+1. Pls fix urgently thank you
1 Like
same issue!
1 Like
Same!
1 Like
Please fix it ASAP
1 Like
Any update?
1 Like
Same issue here. Hoping for a fix soon.
1 Like
This continues to be a very work impacting issue for me. 429 for almost every request when trying to use any Gemini model. Using a Tier 3 key and getting no where close to the actual limit. Gemini CLI works with the same key fine
4 Likes
Is there any update on this? I’ve temporarily switched to Antigravity, but I hope Cursor will fix it soon so I can switch back (I’ve already subscribed to Cursor for a year).
Is there any update?
Is there any update? Also, switched to antigravity
@deanrie HI!, Any update for this?
Hey everyone, I get that this is really inconvenient.
This is a work issue, and the team is already working on a fix. For now, the best option is to temporarily use a different model (Claude or GPT).
i guess if the team cant fix it soon, we hv to switch to antigravity…
sad to see cursor still cant fix it in 2 weeks
9 Likes
I’ve noticed that switching to other models consumes our personal tokens. Since I assume the majority of us are using Gemini Pro via the API, this setup isn’t really the most optimal one. Maybe we should look for a better alternative? @deanrie
+1 to this
1 Like
+1 here, this is very counterproductive
1 Like
+1 
1 Like
Could you please fix this ASAP? It’s really urgent.
1 Like
+1 same here. With own Gemini API key, cursor is almost unusable now.
1 Like
I frequently encounter the issue. What about implementing an automatic retry policy aside from controlling rate limit? Users can configure the retry policy as interval, exponential backoff and so on.
Version: 2.3.34
VSCode Version: 1.105.1
Commit: 643ba67cd252e2888e296dd0cf34a0c5d7625b90
Date: 2026-01-10T21:17:10.428Z
Electron: 37.7.0
Chromium: 138.0.7204.251
Node.js: 22.20.0
V8: 13.8.258.32-electron.0
OS: Darwin arm64 24.6.0