Unable to use Deepseek on Cursor

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

Hello,

Since yesterday, I have been unable to use Deepseek’s AI on Cursor. I get error messages repeatedly with every request.

Thank you.

Steps to Reproduce

Simply by asking Deepseek for something

Operating System

Windows 10/11

Version Information

Version: 2.4.21 (system setup)
VSCode Version: 1.105.1
Commit: dc8361355d709f306d5159635a677a571b277bc0
Date: 2026-01-22T16:57:59.675Z
Build Type: Stable
Release Track: Default
Electron: 39.2.7
Chromium: 142.0.7444.235
Node.js: 22.21.1
V8: 14.2.231.21-electron.0
OS: Windows_NT x64 10.0.26200

For AI issues: which model did you use?

deepseek-coder

For AI issues: add Request ID with privacy disabled

Request ID: f316a72b-cb54-428f-bc48-20b155fd568b
{“error”:57,“details”:{“title”:“Provider 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}
[resource_exhausted] Error
LTe: [resource_exhausted] Error
at kmf (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9095:38337)
at Cmf (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9095:37240)
at $mf (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9096:4395)
at ova.run (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9096:8170)
at async qyt.runAgentLoop (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34190:57047)
at async Wpc.streamFromAgentBackend (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34239:7695)
at async Wpc.getAgentStreamResponse (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34239:8436)
at async FTe.submitChatMaybeAbortCurrent (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9170:14575)
at async Object.Oi [as onSubmit] (vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:32991:3808)
at async vscode-file://vscode-app/c:/Program%20Files/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:32965:59943

Does this stop you from using Cursor

No - Cursor works, but with this issue

1 Like

Deepseek removed from Cursor, but you can try other Models such as Gemini 3 Flash that cheap and have great capabilities

Deepseek Unavailable! No Response from Customer Support! - #3 by sanjeed5

1 Like

Thank you for your reply.

Unfortunately, I already have £20 to spend with Deepseek, so I was thinking of using it on Cursor… Is there really no way to use it?

Thank you.

so you bought from API Key? you can add that via API Key

Probably I met the similar problem.

I’m trying to use deepseek by manually adding the deepseek api keys in OpenAI API Key section, with model name deepseek-chat and base url https://api.deepseek.com/v1.

The strange thing is that for basic greetings or conversations like hi! what model are you, or explain CLT to me, etc., they all just worked fine. However, when I @ a file or let it digging the real, heavy work, it then fails, and returns the following issue:

Request ID: 32820236-f877-4602-a16f-50822497ffc4
{“error”:57,“details”:{“title”:“Provider 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}
[resource_exhausted] Error
LTe: [resource_exhausted] Error
at kmf (vscode-file://vscode-app/d:/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9095:38337)
at Cmf (vscode-file://vscode-app/d:/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9095:37240)
at $mf (vscode-file://vscode-app/d:/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9096:4395)
at ova.run (vscode-file://vscode-app/d:/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9096:8170)
at async qyt.runAgentLoop (vscode-file://vscode-app/d:/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34190:57047)
at async Wpc.streamFromAgentBackend (vscode-file://vscode-app/d:/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34239:7695)
at async Wpc.getAgentStreamResponse (vscode-file://vscode-app/d:/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:34239:8436)
at async FTe.submitChatMaybeAbortCurrent (vscode-file://vscode-app/d:/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:9170:14575)
at async Object.Oi [as onSubmit] (vscode-file://vscode-app/d:/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:32991:3808)
at async vscode-file://vscode-app/d:/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:32965:59943

I suspected if it is the time-out problem, but it still does not work even if I extended the limit manually. Kind of frustrating.

Thanks!

1 Like

Hello,

I think I didn’t explain myself clearly, but I’m already using an API key. I added the Deepseek models I wanted to use to the list, but nothing works. It says ‘Reconnecting’ and then gives me an error message when I make a request.

I encountered the same issue after updating Cursor, but after downgrading Cursor, Deepseek works again.
Previous versions are available on GitHub, so please look for them there.