I Am on the Request-Based Plan my requests are being used up at twice or sometimes three times the advertised rate

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

My request being used at twice the rate.

Steps to Reproduce

Use any model, and my requests will get used twice or three times the rate.

Expected Behavior

Have my requests be used at the advertised rate

Operating System

MacOS

Current Cursor Version (Menu → About Cursor → Copy)

Version: 1.7.37
VSCode Version: 1.99.3
Commit: 1910e1fc4fa41b809793f6c5477108b775c0a120
Date: 2025-10-06T04:16:03.009Z (7 hrs ago)
Electron: 34.5.8
Chromium: 132.0.6834.210
Node.js: 20.19.1
V8: 13.2.152.41-electron.0
OS: Darwin arm64 25.0.0

Does this stop you from using Cursor

Yes - Cursor is unusable

Claude 4.5 is burning 4 requests each time

Could you please share Request IDs and any screenshots of your usage please?


You can see that with just one codex request, it’s charged me for three requests where it should just be one.

Please let me know where I can find the request ID.

I think this is my chat ID

8f602728-efd4-43dd-a8f7-8ca242bdc6d5

I think I’ve burned through about 200 more requests than if I were using the advertised request rates.

I’m having the same issue. Although it’s marked as 1x request, it’s actually consuming more. I’m using gpt-5-high

@G4Q4 were you using Max mode by any chance? Max mode can consume more tokens/requests

@coolboy5398 can you please share Request IDs and usage dashboard?

Request ID is 710f8bb7-3a73-40f1-a035-faf8b299378c
The two screenshots show my usage before and after today. I believe I was using the model at the standard 1x request rate in both cases

@sanjeed5 No im not using max mode. Any update on this bug being resolved?
Also, are we going to be compensated for all these wasted tokens?

This topic was automatically closed 22 days after the last reply. New replies are no longer allowed.