We've hit a rate limit with the provider. - Legacy plan

[Fluent_in_France]

Describe the Bug

I hit a rate limit on the legacy plan despite having used only 92/500 monthly requests.

Steps to Reproduce

Request info:

Request ID: 6b8061c8-8da0-44e2-90ce-17b26ab42101
{“error”:“ERROR_OPENAI_RATE_LIMIT_EXCEEDED”,“details”:{“title”:“Error connecting to the provider.”,“detail”:“We’ve hit a rate limit with the provider. Please switch to the ‘auto-select’ model, another model, or try again in a few moments.”,“additionalInfo”:{},“buttons”:},“isExpected”:false}
ConnectError: [unavailable] Error
at C9a.$endAiConnectTransportReportError (vscode-file://vscode-app/Applications/Cursor.app/Contents/Resources/app/out/vs/workbench/workbench.desktop.main.js:4757:223764)
at uir.S (vscode-file://vscode-app/Applications/Cursor.app/Contents/Resources/app/out/vs/workbench/workbench.desktop.main.js:492:17741)
at uir.Q (vscode-file://vscode-app/Applications/Cursor.app/Contents/Resources/app/out/vs/workbench/workbench.desktop.main.js:492:17519)
at uir.M (vscode-file://vscode-app/Applications/Cursor.app/Contents/Resources/app/out/vs/workbench/workbench.desktop.main.js:492:16607)
at uir.L (vscode-file://vscode-app/Applications/Cursor.app/Contents/Resources/app/out/vs/workbench/workbench.desktop.main.js:492:15708)
at Bwt.value (vscode-file://vscode-app/Applications/Cursor.app/Contents/Resources/app/out/vs/workbench/workbench.desktop.main.js:492:14500)
at ve.B (vscode-file://vscode-app/Applications/Cursor.app/Contents/Resources/app/out/vs/workbench/workbench.desktop.main.js:48:2398)
at ve.fire (vscode-file://vscode-app/Applications/Cursor.app/Contents/Resources/app/out/vs/workbench/workbench.desktop.main.js:48:2617)
at Git.fire (vscode-file://vscode-app/Applications/Cursor.app/Contents/Resources/app/out/vs/workbench/workbench.desktop.main.js:4744:10379)
at u.onmessage (vscode-file://vscode-app/Applications/Cursor.app/Contents/Resources/app/out/vs/workbench/workbench.desktop.main.js:6968:12271)

Expected Behavior

Based on @condor’s answer on this topic: Why Is Traditional Mode Also Affected by Speed Limits? How to Choose? - #2 by jjjjjj

“the legacy plan has no rate limit and is limited to 500 requests but there is no slowdown from Cursors side. If you have issues with any model please file a detailed bug report so the issue can be investigated.”

Screenshots / Screen Recordings

Operating System

MacOS

Current Cursor Version (Menu → About Cursor → Copy)

Version: 1.2.2 (Universal)
VSCode Version: 1.99.3
Commit: faa03b17cce93e8a80b7d62d57f5eda6bb6ab9f0
Date: 2025-07-07T06:07:27.002Z
Electron: 34.5.1
Chromium: 132.0.6834.210
Node.js: 20.19.0
V8: 13.2.152.41-electron.0
OS: Darwin x64 24.5.0

Does this stop you from using Cursor

Yes - Cursor is unusable

[encyphor]

That is saying cursor hit THEIR rate limits with THEIR provider, not that they are rate limiting YOU based on YOUR PLAN. They have agreements with providers, and rate limits applied to them just like all entities do, theirs is just astronomically higher than an individuals would be as they’re prompting on behalf of hundreds (?) of thousands of users - but they can still run into rate limits to their providers.

[Xernive]

Where do we see these magical rate limits at?

[deanrie]

Hey, which model are you using? Also, try starting a new chat, it usually resolves the issue.

[encyphor]

You can’t, you have to hope/expect that cursor maintains enough capacity to deliver these models without that error. I’m just pointing out they’re not limiting YOU specifically based on rate limits or quota, but it feels the same. But it isn’t their per user system, it’s them needing to manage capacity from providers better.

[Xernive]

I see, thank you for the explanation.