Repository navigation
DeepSeek Thinking takes an extremely long time to generate responses #34836
Description
Description
The inference speed of DeepSeek Thinking has become significantly slower.
When I first started using the tool, the response speed was much better. I cannot confirm whether recent version updates are the root cause of this performance drop.
Plugins
OpenCode Desktop for Windows
OpenCode version
v1.17.13
Steps to reproduce
- Select model DeepSeek V4 PRO to send chat requests（The go plan）
- Observe the thinking process generated by the model
- Notice the thinking section is extremely long and the response speed is much slower
Screenshot and/or share link
No response
Operating System
Windows 11
Terminal
OpenCode Desktop
Metadata
Metadata
Assignees
Labels
No labels
Activity
github-actions commentedon Jul 2, 2026
This issue might be a duplicate of existing issues. Please check:
If your issue is the same, please add a reaction or comment on the existing issue rather than opening a new one.
github-actions commentedon Sep 1, 2026
To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.