@Yasser_Elsayed @Kazopl Look here Context decrease - Support / Bug Reports - Cursor - Community Forum
It was resolved for me
It was resolved for me
Resolved for me as well after a restart. Thanks for taking care of this quickly.
The fix for this has been deployed. The functional 300K cap that was overriding the 1M Max mode context is now resolved on our end (server-side, so no client update needed).
A few of you have already confirmed it’s working. If anyone is still seeing the old behavior, try restarting Cursor and let us know.
@Yassine_A — regarding the billing concern you raised: please email [email protected] with your account details so our team can look into that for you.
I’m seeing this problem right now with the latest version.
Version: 3.5.38 (user setup)
VSCode Version: 1.105.1
Commit: 009bb5a3600dd98fe1c1f25798f767f686e14750
Date: 2026-05-26T21:32:06.537Z
Layout: editor
Build Type: Stable
Release Track: Default
Electron: 39.8.1
Chromium: 142.0.7444.265
Node.js: 22.22.1
V8: 14.2.231.22-electron.0
OS: Windows_NT x64 10.0.26200
The fix for this specific issue was deployed server-side on May 12 and has been working since then.
To help narrow down what you’re seeing, could you share a few details?
-
Which model are you using? (e.g., Opus 4.7, Opus 4.8, Sonnet 4.6)
-
Do you have Max mode enabled, and is the 1M context option selected in the model picker?
-
A screenshot of the context indicator showing the issue
-
A Request ID from an affected chat (three-dot menu in chat > Copy Request ID)
That will help us figure out whether this is the same issue or something different. Thanks!
Hello sir. Could you please consider supporting context limit adjust for custom models as well?