The deepseek-v4-pro api cannot be used normally

Support Bug Reports
,
1

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

Provider returned error: {“error”:{“message”:“The reasoning_content in the thinking mode must be passed back to the API.”,“type”:“invalid_request_error”,“param”:null,“code”:“invalid_request_error”}}

Steps to Reproduce

set deepseek-v4-pro api.
set deepseek-v4-pro api key.
prompt: Ask him to write a plan proposal document.

Screenshots / Screen Recordings

PixPin_2026-04-26_06-02-19.png
PixPin_2026-04-26_06-02-19.png875×174 6.02 KB

Operating System

Windows 10/11

Version Information

Version: 3.2.11 (user setup)
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: Windows_NT x64 10.0.26200

Does this stop you from using Cursor

Sometimes - I can sometimes use Cursor

2 Likes
4

Same issue, simply can’t be used

6

Hey, yeah, I’ve seen this issue. DeepSeek V4, same as R1 and Kimi K2.5, requires reasoning_content from previous assistant responses to be sent back to the API in multi-turn requests that include tool calls. On the BYOK path, Cursor currently doesn’t store this field for the DeepSeek API directly, so DeepSeek returns 400.

Until we have a fix on our side, you can use a community proxy that sits between Cursor and DeepSeek and fills in the missing field: GitHub - yxlao/deepseek-cursor-proxy: Fixes reasoning_content issue of DeepSeek V4, supprting deepseek-v4-pro and deepseek-v4-flash · GitHub

Related thread with the same root cause and a workaround discussion: Compatibility with DeepSeek model's design to return reasoning content after tool calls?