# Model provider flakiness / Anthropic

**URL:** <https://forum.cursor.com/t/model-provider-flakiness-anthropic/178666>\
**Category:** Bug Reports\
**Tags:** chat, anthropic, networking\
**Created:** [November 17, 2026, 6:30pm UTC](https://forum.cursor.com/t/model-provider-flakiness-anthropic/178666 "2026-11-17T18:30:21Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![rsb](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/rsb/32/105029_2.png) [@rsb](https://forum.cursor.com/u/rsb)\
**Post date:** [November 17, 2026, 6:30pm UTC](https://forum.cursor.com/t/model-provider-flakiness-anthropic/178666/1 "2026-11-17T18:30:21Z")

</div>

I’m seeing quite a few “we’re having trouble connecting to the model provider” messages this morning using Opus 5.5 (example request ID: 66bc12ea-9cb7-42c6-af82-7e683c25c271 ).

Anyone else having similar issues? It seems to pick up and run once Resume is clicked, but has been coming back.

---

<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:** [November 17, 2026, 6:30pm UTC](https://forum.cursor.com/t/model-provider-flakiness-anthropic/178666/2 "2026-11-17T18:30:29Z")

</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:** ![Colin](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/colin/32/90452_2.png) [@Colin](https://forum.cursor.com/u/Colin)\
**Post date:** [November 17, 2026, 8:50pm UTC](https://forum.cursor.com/t/model-provider-flakiness-anthropic/178666/9 "2026-11-17T20:50:36Z")

</div>

Hey @rsb, this one isn’t on your end. That request stopped because one of the routes we serve Opus 5.5 through was rate limited at that moment. It has been hitting a share of Opus 5.5 requests for the past few days and is still happening today, so you’re not the only one seeing it.

Resume is the right move, it picks up where the run stopped and nothing is lost. If it keeps interrupting you, switching to another model for a while avoids it, since it’s specific to Opus 5.5 right now.

I’ve passed this on to the team along with your request ID..

---

<div class="post-metadata">

**Author:** ![rsb](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/rsb/32/105029_2.png) [@rsb](https://forum.cursor.com/u/rsb)\
**Post date:** [November 18, 2026, 4:35pm UTC](https://forum.cursor.com/t/model-provider-flakiness-anthropic/178666/15 "2026-11-18T16:35:32Z")

</div>

Thanks, @Colin . I haven’t seen issues yet this morning, but I did see “Rate limited by model provider” errors yesterday, so your explanation makes sense.

---

<div class="post-metadata">

**Author:** ![rsb](https://sea3.discourse-cdn.com/cursor1/user_avatar/forum.cursor.com/rsb/32/105029_2.png) [@rsb](https://forum.cursor.com/u/rsb)\
**Post date:** [November 19, 2026, 4:21pm UTC](https://forum.cursor.com/t/model-provider-flakiness-anthropic/178666/16 "2026-11-19T16:21:33Z")

</div>

An ‘auto resume’ option would be very useful. I left my machine for an hour and came back to the model provider error dialog.
