Pro+ account: Network Error / resource_exhausted whenever I select GPT or Claude models

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

Hi Cursor team,

I’m on the Pro+ plan, but I’m unable to use other models. Whenever I select a different GPT or Claude model and submit a prompt, Cursor displays a network error.

Retrying the request produces the same error. I have also tried selecting several different GPT and Claude models, but all of them fail in the same way.

My usage page shows 0% usage, so this does not appear to be caused by reaching my usage limit.

This issue has been happening since I renewed/upgraded my subscription to the Pro+ plan. I have been trying to use the other available models since renewing, but Cursor consistently returns this network error.

Error message
We’re having trouble connecting to the model provider.
This might be temporary - please try again in a moment.

[resource_exhausted] Error
RetriableError: [resource_exhausted] Error

Error details
{
“error”: “ERROR_NETWORK_ERROR”,
“details”: {
“title”: “Network Error”,
“detail”: “We’re having trouble connecting to the model provider. This might be temporary - please try again in a moment.”,
“isRetryable”: true,
“additionalInfo”: {},
“buttons”: ,
“planChoices”:
},
“isExpected”: true
}

Steps to Reproduce

Open Cursor.
Start or open an Agent chat.
Select a GPT or Claude model.
Submit a prompt.
Cursor displays ERROR_NETWORK_ERROR and [resource_exhausted].
Click retry or submit the request again.
The same error appears.

Expected Behavior

Because I have an active Pro+ plan and the usage page shows 0% usage, the selected GPT or Claude model should process the request normally.

If a model is temporarily unavailable, rate-limited or not included in my plan, Cursor should display a clear and accurate message instead of repeatedly showing a generic network error.

Actual behavior
Different GPT models fail.
Different Claude models also fail.
Retrying produces the same result.
The error is consistently shown as a network/provider error.
My account shows 0% usage.
The problem started after I renewed/upgraded to Pro+.
I have been unable to properly use the other models included with my plan.

Screenshots / Screen Recordings

Operating System

MacOS

Version Information

Version: 3.27.22
VS Code Extension API: 1.128.0
Commit: b1aa50cb6db84fd3e8c808259cb172ea73425c10
Date: 2026-10-27T00:33:02.045Z
Layout: Agent Window
Build Type: Stable
Release Track: Default
Electron: 42.11.16
Chromium: 148.0.7778.280
Node.js: 24.19.0
V8: 14.8.178.38-electron.0
xterm.js: 6.1.0-beta.291
OS: Darwin arm64 27.0.0

For AI issues: which model did you use?

all other models
while executing its showing rate limited by model provider

For AI issues: add Request ID with privacy disabled

3cb41bf0-081f-456e-af15-f761d57fe4eb

Additional Information

Could you please check the request ID and my account entitlement after the Pro+ renewal?

It appears that my plan is active, but requests to other model providers may not be routing correctly. Please confirm whether this is an account-provisioning issue, provider-capacity issue, rate limit, model-access problem, or Cursor routing error.

Thank you.

Does this stop you from using Cursor

No - Cursor works, but with this issue

Hi @Bhupathi_reddy

Can you let us know if you’re still facing the issue?

Yes I am still facing same issue since last 2 weeks.
I cant able to use other models, I can only use auto mode.

Hi @Bhupathi_reddy

Please check Cursor Settings → Models and remove any custom API keys / Base URLs you’ve added. It looks like the ones you have set are invalid, causing the error.