modelbenchmark.io

DeepSeek V4 Flash Flex

DeepSeek · deepseek-v4-flash-flex

Compare

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

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
$0.091
Output
$0.182
Cache read
$0.0182

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
neuralwatt$0.091$0.182$0.01821M66K

More from DeepSeek

most-hosted first