modelbenchmark.io

DeepSeek V4 Pro Fast

DeepSeek · deepseek-v4-pro-fast

Compare

Open MoE flagship with million-token context for coding and long agent runs

Specification

most-agreed values

Context
1M
Max output
66K
Released
2026-04-24
Knowledge cutoff
2025-05
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$1.91
Output
$3.83
Cache read
$0.16

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
wally$1.91$3.83$0.16—1M66K—

More from DeepSeek

most-hosted first