modelbenchmark.io

DeepSeek V4 Flash 0731 Fast

DeepSeek · deepseek-v4-flash-0731-fast

Compare

Fast DeepSeek model for efficient chat, coding help, and agent loops

Specification

most-agreed values

Context
1M
Max output
33K
Released
2026-08-09
Knowledge cutoff
2025-05
Retires
Open weights
yes
Input
text
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.35
Output
$0.70
Cache read
$0.0875

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
merge-gateway$0.28$0.56$0.071M384K
venice$0.35$0.70$0.08751M33K

More from DeepSeek

most-hosted first