Describe the Bug
I started my Pro Plan subscription on July 14. Since then, I’ve been carefully tracking my usage based on the limits described in the official documentation.
Despite staying well below the documented Pro Plan limits, I’m now receiving the message:
“You’ve hit your usage limit. You’ve saved $65 on API model usage this month with Pro.”
According to the documentation, the Pro Plan allows approximately:
~225 Claude Sonnet 4 requests
~550 Gemini requests
~650 GPT-4.1 requests
Here’s my actual usage from the Cursor dashboard:
Claude (4-sonnet + 3.7 + 3.5): 104 requests total
Gemini-2.5-pro: 93 requests
Auto: 99 requests
These numbers are clearly under the advertised limits, yet further usage is being blocked. This suggests a potential bug in how usage is being tracked or enforced.
Steps to Reproduce
Start a Pro Plan subscription (mine started on July 14).
Use models within the limits described in the official pricing documentation(Cursor – Models & Pricing)
Example usage:
~104 Claude Sonnet/ Claude 3.7 / 3.5 requests total
~93 Gemini-2.5-pro requests
~98 Auto requests
Regularly check the Cursor usage dashboard to ensure usage stays under the documented limits.
After continued use (while still under the limits), a blocking message appears:
“You’ve hit your usage limit. You’ve saved $65 on API model usage this month with Pro.”
Screenshots / Screen Recordings
Operating System
Windows 10/11
Current Cursor Version (Menu → About Cursor → Copy)
Version: 1.2.4 (user setup)
VSCode Version: 1.99.3
Commit: a8e95743c5268be73767c46944a71f4465d05c90
Date: 2025-07-10T17:09:01.383Z
Electron: 34.5.1
Chromium: 132.0.6834.210
Node.js: 20.19.0
V8: 13.2.152.41-electron.0
OS: Windows_NT x64 10.0.26100