Using your own LLM models in the GitHub Copilot app

Connect a model from an external provider of your choice by supplying your own API key, then use the model in agent sessions.

谁可以使用此功能？

GitHub Copilot 应用 适用于所有付费 Copilot 计划。
Sign up for Copilot

在本文中

注意

Support to use your own provider (BYOK) in the GitHub Copilot 应用 is in 公开预览 and subject to change.

You can configure the GitHub Copilot 应用 to use your own LLM provider, also called BYOK (Bring Your Own Key), instead of GitHub-hosted models.

注意

This article is for users who want to configure their own LLM provider API key on their local machine. To set up custom models for users in an organization or enterprise, see 将 LLM 提供程序 API 密钥与 Copilot 配合使用 and 将 LLM 提供程序 API 密钥与 Copilot 配合使用.

Supported providers

GitHub Copilot 应用 supports these model providers:

  • OpenAI
  • Azure OpenAI
  • Microsoft Foundry
  • Anthropic
  • Ollama
  • Foundry Local
  • LM Studio
  • Any OpenAI-compatible HTTP endpoint

Prerequisites

  • The GitHub Copilot 应用 is installed. For setup steps, see GitHub Copilot 应用入门.
  • You have an API key for your model provider.

Add a model provider

  1. Open the GitHub Copilot 应用.
  2. Open app settings, then click Model providers.
  3. Click Add provider.
  4. Select your provider.
  5. Enter the provider details. This varies by provider but may include the display name, base URL, and API key.
  6. Click Add provider to save the provider.

After you add a provider, its models appear in the model picker alongside GitHub-hosted models. You can select the model and use it in a session. For more information, see 在 GitHub Copilot 应用中使用代理会话.

Keys are stored in the system credential store and are never displayed in the UI.