Model Provider Connection Error – Persistent Issue

[Ebru_YILMAZ]

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

Hello,

I’ve been encountering the following error while using Cursor:

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

ssue Details:

The error occurs consistently and does not seem temporary
Retrying after some time does not resolve the issue
My internet connection is stable (1000 Mbps fiber)
I am not using a VPN
Restarting the application did not fix the problem

Steps I’ve Tried:

Restarted Cursor
Restarted my computer
Tried a different network (same result)

Steps to Reproduce

Steps to Reproduce:

1. Open Cursor IDE
2. Start a new chat or open an existing project
3. Try to send a prompt to the model
4. The error appears: “We’re having trouble connecting to the model provider…”

Screenshots / Screen Recordings

Operating System

Windows 10/11

Version Information

Version: 2.6.22 (system setup)
VSCode Version: 1.105.1
Commit: c6285feaba0ad62603f7c22e72f0a170dc8415a0
Date: 2026-03-27T15:59:31.561Z
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?

GPT-5.2 extra high

For AI issues: add Request ID with privacy disabled

bbed0be8-25c4-4378-b266-41c46cc7faac

Does this stop you from using Cursor

Yes - Cursor is unusable

[deanrie]

Hey, thanks for the report and the Request ID. This error shows up for some users, so let’s narrow it down.

Try these steps:

1. Disable MCP servers: Cursor Settings > Tools & MCP. If any MCP servers are connected, temporarily disable all of them.
2. Check model settings: Cursor Settings > Models. Make sure Override OpenAI Base URL is off and no third-party API keys are set.
3. Run network diagnostics: Cursor Settings > Network > Run Diagnostics. Share the results here.
4. Try a different model: instead of GPT-5.2, try Gemini 3.1 Pro or Composer 2. This helps confirm if the issue is tied to one provider.
5. Start a new chat: don’t continue the current one. Sometimes the built-up context can trigger provider errors.

A couple questions:

• Do you have any MCP servers set up?
• Does the error happen with all models, or only GPT-5.2?

Let me know what you find.