Model name invalid & all models still failing

Support Bug Reports
1

Where does the bug appear (feature/product)?

Background Agent (Network and account)

Describe the Bug

Cursor have investigated the request ID and my account. The error logs show that all model providers are unavailable for my requests, which explains why every model is failing. This needs investigation from their technical team to understand why all providers fail

2

Hi there!

We detected that this may be a bug report, so we’ve moved your post to the Bug Reports category.

To help us investigate and fix this faster, could you edit your original post to include the details from the template below?

Bug Report Template - Click to expand

Where does the bug appear (feature/product)?

  • Cursor IDE
  • Cursor CLI
  • Background Agent (GitHub, Slack, Web, Linear)
  • BugBot
  • Somewhere else…

Describe the Bug
A clear and concise description of what the bug is.

Steps to Reproduce
How can you reproduce this bug? We have a much better chance at fixing issues if we can reproduce them!

  1. …
  2. …
  3. …

Expected Behavior
What is meant to happen here that isn’t working correctly?

Screenshots / Screen Recordings
If applicable, attach images or videos (.jpg, .png, .gif, .mp4, .mov)

Operating System

  • Windows 10/11
  • MacOS
  • Linux

Version Information

  • For Cursor IDE: Menu → About Cursor → Copy
  • For Cursor CLI: Run agent about in your terminal
IDE:
Version: 2.xx.x
VSCode Version: 1.105.1
Commit: ......

CLI:
CLI Version 2026.01.17-d239e66

For AI issues: which model did you use?
Model name (e.g., Sonnet 4, Tab…)

For AI issues: add Request ID with privacy disabled
Request ID: f9a7046a-279b-47e5-ab48-6e8dc12daba1
For Background Agent issues, also post the ID: bc-…

Additional Information
Add any other context about the problem here.

Does this stop you from using Cursor?

  • Yes - Cursor is unusable
  • Sometimes - I can sometimes use Cursor
  • No - Cursor works, but with this issue

The more details you provide, the easier it is for us to reproduce and fix the issue. Thanks!

5

Hey, I’ll need a bit more info to figure this out. Right now there aren’t enough details in the post to diagnose it.

Please update the post with:

  1. Request ID: open the chat context menu (top right corner) and click Copy Request ID. Please share at least one ID from a failed request.
  2. Exact error message: screenshot or the error text you see. Model name invalid and all providers unavailable are different issues, so I want to understand what’s actually happening.
  3. Where the error happens: Chat, Agent, or Background Agent?
  4. Cursor version: Menu > About Cursor > Copy.
  5. OS: Windows, Mac, or Linux.

Also, you mentioned Cursor already investigated your Request ID and account. Can you share a link to that thread or a previous Request ID? That’ll make it easier to pick up the context.

Let me know, and we’ll sort it out.

6

Request ID: 64c1304b-2d0f-46eb-b330-5f0c96703bb1
[internal] Failed to run step, exceeded max retries
_he: [internal] Failed to run step, exceeded max retries
at jpA (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:32115:44883)
at WpA (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:32115:43786)
at ZpA (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:32116:5088)
at Ool.run (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:32116:9098)
at async s$o.resume (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:44360:12816)
at async zOl.streamFromAgentBackend (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:44408:8884)
at async zOl.getAgentStreamResponse (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:44408:9837)
at async yLe.submitChatMaybeAbortCurrent (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:32182:15752)

7

I see the Request ID and stack trace, thanks. The Failed to run step, exceeded max retries error usually means the backend can’t reach the model provider after several attempts.

While we’re looking into it, please try this:

  1. Start a new chat, don’t continue the current one
  2. Settings > search for HTTP/2 > turn on Disable HTTP/2, then restart Cursor
  3. Switch the model manually, instead of Auto pick a specific one like Claude Sonnet 4.6
  4. If you’re using a VPN or proxy, try without it

I also need a couple details from my previous message so I can check your account:

  • Cursor version: Menu > About Cursor > Copy
  • OS: Windows, Mac, or Linux?

Let me know how it goes after these steps.

8

Version: 2.5.26
VSCode Version: 1.105.1
Commit: 7d96c2a03bb088ad367615e9da1a3fe20fbbc6a0
Date: 2026-02-26T04:57:56.825Z
Build Type: Stable
Release Track: Default
Electron: 39.4.0
Chromium: 142.0.7444.265
Node.js: 22.22.0
V8: 14.2.231.22-electron.0
OS: Linux x64 6.8.0-107-generic

ubuntu22.04

I don’t use VPN，urn on Disable HTTP/2, then restart Cursor dosen’t work,Switch the model manually, instead of Auto pick a specific one like Claude Sonnet 4.6, any model dosen’t work.

9

I see the info, thanks. The main thing that stands out is you’re on version 2.5.26 from February. That’s pretty old, and it could be why all models are failing. The backend may have updated routing, and an older client can send invalid requests.

First thing to do:

  1. Update Cursor to the latest version: Help > Check for Updates, or download the newest build from cursor.com
  2. After updating, restart Cursor and try the new chat again

If the issue is still there after updating:

  • Go to Cursor Settings > Network > Run Diagnostics and paste the results here
  • Try a different network, like a mobile hotspot. This helps confirm whether something is being blocked by your ISP

Let me know how it goes after the update.

10

Thanks for replying my issue!But it still doesn’t work whatever I input ,short words in a new prompt ,a newer version or in a new folder environment!
Version: 3.0.4
VSCode Version: 1.105.1
Commit: 63715ffc1807793ce209e935e5c3ab9b79fddc80
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: Linux x64 6.8.0-107-generic

Request ID: 4c96ae3c-74cd-4c91-be04-6facbcdf8c96
[internal] Failed to run step, exceeded max retries
rae: [internal] Failed to run step, exceeded max retries
at Ntw (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:43958:24479)
at Ptw (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:43958:23385)
at Htw (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:43959:6355)
at j5u.run (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:43959:11154)
at async qIn.runAgentLoop (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:56301:11753)
at async s0d.streamFromAgentBackend (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:56371:11057)
at async s0d.getAgentStreamResponse (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:56371:17161)
at async s3e.submitChatMaybeAbortCurrent (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:44070:19892)
at async mu (vscode-file://vscode-app/usr/share/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:55354:4887)

在 2026-04-03 01:34:32，“Dean Rie” [email protected] 写道：