Flash — fastest and cheapest, lighter reasoningOpen Weights

DeepSeek V4 Flash 0731 Pricing

DeepSeek · deepseek-deepseek-v4-flash-0731

ShareX Facebook LinkedIn

Input / 1M tokens

$0.060

Output / 1M tokens

$0.120

Context window

1,310,720 tokens

≈ 1,748 pages of text

Max output

943,718 tokens

What it costs in practice

Typical request (1,200 in + 400 out tokens)$0.0001

1,000 requests / month$0.12/mo 10,000 requests / month$1.20/mo 100,000 requests / month$12.00/mo

Estimate your own workloadOpens the calculator with DeepSeek V4 Flash 0731 preloaded — adjust volume and token counts there.

Price history

List price per 1M tokens since we started tracking in Jul 2026. Each step marks a price change — hover a point for the exact date and rate.

What it excels at

Supports 1M-token contexts and 384k output at very low per-token cost, suitable for high-volume batch processing and long-document tasks.

The business tradeoff

Flash designation indicates lighter optimization; complex multi-step reasoning trails closed flagships and output quality depends on deployment configuration.

Same tier from other providers

GPT-5.4 NanoOpenAI$0.0007/ typical request Claude Haiku 4.5Anthropic$0.0032/ typical request Gemini 3.5 FlashGoogle$0.0054/ typical request

Head-to-head

DeepSeek V4 Flash 0731 vs GPT-5.4 Nano →DeepSeek V4 Flash 0731 vs Claude Haiku 4.5 →DeepSeek V4 Flash 0731 vs Gemini 3.5 Flash →

Vendor list rates, as of Sep 14, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.