DoublewordDoubleword

Model Name

deepseek-ai/DeepSeek-V4-Flash-0731

DeepSeek V4 Flash 0731

  • Type: Generation
  • Capabilities: reasoning

Overview

DeepSeek V4-Flash 0731 is the latest release in DeepSeek’s V4 family and delivers a major upgrade for agent use cases. With 284B total parameters, 13B activated per token, and a 1M-token context window, it combines efficient inference with substantially stronger results than V4-Flash Preview and V4-Pro Preview.

Pricing

PriorityInput Tokens (per 1M)Output Tokens (per 1M)
Realtime1$0.09$0.18
Async$0.07$0.14
Batch (24h)$0.05$0.09

Playground

Open this model in the Playground.

Footnotes

  1. Realtime availability is limited. Doubleword is primarily a batch API.