Skip to main content
Cursor is an AI code editor. This guide shows how to configure AIHubMix in Cursor so Cursor can call AIHubMix models through an OpenAI-compatible endpoint. Download: Cursor official download

​
Prerequisites

​
Configure AIHubMix

​
1. Open Models settings

Click the settings button in the upper-right corner of Cursor, then open Models. Open Cursor Models settings

​
2. Enter the API Key and Base URL

Enter the API Key created in the AIHubMix Console under OpenAI API Key. Turn on Override OpenAI Base URL, then enter:
If the primary endpoint is temporarily unavailable, use the backup endpoint:
Enter OpenAI API Key and Base URL After filling in the fields, click Verify. When verification succeeds, Cursor can send OpenAI-compatible requests through AIHubMix.

​
3. Add a model

Add the model ID you want to use in the model settings area, for example gpt-5.6-terra. The model ID must match the name in the AIHubMix model list. Add an AIHubMix model To use Claude, Gemini, Qwen, Kimi, or other models, add the model ID supported by AIHubMix directly. Avoid selecting Cursor’s built-in official model entries, because those entries may use the provider’s own default endpoint instead of the AIHubMix address configured above.

​
Use and verify

Return to Cursor, select the model you added in the chat or Agent panel, and send a simple request. If Cursor returns a normal response, the configuration is working. Use an AIHubMix model in Cursor

​
FAQ

What should I do if Verify fails? Check that the API Key is complete, the Base URL includes /v1, and your network can access the configured address. If the primary endpoint is temporarily unavailable, change Override OpenAI Base URL to https://api.inferera.com/v1 and verify again. Why is Cursor not using AIHubMix after I select a model? Make sure you selected the AIHubMix model ID you added to the model list, not Cursor’s built-in official model entry. With this setup, Cursor sends OpenAI-compatible requests to the Base URL you configured.
Last updated: 2026-08-04