modelbenchmark.io

DeepSeek V4 Pro 0813 (EU)

DeepSeek · deepseek-v4-pro-0813-eu

Compare

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

Specification

most-agreed values

Context
1M
Max output
66K
Released
2026-08-13
Knowledge cutoff
—
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.75
Output
$3.50
Cache read
$0.44

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
requesty$1.75$3.50$0.44—1M66K—

More from DeepSeek

most-hosted first