Auto mode is extremely slow, but all manually selected models are fast

[Danil_Zelichenko (Данил Зеличенко)]

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

Auto mode is consistently very slow for me.
If I manually select any available model, responses are fast.
As soon as I switch back to Auto, the slowdown returns immediately.

Steps to Reproduce

1. Open a new chat
2. Send a short request in Auto mode → very slow
3. Switch to manually selected models → fast
4. Switch back to Auto → slow again

Expected Behavior

Auto mode should be at least comparable to manually selected models and should not be dramatically slower.

Operating System

Windows 10/11

Version Information

Version: 3.0.9 (user setup)
VSCode Version: 1.105.1
Commit: 93e276db8a03af947eafb2d10241e2de17806c20
Date: 2026-04-03T02:06:46.446Z
Layout: editor
Build Type: Stable
Release Track: Default
Electron: 39.8.1
Chromium: 142.0.7444.265
Node.js: 22.22.1
V8: 14.2.231.22-electron.0
OS: Windows_NT x64 10.0.26200

For AI issues: which model did you use?

The issue happens specifically in Auto mode.
If I manually select any available model, responses are fast.
As soon as I switch back to Auto, the slowdown returns immediately.

Does this stop you from using Cursor

Sometimes - I can sometimes use Cursor

[deanrie]

Hey, thanks for the report. This is a known issue. Auto mode goes through extra routing steps on the server that don’t happen when you pick a model manually, and that adds latency. The team is aware and is working on improving the routing.

For now, like you noticed, the workaround is to pick a model manually.

If you want to help us debug your specific case, send the Request ID from one of the slow requests in Auto mode (top right of the chat > Copy Request ID). That’ll help us see what’s happening on the server side.

Let me know if you have any questions.