Model comparison
DeepSeek V4 Flash vs DeepSeek V3
Capability radar, value bars, and side-by-side posture.
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
| Field | DeepSeek V4 Flash | DeepSeek V3 |
|---|---|---|
| Developer | ~deepseek | ~deepseek |
| Context | — | 128K |
| Modalities | Text, Code | |
| Openness | — | Open Weights |
| Speed | — | — |
| Price | — | $0.27/1M in · $1.1/1M out |
| Value score | — | 87 |
| Summary | DeepSeek 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. |