modelbenchmark.io

deepseek-ai/DeepSeek-V4.1-Flash-Fast

DeepSeek · deepseek-v4-1-flash-fast

Compare

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

Specification

most-agreed values

Context
1M
Max output
33K
Released
2026-09-10
Knowledge cutoff
2025-05
Retires
—
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$0.60
Output
$2.40
Cache read
$0.14

Available from 2 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
baseten$0.60$2.40$0.14—1M33K—
baseten · deepseek-ai$0.60$2.40——1M33K—

More from DeepSeek

most-hosted first