Has anyone noticed performance issues with Opus 4.6 (Max Mode) recently?

Discussions
, ,
1

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

Has anyone noticed performance issues with Opus 4.6 (Max Mode) recently?

Over the past few days, it has become extremely slow on my end. Responses take much longer than usual, even for relatively simple prompts, which is starting to impact productivity.

It also seems like this might not be an issue from Anthropic’s side, so I’m wondering if others are experiencing the same behavior within Cursor specifically.

Any insights or similar experiences?

Steps to Reproduce

Has anyone noticed performance issues with Opus 4.6 (Max Mode) recently?

Over the past few days, it has become extremely slow on my end. Responses take much longer than usual, even for relatively simple prompts, which is starting to impact productivity.

It also seems like this might not be an issue from Anthropic’s side, so I’m wondering if others are experiencing the same behavior within Cursor specifically.

Any insights or similar experiences?

Operating System

Windows 10/11

Version Information

Version: 2.6.22 (user 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 10.0.19045

Does this stop you from using Cursor

Sometimes - I can sometimes use Cursor

1 Like
5

I am having the same issue, was okay 2 hours ago and now responses come in at 3-4 tokens per second, painfully slow even on a small <50k context window

2 Likes
6

Hey, a few others have mentioned similar things recently. There’s a related thread here: Opus 4.6 was fun for 1 week..... why?!

One thing to keep in mind: Opus 4.6 in Max Mode uses extended thinking, which means the model does extra reasoning steps before producing the final output. This naturally increases response time compared to non-Max or non-thinking variants. That said, if it feels noticeably slower than before, we’d want to look into it.

To dig deeper, I’ll need:

  1. Request IDs from the slow sessions. Top right corner of the chat > Copy Request ID. Even 2 to 3 examples would help.
  2. How long are the responses taking roughly? Are we talking 30s, 1min+?
  3. Are you seeing the same slowness with other models, for example Sonnet 4.6 or non-Max Opus?

A couple of things to try in the meantime:

  • Start a fresh chat for new tasks instead of continuing long threads. Accumulated context can increase latency significantly.
  • Try Opus 4.6 without Max Mode to see if the speed difference is drastic.

Share those request IDs and I can check what’s happening on our end.

7

It’s happening across multiple conversations. I was using another program, and it works fine—so it seems the issue is with Cursor.
eff745a1-9158-4c52-98ad-65c091b1c75d

1 Like
8

Same issue here , any workaround with different model ?

10

@Abdelrahman_Mohamed @Alexander_Jacob_Yue It looks like there was an issue with Anthropic APIs (Opus included) around the time of your report.

@heavy_user Do you have a Request ID that you can share?

12

@Colin

3fda5e38-f237-4da4-8701-021faf0f5bd3

13

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

I am a Cursor Ultra plan subscriber who exclusively uses the Opus 4.6 model for all tasks. I have observed a severe, progressive degradation in response speed as my API usage percentage increases, while other models remain fully responsive.

Steps to Reproduce

  1. Subscribe to Cursor Ultra plan and use Opus 4.6 as the primary model for all development tasks.
  2. Monitor API usage percentage in the Cursor dashboard.
  3. Observe response speed as usage approaches 90%, then 95%, and near 100%.
  4. Compare response speed by switching to other available models at the same usage level.

Operating System

MacOS

Version Information

Version: 2.6.22
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: Darwin arm64 25.4.0

Does this stop you from using Cursor

No - Cursor works, but with this issue

14

@ahhxyz Do you have a Request ID that you can share?

15

its not an issue from anthropic side..i can use claude code and claude code just fine with opus4.6 extended thinking…the bottleneck is on cursor side where the processing and performance is choked ..maybe scaling issues etc

16

also nothing yet on cursor status page or any kind of degradation notification….that page should have been updated 4 hours ago

17

Where does the bug appear (feature/product)?

Cursor CLI

Describe the Bug

When I use Cursor to call the Opus 4.6 model, the response is extremely, extremely, extremely slow.
Even a very simple question now takes more than 20 minutes to process. It used to respond smoothly and fluently before. What is causing this?

Steps to Reproduce

When I use Cursor to call the Opus 4.6 model, the response is extremely, extremely, extremely slow.
Even a very simple question now takes more than 20 minutes to process. It used to respond smoothly and fluently before. What is causing this?

Operating System

MacOS

Version Information

Version: 2.6.22
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: Darwin arm64 25.3.0

Does this stop you from using Cursor

No - Cursor works, but with this issue

20

After upgrading to the most expensive plan I’m running into the problem that the Opus 4.6 model failed three times to generate a plan for me. It is pretty disappointing because this is an expensive model, it did all the work but never finished generating a proper plan, so it just burned tokens for nothing. Also, it was very slow to generate anything.

Is there anything that can be done about it?

Request ID: c4fb6192-0be1-4064-8492-964becf5eae8

23

Hey all!

We apologize for the disruption. We’re currently investigating latency and performance issues. We observed a spike in Opus-related latency that appears to have largely subsided, but we’re continuing to monitor the situation and investigate any remaining reports of slowness. Thank you for your patience.

1 Like
24

I’m back, you guys are not updating your https://status.cursor.com/ website with this?

25

This is still very slow. just a few tokens per second. I think I can type faster than Cursor/Opus now. I have restarted, logged out and back in. The slowness remains.

26

I can confirm Opus 4.6 performance has degraded on my end across all chats. Extremely slow across all chats. Other models are not affected. Anthropic did have issues with Claude over the past 24 hours, but performance still remains degraded on my end.

27

@midaz This should be resolved by now, if you’re still seeing the same issue can you send us a request Id (with Share Data enabled before making the request please)

1 Like
28

How do I enable shared data? Here is the request id fcdb942d-ba84-4ca7-8034-6b15c4ad0b8f. It was generating more this time, then suddenly it became super slow and stopped…again. :frowning:

29

It seems massively improved now, thank you for the update!