Issue with Custom OpenAI API Configuration in Cursor Team Edition

[user954]

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

I’m encountering configuration issues when trying to use my own purchased deepseek API with Cursor Team Edition (after my team quota was exhausted). Here’s my situation:

Current Setup:

Added my purchased API key to the “deepseek API key” field
Enabled the deepseek API toggle/slider
Overrode the Base URL with my custom endpoint
Specified my model name in the settings
Problem Behavior:

When the deepseek API toggle is enabled:
I keep getting “team limit” notifications (suggesting Cursor is still trying to use team quota)
When the deepseek API toggle is disabled:
I get an “invalid model” error instead
Troubleshooting Attempted:

Verified my API key, Base URL, and model name are correct
Restarted Cursor completely after configuration changes
Tried different configuration orders

Steps to Reproduce

Add custom model always reproduce

Operating System

Windows 10/11

Current Cursor Version (Menu → About Cursor → Copy)

Cursor Version:
Version: 1.7.39 (system setup)
Commit: 1.99.3
Date: a9c77ceae65b77ff772d6adfe05f24d8ebcb2790
Electron: 2025-10-08T00:33:20.352Z
ElectronBuildId: 34.5.8
Chromium: undefined
Node.js: 132.0.6834.210
V8: 20.19.1
OS: 13.2.152.41-electron.0

Does this stop you from using Cursor

No - Cursor works, but with this issue

[deanrie]

Hey, thanks for the report. I need a bit more info to diagnose the issue:

• Could you share a screenshot of your model settings with the DeepSeek configuration?
• Which feature triggers the “team limit” notification, Agent or inline chat?

Once I see your exact configuration, I can help debug or escalate to the team if it’s a bug in the API override logic.

[user954]

Here is my screenshot, I’m not sure if I did something wrong

[deanrie]

Sorry for the delay. I’d recommend reaching out to your team’s Cursor admin, since Team plans often have features like custom API keys disabled.