modelbenchmark.io

DeepSeek V4.1 Flash

DeepSeek · deepseek-flash

Compare

DeepSeek V4.1 Flash model for reasoning and agentic coding

Specification

deepseek listing

Context
1M
Max output
384K
Released
2026-09-10
Knowledge cutoff
2025-05
Retires
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · deepseek list price

Input
$0.15
Output
$0.60
Cache read
$0.003
Cache write
free

Available from 5 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
deepseekvendor
$0.15
$0.30
$0.60
$1.20
$0.003
$0.006
free1M
384K
393K
302ai$0.15$0.60$0.0031M384K
kilo$0.15$0.60$0.0151M944K
openrouter$0.15$0.60$0.0151M944K
vancine$0.24$0.96$0.00481M384K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-11deepseekCache read$0.003
2026-09-13deepseekCache read$0.003
2026-09-11deepseekInput$0.15
2026-09-13deepseekInput$0.15
2026-09-11deepseekOutput$0.60
2026-09-13deepseekOutput$0.60

More from DeepSeek

most-hosted first