← All models
DeepSeekCurrent

DeepSeek V4 Flash

DeepSeeks fast, efficient, and economical model. 284B total / 13B active params with 1M context. Supports both non-thinking and thinking modes.

Context Window

1049K tokens

≈ 786K words

Input Price

$0.14

per 1M tokens

Output Price

$0.28

per 1M tokens

Released

April 2026

Capabilities

Tool / Function calling

Best for

Fast everyday tasks, agentic workflows, and high-throughput workloads on a budget

Strengths

  • Speed
  • Cost efficiency
  • Long context
  • Tool calls
  • Thinking mode

API identifier

deepseek-v4-flash

Compare DeepSeek V4 Flash side-by-side with any other model

Compare models →