini 2.0 Flash models are supported.
Experimental pre-release versions of the models may not interact with all filters correctly, including the duplication detection filter.

Changing your AI model

These instructions are for Copilot on the GitHub website. For Visual Studio or VS Code, 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.

In the top right of any page on GitHub, click the down arrow beside the icon and click Immersive in the dropdown menu.
At the top of the immersive view, select the CURRENT-MODEL dropdown menu, then click the AI model of your choice.

Note

Multiple model support in Copilot Chat is in public preview and is subject to change.

AI models for Copilot Chat

The following models are currently available through multi-model Copilot Chat:

GPT 4o: This is the default Copilot Chat model. It is a versatile, multimodal model that excels in both text and image processing and is designed to provide fast, reliable responses. It also has superior performance in non-English languages. Learn more about the model's capabilities and review the model card. GPT 4o is hosted on Azure.
Claude 3.5 Sonnet: This model excels at coding tasks across the entire software development lifecycle, from initial design to bug fixes, maintenance to optimizations. Learn more about the model's capabilities or read the model card. GitHub Copilot uses Claude 3.5 Sonnet hosted on Amazon Web Services.
Gemini 2.0 Flash: This model has strong coding, math, and reasoning capabilities that makes it well suited to assist with software development. For information about the capabilities of Gemini 2.0 Flash, see the Google for developers blog and the Google Cloud documentation. For details of Google's data handling policy, see Generative AI and data governance on the Google website.
o1: This model is focused on advanced reasoning and solving complex problems, in particular in math and science. It responds more slowly than the GPT 4o model. You can make 10 requests to this model per day. Learn more about the model's capabilities and review the model card. o1 is hosted on Azure.
o3-mini: This model is the next generation of reasoning models, following from o1 and o1-mini. The o3-mini model outperforms o1 on coding benchmarks with response times that are comparable to o1-mini, providing improved quality at nearly the same latency. It is best suited for code generation and small context operations. You can make 50 requests to this model every 12 hours. Learn more about the model's capabilities and review the model card. o3-mini is hosted on Azure.

For more information about these models, see:

OpenAI's GPT 4o, o1, and o3-mini models: Models in the OpenAI Platform documentation.
Anthropic's Claude 3.5 Sonnet model: Using Claude 3.5 Sonnet in Copilot Chat.
Google's Gemini 2.0 Flash model: Using Gemini 2.0 Flash in Copilot Chat.

Changing your AI model

These instructions are for VS Code. For Visual Studio or for Copilot on the GitHub website, 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.
Experimental pre-release versions of the models may not interact with all filters correctly, including the duplication detection filter.

To open the chat view, click the chat icon in the activity bar or press Control+Command+i (Mac) / Ctrl+Alt+i (Windows/Linux).
In the bottom right of the chat view, select the CURRENT-MODEL dropdown menu, then click the AI model of your choice.

Note

Multiple model support in Copilot Chat is in public preview and is subject to change.

AI models for Copilot Chat

The following models are currently available through multi-model Copilot Chat:

GPT 4o: This is the default Copilot Chat model. It is a versatile, multimodal model that excels in both text and image processing and is designed to provide fast, reliable responses. It also has superior performance in non-English languages. Learn more about the model's capabilities and review the model card. GPT 4o is hosted on Azure.
Claude 3.5 Sonnet: This model excels at coding tasks across the entire software development lifecycle, from initial design to bug fixes, maintenance to optimizations. Learn more about the model's capabilities or read the model card. GitHub Copilot uses Claude 3.5 Sonnet hosted on Amazon Web Services.
o1: This model is focused on advanced reasoning and solving complex problems, in particular in math and science. It responds more slowly than the GPT 4o model. You can make 10 requests to this model per day. Learn more about the model's capabilities and review the model card. o1 is hosted on Azure.
o1-mini: This is the faster version of the o1 model, balancing the use of complex reasoning with the need for faster responses. It is best suited for code generation and small context operations. You can make 50 requests to this model per day. Learn more about the model's capabilities and review the model card. o1-mini is hosted on Azure.

For more information about the o1 models, see Models in the OpenAI Platform documentation.

For more information about the Claude 3.5 Sonnet model from Anthropic, see Using Claude 3.5 Sonnet in Copilot Chat.