[Bug] Excessive quota consumption with Claude models on Max plan
Bug Description
Helo, I'm using plan Max (5x) for a while. What I noticed during my recent two sessions with Fable and Opus (both on Max) is that they burn my quota extremally quickly, despite I did only a few requests to the Vertex. I'm literally at 85% of usage despite I made only a few commands. I would be grateful for help, because even if I'd buy Max 20x, at this pace I'd burn quota within hour, which absolutely shouldn't be like this.
Environment Info
- Platform: darwin
- Terminal: WarpTerminal
- Version: 2.1.210
- Feedback ID: 0efb57bf-7b95-40b3-bb20-28628a57f974
Quota was almost at 85%
<img width="748" height="630" alt="Image" src="https://github.com/user-attachments/assets/b10baa12-344d-43a2-a101-749688a2aa4f" />
Context when the quota was 85%
<img width="1138" height="483" alt="Image" src="https://github.com/user-attachments/assets/8c1aeb43-4c67-4b46-8a13-19946d850f64" />
Moment later it was like this:
<img width="752" height="625" alt="Image" src="https://github.com/user-attachments/assets/ee68c64f-f185-44b5-8618-fe73332d5603" />
<img width="1375" height="525" alt="Image" src="https://github.com/user-attachments/assets/01facb8d-53c9-490d-ad0c-9f47e803a9d7" />
You can compare time how quickly I burnt remaining 15% quota. It's the first time such thing happened to me.
This issue has 1 comment on GitHub. Read the full discussion on GitHub ↗