Model comparison

DeepSeek V4 Flash vs DeepSeek V3

Capability radar, value bars, and side-by-side posture.

← Back to Compare

DeepSeek V4 Flash
Not scored
value score
DeepSeek V3
87
value score
DeepSeek V4 Flash ctx
DeepSeek V3 ctx
128K

Capability radar

Value · context · multimodal · openness · speed posture

Value head-to-head

  • DeepSeek V387

Attribute tape

FieldDeepSeek V4 FlashDeepSeek V3
Developer~deepseek~deepseek
Context128K
ModalitiesText, Code
OpennessOpen Weights
Speed
Price$0.27/1M in · $1.1/1M out
Value score87
SummaryDeepSeek V4 Flash is an efficiency-tier Mixture-of-Experts large language model from DeepSeek, featuring 284B total parameters with only ~13B active per token and a 1M-token context window. It is designed for fast, low-cost inference across coding, reasoning, chat, and agentic workloads.Strong open-weights MoE general model.
Open DeepSeek V4 FlashOpen DeepSeek V3