My API key is successfully verified but I get "invalid model"

[david1175082521]

Thanks for reporting a bug you have found in Cursor!
Please add the following info to help us diagnose your issue:

Check the forum to ensure the issue hasn’t been reported already
I’ve checked.

Provide a clear description of the bug
I can successfully verify the API key for my custom model (Step series).
The API provider also shows a record of using the key for verification.
But I get “invalid model” when using chat mode or cmd+k mode.

Explain how to reproduce the bug (if known)
Attach screenshots or recordings (e.g., .jpg, .png, .mp4).

Tell us your operating system and your Cursor version (e.g., Windows, 0.x.x).
Version: 0.49.6 (Universal)
VSCode Version: 1.96.2
Commit: 0781e811de386a0c5bcb07ceb259df8ff8246a50
Date: 2025-04-25T04:39:09.213Z
Electron: 34.3.4
Chromium: 132.0.6834.210
Node.js: 20.18.3
V8: 13.2.152.41-electron.0
OS: Darwin arm64 24.4.0

Tell us if the issue stops you from using Cursor.

[david1175082521]

any one can help?
I cannot use any custom models like Qwen and Step

[deanrie]

Hey, which provider do you use?

[david1175082521]

I’m using qwen and step.
After I’ve upgraded to pro, I can use these custom models.
However, I think free users should have the access to use their custom models.

[deanrie]

Yes, this is an issue that we are trying to resolve. Free users should still be able to add their API keys.

[BenkangPeng]

Looking forward to cursor team’s improvement! I met the same issue when I add the custom deepseek model by deepseek api.

My key has been verified(deepseek offical said their key is compatiable to openai’s):

But I get the error when chat with the model: