Pyyan / Open-Weight Models / DeepSeek V4.1 Flash

DeepSeek V4.1 Flash

Name: DeepSeek V4.1 Flash
Brand: DeepSeek
Price: 0.3 USD
Availability: InStock

Twice the parameters of the Flash it replaces, and cheaper to run.

currentDeepSeek ↗Verified 2026-10-20

90.6%

Terminal-Bench 2.1

Context	1Msource · as of 2026-09-13
Input ($/Mtok)	$0.3source · as of 2026-09-13 · medium confidence
Output ($/Mtok)	$1.2source · as of 2026-09-13 · medium confidence
Licence	MITsource · as of 2026-09-13
Max output	256Ksource · as of 2026-09-13
Parameters	552B total, 8B / 16B activesource · as of 2026-09-13
Released	10 Sep 2026, refreshed 17 Octsource · as of 2026-10-20
Model ID	deepseek-flashsource · as of 2026-09-13

552B total, 8B active while reading the prompt and 16B while generating, with a 1M token context
DeepSeek says it beats V4-Pro; V4-Pro requests route to it from 14 September 2026
MIT licence, native image input, and a KV cache about a quarter the size of V4-Flash's
Refreshed on 17 October as V4.1-Flash-1017, still MIT, improving on all eleven benchmarks DeepSeek published

Best for cheap agentic coding with images.