High Load bug everyday

Describe the Bug

Whenever I use it after 5 p.m., the “High Load” error occurs. I hope you can fix this problem as soon as possible.
Request ID: afc67847-6c08-45f0-bd52-0dfbec92cb2e
{“error”:“ERROR_RESOURCE_EXHAUSTED”,“details”:{“title”:“High Load”,“detail”:“We’re experiencing high demand for the selected model right now. Please switch to Auto, another model, or try again in a few moments.”,“isRetryable”:true,“additionalInfo”:{},“buttons”:,“planChoices”:},“isExpected”:true}
[resource_exhausted] Error
OTe: [resource_exhausted] Error
at lpf (vscode-file://vscode-app/d:/cursorAi/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9097:38348)
at apf (vscode-file://vscode-app/d:/cursorAi/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9097:37251)
at Cpf (vscode-file://vscode-app/d:/cursorAi/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9098:5088)
at Tva.run (vscode-file://vscode-app/d:/cursorAi/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9098:9098)
at async Vyt.resume (vscode-file://vscode-app/d:/cursorAi/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34206:60624)
at async mgc.streamFromAgentBackend (vscode-file://vscode-app/d:/cursorAi/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34255:7835)
at async mgc.getAgentStreamResponse (vscode-file://vscode-app/d:/cursorAi/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34255:8576)
at async qTe.submitChatMaybeAbortCurrent (vscode-file://vscode-app/d:/cursorAi/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9180:14965)

Steps to Reproduce

“High Load” error

Operating System

Windows 10/11

Version Information

any CLI version

Does this stop you from using Cursor

Yes - Cursor is unusable

Hey, this is a known issue. During peak hours, Auto mode can hit capacity limits on the model it tries to route to.

Workaround: manually select a specific model, for example composer-1.5, instead of Auto. This usually fixes it because it avoids the overloaded model. A few other users confirmed this helps: Repeated High Load Error

The team is aware of the Auto mode routing behavior during high demand.

Let me know if switching models helps.

A post was merged into an existing topic: Repeated High Load Error