DeepSeek V4 Flash Vision Exp

DeepSeek🇨🇳 China
active
Context window1000K tokens
Input / 1M tokens$0.22
Output / 1M tokens$0.66

Version History

V4 Flash Vision Expminor

DeepSeek released an experimental vision-enabled variant of V4 Flash 0731, adding image understanding capabilities while matching the base model's text performance. The sparse MoE model uses 13B active parameters out of 284B total with a 1M token context window.

Coverage