modelbenchmark.io

DeepSeek V4 Flash 0731 Fast

DeepSeek · deepseek-v4-flash-0731-fast

Compare

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

Specification

most-agreed values

Context
1M
Max output
384K
Released
2026-07-31
Knowledge cutoff
2025-05
Retires
—
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.28
Output
$1.40
Cache read
$0.07

Available from 3 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
aihubmix$0.28$1.40$0.07—1M384K—
merge-gateway$0.28$0.56$0.07—1M384K—
venice$0.35$0.70$0.0875—1M33K—

More from DeepSeek

most-hosted first