PyyanThe AI Index

Pyyan / Compare / DeepSeek V4.1 Flash vs DeepSeek V4 Flash Vision Exp

DeepSeek V4.1 Flash vs DeepSeek V4 Flash Vision Exp

2 of 5

Open-Weight Models · verified 13 Sept 2026

DeepSeek V4.1 FlashDeepSeekcurrent
DeepSeek V4 Flash Vision ExpDeepSeekdeprecated
3 slots left
SpecificationDeepSeek V4.1 FlashDeepSeek V4 Flash Vision Exp
SummaryTwice the parameters of the Flash it replaces, and cheaper to run.Experimental, says so in the name, and shipped anyway.
Context1M128K
Input ($/Mtok)$0.3$0.44
Output ($/Mtok)$1.2$1.32
LicenceMITOpen weights
Max output256K32K
Parameters552B total, 8B / 16B activeNot published
Released10 Sep 202621 Aug 2026
Model IDdeepseek-flashdeepseek-ai/DeepSeek-V4-Flash-Vision-Exp
CategoryOpen-Weight ModelsOpen-Weight Models
OfficialDeepSeek ↗—

Highlighted rows are where these differ.

DeepSeek V4.1 Flash

  • 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

Best for cheap agentic coding with images.

Full spec sheet →

DeepSeek V4 Flash Vision Exp

  • Retired 10 September 2026: requests now route to DeepSeek V4.1 Flash
  • Was DeepSeek's first Flash tier with image input

Best for cheap multimodal trials.

Full spec sheet →