modelbenchmark.io

DeepSeek V4.1 Flash 1017 Ultra-fast

DeepSeek · deepseek-v4-1-flash-1017-ultrafast

Compare

October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding

Specification

most-agreed values

Context
1M
Max output
384K
Released
2026-10-17
Knowledge cutoff
2025-05
Retires
—
Open weights
yes
Input
text, image
Output
text

Price

US dollars per million tokens · most-agreed

Input
$2.40
Output
$9.60
Cache read
$0.048

Available from 6 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
abliteratedllm$2.16$8.64$0.0432—1M1M—
fireworks_ai$2.40$9.60$0.048—1M393K—
fireworks-ai · accounts$2.40$9.60$0.048—1M384K—
kilo$2.40$9.60$0.048—1M1M—
vercel$2.40$9.60$0.048—1M1M—
venice$3.00$12.00$0.06—1M131K—

More from DeepSeek

most-hosted first