Skip to content
| Marketplace
Sign in
Visual Studio Code>Machine Learning>ai& for GitHub CopilotNew to Visual Studio Code? Get it now.
ai& for GitHub Copilot

ai& for GitHub Copilot

ai&

|
25 installs
| (1) | Free
Use hosted ai& models in GitHub Copilot Chat with your ai& API key.
Installation
Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.
Copied to clipboard
More Info

ai&

ai& for GitHub Copilot

Use ai& models directly from the GitHub Copilot Chat model picker in Visual Studio Code.

Visual Studio Marketplace version CI status MIT license

This extension is a native VS Code LanguageModelChatProvider. It validates a user-supplied ai& API key, discovers the models available to that key, and streams OpenAI-compatible chat completions directly from https://api.aiand.com/v1 into Copilot Chat.

Highlights

  • Direct ai& integration without a local proxy
  • API keys managed by VS Code Secret Storage or provider configuration
  • Multiple isolated ai& API-key entries in Manage Language Models
  • Current input, cached-input, and output pricing in the model picker
  • Live organization credit balance with locally tracked token activity and request history
  • Live /models discovery with context and output limits from ai& metadata
  • Streaming text, reasoning_content, token usage, and function-tool calls
  • ai& reasoning effort controls only on models that advertise support
  • Image input for models that advertise image capability
  • Agent mode function-tool calls

Quick start

  1. Install the extension from the Visual Studio Marketplace. You need VS Code 1.125 or newer and GitHub Copilot Chat.
  2. Create an API key in the ai& dashboard.
  3. Open Copilot Chat, select Manage Models, add a ai& provider entry, and enter the key.
  4. Choose any model returned by your ai& account.

To use more than one account or key, add another ai& entry. Each entry keeps its own credential and model list. The legacy ai&: Configure API Key command remains available for command-driven workflows.

For models that support configurable reasoning, choose None, Low, Medium, or High from the reasoning control in Copilot Chat. A per-request selection overrides aiandCopilot.reasoningEffort.

Documentation

  • Setup, settings, and troubleshooting
  • Models and pricing
  • API key and security model
  • Development and releases

Credits

Officially maintained by ai&. Originally created by Griko Nibras, who handed the project over to ai&. Everyone else who has helped is listed in THANKS.md.

Not affiliated with GitHub or Microsoft. ai& usage limits and charges apply. Licensed under MIT.

  • Contact us
  • Jobs
  • Privacy
  • Manage cookies
  • Terms of use
  • Trademarks
  • Your Privacy Choices
  • Consumer Health Privacy
© 2026 Microsoft