DoublewordDoubleword

Model Name

deepseek-ai/DeepSeek-V4-Pro

DeepSeek V4 Pro

  • Type: Generation
  • Capabilities: reasoning

Overview

DeepSeek V4-Pro is DeepSeek’s flagship open MoE model for advanced reasoning, coding, and agentic work. With 1.6T total parameters, 49B active parameters, and a 1M-token context window, it is designed for the hardest tasks in the V4 lineup: complex problem solving, knowledge-intensive workflows, and high-stakes coding or research use cases.

Pricing

PriorityInput Tokens (per 1M)Output Tokens (per 1M)
Realtime1$1.74$3.48
High (1h)$1.31$2.75
Standard (24h)$1.05$2.20

Playground

Open this model in the Playground.

Footnotes

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