modelbenchmark.io

Deepseek V4 Flash

DeepSeek · deepseek-4-flash

Compare

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

Specification

most-agreed values

Context
1M
Max output
384K
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
$0.14
Output
$0.28
Cache read
$0.028

Quality

1 benchmark · 1 source

Composite
9th
percentile of 344 scored models
Rank
315 / 344
±0.56 sd
Evidence
1 × 1
too little evidence to place with confidence
Effort range
—
one configuration only
general6th1/1 bench

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
LiveBench66.1default · 23 runsLiveBench2026-06-25

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 1 host

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
digitalocean$0.14$0.28$0.028—1M384K—

Price history

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

DateHostField$/M
2026-09-02digitaloceanCache read$0.0168
2026-09-22digitaloceanCache read$0.028
2026-09-02digitaloceanInput$0.0679
2026-09-22digitaloceanInput$0.14
2026-09-02digitaloceanOutput$0.168
2026-09-22digitaloceanOutput$0.28

Other listings of this model

this page is one of them

The corpus files Deepseek V4 Flash under several keys. This page is the deepseek-4-flash listing. The full record — every host, every price and every benchmark score — is on the main Deepseek V4 Flash page.

More from DeepSeek

most-hosted first