Cursor Custom Configuration

This page explains how to connect Cursor to this service through a custom OpenAI-compatible configuration.

Different Cursor versions use slightly different labels, but the core idea is the same: point Cursor's OpenAI API key and Base URL to your own gateway.

1. Open model settings

Open Cursor Settings, then go to the Models section.

If your version supports a custom OpenAI route, you will usually see fields like:

• OpenAI API Key
• OpenAI Base URL
• Custom Base URL
• Override OpenAI Base URL

2. Enter connection details

Use this service's values:

• Base URL: https://aiapi.aisonnet.org/v1
• API key: your codex_... key
• Model ID: use whatever is returned by GET /v1/models; for a quick connectivity test, try gpt-5.4 first

3. Verify

Save the settings, click Verify, or start a new chat.

If Cursor can start a session normally, the custom configuration is working.

Notes

• The Base URL should be the OpenAI-compatible root path: https://aiapi.aisonnet.org/v1
• Do not enter the full /v1/chat/completions or /v1/responses endpoint
• If your Cursor version only accepts the official OpenAI API key but does not expose a custom Base URL, it cannot be pointed to this gateway directly
• Cursor API key docs: https://docs.cursor.com/advanced/api-keys
• Cursor's official docs note that custom API keys mainly apply to standard chat models; some built-in Cursor features may still use Cursor-managed model routes