modelbenchmark.io

DeepSeek/DeepSeek-V3.1-Terminus-Thinking

DeepSeek · deepseek-v3-1-terminus-thinking

Compare

DeepSeek chat model for instruction following, coding, and analysis

Specification

most-agreed values

Context
128K
Max output
32K
Released
2025-09-22
Knowledge cutoff
Retires
Open weights
no
Input
text
Output
text

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
qiniu-ai128K32K

More from DeepSeek

most-hosted first