For AI issues: add Request ID with privacy disabled
Request ID: 2e971901-6566-4451-94b1-5b6d34a05000
{“error”:“ERROR_RESOURCE_EXHAUSTED”,“details”:{“title”:“High Load”,“detail”:“We’re experiencing high demand for the selected model right now. Please upgrade to Pro, switch to Auto, another model, or try again in a few moments.”,“isRetryable”:true,“additionalInfo”:{},“buttons”:,“planChoices”:},“isExpected”:true}
[resource_exhausted] Error
mie: [resource_exhausted] Error
at P5A (vscode-file://vscode-app/c:/Users/joris/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34267:23755)
at B5A (vscode-file://vscode-app/c:/Users/joris/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34267:22658)
at $5A (vscode-file://vscode-app/c:/Users/joris/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34268:6285)
at Wou.run (vscode-file://vscode-app/c:/Users/joris/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34268:10400)
at async $Oa.runAgentLoop (vscode-file://vscode-app/c:/Users/joris/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:46832:10024)
at async n5u.streamFromAgentBackend (vscode-file://vscode-app/c:/Users/joris/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:46886:9277)
at async n5u.getAgentStreamResponse (vscode-file://vscode-app/c:/Users/joris/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:46886:13663)
at async bMe.submitChatMaybeAbortCurrent (vscode-file://vscode-app/c:/Users/joris/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34329:17597)
at async Ea (vscode-file://vscode-app/c:/Users/joris/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:45811:4826)
This is a known issue. The upgrade to Pro message is showing incorrectly for users who are already on a paid plan. The team is aware, but there’s no timeline yet for a fix.
In the meantime, try selecting a specific model manually, for example composer-1.5, instead of Auto. Auto mode sometimes fails to route to an available model during high demand periods, but picking one directly should work.
A few other users are hitting the same thing today. See this thread for reference: High Load Issue on Cursor
I only have access to composer-1.5 and am getting a “Unable to Reach model Provider”. So far, I’m the only person in my department facing this issue. Are there other steps I can try to resolve?
Edit:
I was able to resolve my issue by turning “Auto” on. I had it disabled. Enabling it resolved the issue.
I’m facing the same issue, and manual selection of the model (composer 1.5) worked
what about the pricing/usage when I use composer manually instead of using auto mode ?
I’m usually usng auto 95% of the time because it does the job right well, and I only switch to manual when auto is stuck.
when I manually select a specific model, I can’t use it too often or I spend all my credits in two days, and in auto I can most often last the whole month @deanrie could you please clarify if manual selection of composer is as generous for usage as using auto ?
I am also facing the same problem. Manually selecting Composer 1.5 can solve this problem, but the model’s ability is too poor and the analysis results are incorrect, which cannot be trusted by me. Therefore, I am currently in a state of giving up using cursor. I have been using cursor for almost a year, and the recent series of problems have made me very frustrated. I hope to solve this problem as soon as possible. Currently, cursor is completely unusable.
this is my 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)
I’m a paid Cursor Pro user and heavily rely on the auto mode for my personal development work. Over the past weeks, I’ve been hitting frequent rate limits in auto mode, which makes it impossible to continue my tasks smoothly.
I tried switching to the composer-1.5 model to avoid the limit, but after sending only one single question, I got the error: “You have exceeded your limit.” This means switching models does not work as a solution either.
Could the team please look into optimizing the rate-limiting logic for the auto mode? As a Pro subscriber, I expect to have reliable access to the core features I paid for, without being blocked mid-workflow by arbitrary limits. This is critical for me to keep using Cursor productively.
I’m seeing the same issue. So I’ve had to switch to another paid model. I’m a Cursor Pro user who relies on Auto Mode with the annual plan, but the replacement feels less smart than before.
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)
High Load error tells me to “switch to Auto” even when I’m already using Auto, and tells me to “switch to … another model” even when using free.
[This bug report is NOT about the underlying High Load error, which has been reported elsewhere. It is about the incorrect error messages the IDE shows in this situation.]
Steps to Reproduce
Several times this week, starting an agent in “plan” mode with “Auto” selected.
This has happened both for me (in Pro), and for a colleague I was trying to persuade to switch to Cursor (in free).
Expected Behavior
This should give a useful warning message.
In particular, it should NOT tell me to “switch to Auto” mode when I am already in Auto mode.
For my colleague, who was using Free, the message told him to “switch to … another model”, which then gives the error that he couldn’t do that on free.
same i reload