# Changing the AI model for GitHub Copilot Chat
> Learn how to switch between models for Copilot Chat.
- 网址：https://funcoding.ai/agents/github-copilot/how-tos/copilot-in-your-ide/chat-with-copilot/change-the-chat-model/
- 来源：GitHub Copilot 官方文档原文（英文），CC-BY-4.0 许可，同步于 2026-10-11
- 官方原文：https://docs.github.com/en/copilot/how-tos/copilot-in-your-ide/chat-with-copilot/change-the-chat-model
---
Choose from a selection of 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.
To view the available models per client, see [AUTOTITLE](https://docs.github.com/copilot/reference/ai-models/supported-models#supported-ai-models-per-client).
The models available to you depend on your Copilot plan and where you're using Copilot, such as GitHub.com or an IDE. Different models consume AI credits at different rates based on their token pricing. For details, see [AUTOTITLE](https://docs.github.com/copilot/reference/copilot-billing/models-and-pricing).
Copilot allows you to change the model during a chat and have the alternative model used to generate responses to your prompts.
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 [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/administer-copilot/manage-for-organization/manage-policies/) or [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/administer-copilot/manage-for-enterprise/manage-enterprise-policies/).
Changing the model used by Copilot Chat does not affect the model used for Copilot inline suggestions. See [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/copilot-in-your-ide/copilot-for-common-tasks/change-the-completion-model/).
**VS Code**
## Changing the AI model
These instructions are for Visual Studio Code. For instructions on different clients, click the appropriate tab at the top of this page.
* 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 setting to block suggestions matching public code (see [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/manage-your-account/manage-policies/#enabling-or-disabling-suggestions-matching-public-code)).
1. Open Copilot Chat by clicking the chat icon in the title bar of Visual Studio Code.
1. At the bottom of the chat view, select the **CURRENT-MODEL** chevron-down dropdown menu, then click the AI model of your choice.
If you select **Auto**, Copilot auto model selection will select the best model based on availability and to help reduce rate limiting. See [AUTOTITLE](https://funcoding.ai/agents/github-copilot/concepts/models/auto-model-selection/).
## Adding more models
You can expand the model options that are available to power Copilot Chat. You can add models from:
* **A model provider**—such as Anthropic, Gemini, OpenAI, and others.
* **The AI Toolkit for Visual Studio Code**.
Using the AI Toolkit for VS Code is in public preview and subject to change.
### Prerequisites
* Depending on the provider or model you choose, you may need to supply an API key, or model ID, from the provider, or a GitHub personal access token (PAT).
* To add models from the AI Toolkit for Visual Studio Code, you must install the AI Toolkit extension.
* If you are on a Copilot Business or Copilot Enterprise plan and want to use third-party models in a supported IDE, the **Bring Your Own Language Model Key in Select IDEs** policy must be enabled. For more information, see [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/administer-copilot/manage-for-organization/manage-policies/) or [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/administer-copilot/manage-for-enterprise/manage-enterprise-policies/).
### Adding models
1. In the Copilot chat view, click the **CURRENT-MODEL** chevron-down dropdown menu.
1. Click **Manage Models**.
A list of providers is displayed.
If you have installed the AI Toolkit, then additional providers, added via the AI Toolkit, are also listed.
1. Click the provider whose model(s) you want to add.
1. Depending on which provider you selected, you may be prompted to enter a GitHub PAT, an API key for the provider, or a model ID for a specific model.
Enter the required information, then press Enter.
A list of available models is displayed.
1. Select the model(s) you want to add, then click **OK**.
The models you selected are now available in the model picker in the chat view.
If you added a model from a provider via the AI Toolkit then the first time you use the model, you will be prompted to download it. You may also be prompted to authenticate with the provider.
If you're already using chat with auto model selection, you'll need to start a new chat session to switch models. To start a new session, in the top right of the chat view, click new chat new chat.
**Visual Studio**
## Changing the AI model
These instructions are for Visual Studio. For instructions on different clients, click the appropriate tab at the top of this page.
To use multi-model Copilot Chat, you must use Visual Studio 2022 version 17.12 or later. See the [Visual Studio downloads page](https://visualstudio.microsoft.com/downloads/).
* 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 setting to block suggestions matching public code (see [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/manage-your-account/manage-policies/#enabling-or-disabling-suggestions-matching-public-code)).
1. In the Visual Studio menu bar, click **View**, then click **GitHub Copilot Chat**.
1. In the bottom right of the chat view, select the **CURRENT-MODEL** triangle-down dropdown menu, then click the AI model of your choice.
If you select **Auto**, Copilot auto model selection will select the best model based on availability and to help reduce rate limiting. See [AUTOTITLE](https://funcoding.ai/agents/github-copilot/concepts/models/auto-model-selection/).
**JetBrains IDEs**
## Changing the AI model
These instructions are for the JetBrains IDEs. For instructions on different clients, click the appropriate tab at the top of this page.
* 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 setting to block suggestions matching public code (see [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/manage-your-account/manage-policies/#enabling-or-disabling-suggestions-matching-public-code)).
For reasoning models that support configurable thinking effort, you can control how much reasoning the model applies to each request.
1. Click the **copilot** icon in the status bar.
1. In the popup menu, click **Open GitHub Copilot Chat**.
1. In the bottom right of the chat view, select an AI model of your choice from the **CURRENT-MODEL** chevron-down dropdown menu.
1. Optionally, hover over a reasoning model that supports configurable thinking effort.
1. In the **Thinking Effort** submenu, select an effort level. Nonreasoning models do not display the **Thinking Effort** submenu.
If you select **Auto**, Copilot auto model selection will select the best model based on availability and to help reduce rate limiting. See [AUTOTITLE](https://funcoding.ai/agents/github-copilot/concepts/models/auto-model-selection/).
Model selection is also available when using Copilot through JetBrains AI Assistant. For more information, see [AUTOTITLE](https://funcoding.ai/agents/github-copilot/concepts/copilot-surfaces/copilot-in-ides/).
**Eclipse**
## Changing the AI model
These instructions are for the Eclipse IDE. For instructions on different clients, click the appropriate tab at the top of this page.
* 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 setting to block suggestions matching public code (see [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/manage-your-account/manage-policies/#enabling-or-disabling-suggestions-matching-public-code)).
1. Click the **copilot** icon in the status bar.
1. In the popup menu, click **Open Chat**.
1. In the bottom right of the chat panel, click the currently selected AI model, then select an alternative model from the popup menu.
If you select **Auto**, Copilot auto model selection will select the best model based on availability and to help reduce rate limiting. See [AUTOTITLE](https://funcoding.ai/agents/github-copilot/concepts/models/auto-model-selection/).
**Xcode**
## Changing the AI model
These instructions are for Xcode. For instructions on different clients, click the appropriate tab at the top of this page.
To use multi-model Copilot Chat, you must install the GitHub Copilot for Xcode extension. See [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/copilot-in-your-ide/set-up-copilot/install-copilot-extension/).
* 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 setting to block suggestions matching public code (see [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/manage-your-account/manage-policies/#enabling-or-disabling-suggestions-matching-public-code)).
1. To open the chat view, click **Editor** in the menu bar, then click **copilot Copilot** then **Open Chat**. Copilot Chat opens in a new window.
1. In the bottom right of the chat view, select the **CURRENT-MODEL** triangle-down dropdown menu, then click the AI model of your choice.
If you select **Auto**, Copilot auto model selection will select the best model based on availability and to help reduce rate limiting. See [AUTOTITLE](https://funcoding.ai/agents/github-copilot/concepts/models/auto-model-selection/).
## Further reading
* [AUTOTITLE](https://funcoding.ai/agents/github-copilot/how-tos/copilot-in-your-ide/copilot-for-common-tasks/change-the-completion-model/)
* [AUTOTITLE](https://docs.github.com/copilot/reference/ai-models/model-comparison)
**VS Code**
* [AI language models in VS Code](https://code.visualstudio.com/docs/copilot/language-models#_bring-your-own-language-model-key) in the Visual Studio Code documentation.