Add Custom Model, no model ID can be added

Support Bug Reports
1

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

I just created an “Add Custom Models” and success for a model: “DeepSeek-V4”, after that there is no place to fill in the Model ID or any others. Attached is the picture, which also shows up an orange circle 1, whatever I click it, nothing happen.
Here is the About Cursor:
Version: 3.2.11 (Universal)
VSCode Version: 1.105.1
Commit: e9ee1339915a927dfb2df4a836dd9c8337e17cc0
Date: 2026-04-24T14:36:47.933Z
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: Darwin arm64 25.2.0

I am using MacBook M1 Pro

Steps to Reproduce

Model>Add Custom Model

Expected Behavior

add Model ID

Screenshots / Screen Recordings

微信图片_20260426081247_3614_35.png
微信图片_20260426081247_3614_35.png2992×1934 480 KB

Operating System

MacOS

Version Information

Cursor IDE> Model> Add Custom Models

Here is the About Cursor:
Version: 3.2.11 (Universal)
VSCode Version: 1.105.1
Commit: e9ee1339915a927dfb2df4a836dd9c8337e17cc0
Date: 2026-04-24T14:36:47.933Z
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: Darwin arm64 25.2.0

I am using MacBook M1 Pro

Does this stop you from using Cursor

No - Cursor works, but with this issue

3

In the model search bar, you have to input the requested model as is, then press “ADD”, it will be added at the end of the list

image
image1582×255 6.76 KB

6

it will just add another new Model, but it is supposed to fill Model ID… on the right side, I did not see them.

8

Hey thanks for the report.

The thing is that DeepSeek V4 both deepseek-v4-pro and deepseek-v4-flash uses thinking mode, which requires returning reasoning_content back to the API during multi-turn tool calls. Cursor can’t do that yet, so the DeepSeek API returns this error:

The reasoning_content in the thinking mode must be passed back to the API.

There are already a few recent reports about this on the forum:

There is also a separate feature request to add compatibility. Can you drop a like to help raise priority: Compatibility with DeepSeek model's design to return reasoning content after tool calls?

What you can do right now: