> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aixy-gateway.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Cursor

> Use Aixy as Cursor's OpenAI-compatible API endpoint.

Cursor can send chat-model requests to Aixy through its OpenAI provider and a custom base URL.

## Configure the provider

1. Open **Cursor Settings → Models**.
2. Add your project-scoped Aixy API key in the **OpenAI API key** field.
3. Enable **Override OpenAI Base URL** and set it to `https://api.aixy-gateway.com/v1`.
4. Enable the provider-qualified model you want to use, for example `openai/gpt-4.1-mini`.
5. Start a new chat and choose that model from Cursor's model picker.

For a self-hosted instance, replace the hosted URL with its public gateway URL. Cursor uses the
OpenAI-compatible Chat Completions API, so the key remains scoped to the Aixy project.

This setup applies to chat models configured with your key. Verify the selected model in a new
chat and inspect the request in [Activity](/observe/activity). Cursor routes requests through its
own backend for prompt building, so include that client path in your organization's data-handling
review. Tab completion uses Cursor's built-in models.

See [Cursor's API key guide](https://cursor.com/help/models-and-usage/api-keys) for its
current BYOK limitations.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.