참고
Support to use your own model provider in the GitHub Copilot 앱 is in 공개 미리 보기 and subject to change.
You can configure the GitHub Copilot 앱 to use your own LLM provider, also called BYOK (Bring Your Own Key), instead of GitHub-hosted models. You can set up your model provider when you first open the app or later in app settings.
You must sign in with a GitHub account to use the app, but you do not need a Copilot plan if you use your own model provider. If you do have a Copilot plan, you can use both your own model provider and GitHub-hosted models in the same app.
참고
This article is for users who want to configure their own LLM provider settings on their local machine. To set up custom models for users in an organization or enterprise, see Copilot와 함께 LLM 공급자 API 키 사용 and Copilot와 함께 LLM 공급자 API 키 사용.
Supported providers
GitHub Copilot 앱 supports these model providers:
- OpenAI
- Azure OpenAI
- Microsoft Foundry
- Anthropic
- Ollama
- Foundry Local
- LM Studio
- Any OpenAI-compatible HTTP endpoint
Prerequisites
- The GitHub Copilot 앱 is installed. For setup steps, see GitHub Copilot 앱 시작.
- You have any required credentials, such as API key, for your model provider.
Set up a model provider
If you are setting up the app for the first time and do not have a Copilot plan, you can choose to set up your own model provider during onboarding.
To add or update a model provider later:
- Open the GitHub Copilot 앱.
- Open app settings, then click Model providers.
- Click Add provider.
- Select your provider.
- Enter the provider details. This varies by provider but may include the display name, base URL, and API key.
- 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 GitHub Copilot 앱에서 에이전트 세션 사용하기.
Provider credentials are stored in the system credential store and are never displayed in the UI.
