Apr 4, 2025

How to Use Custom API Keys with GitHub Copilot

• 2 min read

vscode extensions AI github workflow tutorial

Table of Contents

With the "March 2025 (v1.99.0)" Visual Studio Code release, I can now use my own custom API key and use any models associated with it in GitHub Copilot VSCode extension. GitHub Copilot Chat now supports API keys generated from major AI platforms/providers, namely, Anthropic, Azure, OpenRouter, OpenAI, Gemini and Ollama.

In this tutorial, I will demonstrate how you can use custom API keys from multiple AI providers and use any models associated with them in GitHub Copilot Chat VSCode extension.

1. Open GitHub Copilot Chat

Go to the GitHub Copilot Chat window by clicking the copilot icon besides the search bar in VSCode. You can also access github copilot chat by using the shortcut Ctrl + Alt + I (Windows) or Ctrl + Command + I (MacOS).

github copilot chat vscode window panel — GitHub Copilot Chat

2. Manage Models

Click on the model name dropdown (claude-3-5-sonnet-202041022 in the image below) and select "Manage Models...".

github copilot chat vscode window panel (manage models) — GitHub Copilot Chat Manage Models Feature

3. Choose Your AI Provider

Once you click on 'Manage Models...', a dialog box will appear, prompting you to select your preferred AI provider for the model. The manage models feature supports Anthropic, OpenAI, OpenRouter, Ollama, Azure and Gemini for now.

github copilot chat vscode dialog (manage models > select AI provider) — GitHub Copilot Chat Manage Models Feature (Selecting AI Provider)

4. Add Your API Key

After selecting the AI platform/provider, you will be asked to provide an API key (or a deployment URL if you select Azure).

github copilot chat vscode dialog (manage models > select AI provider > insert API key/deployment URL) — GitHub Copilot Chat Manage Models Feature (Adding API keys)

5. Select AI Models

Once you enter the API key, a dialog box listing available AI models will appear, and you can select models which you plan to use with GitHub Copilot.

github copilot chat vscode dialog (manage models > select AI provider > insert API key/deployment URL > select models to be used) — GitHub Copilot Chat Manage Models Feature (Selecting Models)

You can also add custom models of your own which are accessible with the API key you entered.

Using the AI Models

For instance, if I selected a total of five AI models across three AI providers, all of those five models will be listed in the model selection dropdown I showed earlier.

github copilot chat vscode panel (selecting AI model) — GitHub Copilot Chat (Selecting Model)

One thing that's missing in this Manage Models feature is the ability to show the AI platform/provider besides the model name. It will be really helpful to differentiate models based on providers, for example, OpenRouter and Anthropic both provide claude-3-5-sonnet model, so it will be helpful to know if I am using a claude model through OpenRouter or Anthropic directly.

I hope they add this in the future, considering the fact that the Manage Models feature in GitHub Copilot is still in preview.