DoublewordDoubleword

Model Name

deepseek-ai/DeepSeek-V4-Flash

DeepSeek V4 Flash

  • Type: Generation
  • Capabilities: reasoning

Overview

DeepSeek V4-Flash is a general-purpose open MoE model built for reasoning, tool use, and long-context work. With 284B total parameters, 13B active parameters, and a 1M-token context window, it brings the core strengths of the V4 family into a more compact package. It’s a strong fit for chat, structured generation, document-scale analysis, and agentic workflows that need broad capability across everyday tasks.

Pricing

PriorityInput Tokens (per 1M)Output Tokens (per 1M)
Realtime1$0.14$0.28
High (1h)$0.10$0.20
Standard (24h)$0.07$0.14

Playground

Open this model in the Playground.

Footnotes

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