Skip to main content

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.

Wer kann dieses Feature verwenden?

GitHub Copilot App ist für alle kostenpflichtigen Copilot Pläne verfügbar.
Sign up for Copilot

In diesem Artikel

Hinweis

Support to use your own provider (BYOK) in the GitHub Copilot App is in Öffentliche Vorschau and subject to change.

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

Hinweis

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 Verwenden Ihrer LLM-Anbieter-API-Schlüssel mit Copilot and Verwenden Ihrer LLM-Anbieter-API-Schlüssel mit Copilot.

Supported providers

GitHub Copilot App supports these model providers:

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

Prerequisites

Add a model provider

  1. Open the GitHub Copilot App.
  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 Arbeiten mit Agent-Sitzungen in der GitHub-Copilot-App.

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