# Have they already cut Cursor from the OpenAI models?

**URL:** <https://forum.cursor.com/t/have-they-already-cut-cursor-from-the-openai-models/170504>\
**Category:** Bug Reports\
**Tags:** openai, networking\
**Created:** [September 3, 2026, 9:21pm UTC](https://forum.cursor.com/t/have-they-already-cut-cursor-from-the-openai-models/170504 "2026-09-03T21:21:04Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Rock\_Law](https://avatars.discourse-cdn.com/v4/letter/r/a3d4f5/32.png) [@Rock\_Law](https://forum.cursor.com/u/Rock_Law)\
**Post date:** [September 3, 2026, 9:21pm UTC](https://forum.cursor.com/t/have-they-already-cut-cursor-from-the-openai-models/170504/1 "2026-09-03T21:21:04Z")

</div>

I haven’t been able to use the gpt 5.6 sol for the last few hours (trouble reaching model provider) etc.

---

<div class="post-metadata">

**Author:** ![system](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/system/32/99069_2.png) [@system](https://forum.cursor.com/u/system)\
**Post date:** [September 3, 2026, 9:21pm UTC](https://forum.cursor.com/t/have-they-already-cut-cursor-from-the-openai-models/170504/2 "2026-09-03T21:21:13Z")

</div>

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)?**
> 
> - Editor, Tab & Chat (autocomplete, Composer, in-editor agent)
> - Terminal & commands
> - Models, pricing & API keys (availability, Auto/Max, BYOK/Bedrock)
> - MCP & tools
> - Cloud Agents & Automations ([cursor.com/agents](http://cursor.com/agents), scheduled/event)
> - BugBot & Code Review
> - Cursor CLI
> - Cursor Mobile
> - Remote (SSH / Dev Containers / WSL)
> - Account, billing & login
> - Something 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
> 
> ```auto
> 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!

---

<div class="post-metadata">

**Author:** ![kevinn](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/kevinn/32/101206_2.png) [@kevinn](https://forum.cursor.com/u/kevinn)\
**Post date:** [September 3, 2026, 10:07pm UTC](https://forum.cursor.com/t/have-they-already-cut-cursor-from-the-openai-models/170504/7 "2026-09-03T22:07:31Z")

</div>

Hey @Rock_Law, thanks for the report.

To answer the question in the title: no, OpenAI models have not been cut off. OpenAI announced they plan to end the direct partnership in about three months, but GPT models (including GPT-5.6 Sol) continue to work in Cursor today, and we will share more about continued access to OpenAI models in the coming weeks.

What you are hitting is different. The requests from that particular chat are being rejected by the model provider’s safety filter, not by a connection problem. Because the whole conversation is sent to the model on every message, every retry in that chat gets rejected the same way, and unfortunately the error message we show for it (“trouble reaching the model provider”) is misleading. We are looking at making that message clearer.

To get unblocked:

1. Start a new chat (the + button at the top of the agent panel) rather than continuing the current one.
2. If your last few messages in the old chat included pasted content or screenshots, try describing what you need in your own words first, then add the material back in smaller pieces.

Your current chat is also very long (hundreds of messages), so a fresh chat should be faster and more reliable regardless.

If a brand new chat with GPT-5.6 Sol still fails, reply with the Request ID from the error (click the error, then Copy Request ID, with Privacy Mode off) and we will take another look.
