modelbenchmark.io

DeepSeek V4.1 Flash 0910 Uncensored Thinking

DeepSeek · deepseek-v4-1-flash-0910-uncensored

Compare

dealignai's September 10 uncensored release of DeepSeek V4.1 Flash. This dated model stays on the original checkpoint, with text input, optional reasoning, and tool calling.

Specification

most-agreed values

Context
524K
Max output
33K
Released
2026-10-27
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.33
Output
$1.32
Cache read
$0.0083

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
nano-gpt$0.33$1.32$0.0083—524K33K—
nano-gpt · thinking$0.33$1.32$0.0083—524K33K—

More from DeepSeek

most-hosted first