PyyanThe AI Index

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

DeepSeek V4 Flash Vision Exp vs DeepSeek V4.1 Flash

2 of 5

Open-Weight Models · verified 13 Sept 2026

DeepSeek V4 Flash Vision ExpDeepSeekdeprecated
DeepSeek V4.1 FlashDeepSeekcurrent
3 slots left
SpecificationDeepSeek V4 Flash Vision ExpDeepSeek V4.1 Flash
SummaryExperimental, says so in the name, and shipped anyway.Twice the parameters of the Flash it replaces, and cheaper to run.
Context128K1M
Input ($/Mtok)$0.44$0.3
Output ($/Mtok)$1.32$1.2
LicenceOpen weightsMIT
Max output32K256K
ParametersNot published552B total, 8B / 16B active
Released21 Aug 202610 Sep 2026
Model IDdeepseek-ai/DeepSeek-V4-Flash-Vision-Expdeepseek-flash
CategoryOpen-Weight ModelsOpen-Weight Models
Official—DeepSeek ↗

Highlighted rows are where these differ.

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 →

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 →