Thanks everyone for the details. Actually, I’ve already logged this issue in our internal bug tracker, and the team is investigating it.
Hey all, looks like a bad deployment occurred yesterday, which caused this!
Team are investigating now and I’d expect a fix soon - sorry for the inconvenience here 
Just added Anthropic key and got hit with the same after a few requests.
What’s inteeresting- one instance of Cursor works, one gets this error.
For the past 24 hours Claude’s API worked fine, and now—out of the blue—I’m getting the same error again. It’s really frustrating.
We encountered an issue when using your API key:
Provider was unable to process your request
API Error 400
{
“error”: {
“code”: 400,
“message”: “API key not valid. Please pass a valid API key.”,
“status”: “INVALID_ARGUMENT”,
“details”: [
{
“@type”: “type.googleapis.com/google.rpc.ErrorInfo”,
…
Hey team, sorry about this one!
We’ve found the cause of this issue and are deploying a fix now. Please let us know if you’re still seeing this in an hour or so!
Apologies for the disruption
Will this fix resolve sudden The model claude-4-sonnet-thinking does not work with your current plan or api key on only 1 out of 4 Cursor instances? The other 2 are plagued with the 400 API key error.
Yes I’m still seeing the issue now.
Indeed the issue still persists when using my own key for Anthropic on Cursor.
We encountered an issue when using your API key: Provider was unable to process your request API Error: Request failed with status code 400: [{ "error": { "code": 400, "message": "API key not valid. Please pass a valid API key.", "status": "INVALID_ARGUMENT", "details": [ { "@type": "type.googleapis.com/google.rpc.ErrorInfo", "reason": "API_KEY_INVALID", "domain": "googleapis.com", "metadata": { "service": "generativelanguage.googleapis.com" } }, { "@type": "type.googleapis.com/google.rpc.LocalizedMessage", "locale": "en-US", "message": "API key not valid. Please pass a valid API key." } ] } } ]
@danperks are you guys going to push an actual fix for this today?
4hrs later and the issues are still here
It appears our fix hasn’t had the desired effect, but the team are actively looking into this right now!
For those facing this, can you confirm if you are / are not using an API key for the model you are trying to query?
Yes I’m using the Anthropic API key for the model Claude Sonnet 4.
The error content has changed to an OpenAI error.
In the settings screen, the OpenAI API key field is blank, and the toggle is off.
- API errors occur only when continuing to use the same chat thread.
- Verification in the settings screen obviously succeeds.
- If switched to a new chat thread, it works without issue.
- Once an API error occurs, the API cannot be used in that thread (the built-in model can still be used as expected).
Version: 1.2.4 (system setup)
Commit: 1.99.3
Date: a8e95743c5268be73767c46944a71f4465d05c90
Electron: 2025-07-10T17:09:01.383Z
ElectronBuildId: 34.5.1
Chromium: undefined
Node.js: 132.0.6834.210
V8: 20.19.0
OS: 13.2.152.41-electron.0
Request ID: 1abd27a4-e605-4911-9141-b2acadc9321b
{“error”:“ERROR_OPENAI”,“details”:{“title”:“Unable to reach the model provider”,“detail”:“We’re having trouble connecting to the model provider. This might be temporary - please try again in a moment.”,“additionalInfo”:{},“buttons”:},“isExpected”:false}
ConnectError: [unavailable] Error
at x9a.$endAiConnectTransportReportError (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:4757:223764)
at hir.S (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:492:17741)
at hir.Q (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:492:17519)
at hir.M (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:492:16607)
at hir.L (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:492:15708)
at Bwt.value (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:492:14500)
at ve.B (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:48:2398)
at ve.fire (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:48:2617)
at Git.fire (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:4744:10379)
at u.onmessage (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:6968:12271)
Hey team, pretty sure we’ve got a working fix out for this - anyone able to confirm?
It seems solved now at least on my side.
Thanks!
After I submitted the error report the other day, I have not experienced any issues when using new chat threads. Everything has been working normally.
Thank you for the fix!