DeepSeek · current

DeepSeek V4 Flash API pricing

High-throughput DeepSeek V4 model with unusually low cache-hit pricing.

Input / million
$0.1400
Cached input / million
$0.0028
Output / million
$0.2800
Context window
1,000,000

Example cost

A request with 10,000 input tokens and 2,000 output tokens costs approximately $0.00196 at the recorded standard rate.

  • 10,000 standard input tokens / 1,000,000 × $0.14
  • 0 cached tokens / 1,000,000 × $0.0028
  • 2,000 output tokens / 1,000,000 × $0.28

Pricing rules and limitations

Cache-hit and cache-miss input rates are separate; supports thinking and non-thinking modes.

Price history

EffectiveUntilInputOutputStatus
2026-07-01Current / scheduled$0.1400$0.2800current