DeepSeek V4 Flash 0731 (Thinking)

Name: DeepSeek V4 Flash 0731 (Thinking)
Brand: deepseek
SKU: deepseek/deepseek-v4-flash-0731-thinking

deepseek·deepseek/deepseek-v4-flash-0731-thinking·GA·Open weights·deepseek-flash series·NEW

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

Specs & pricing

Input / output per 1M tokens

Reference priceNanoGPT

$0.05 / $0.16

Blended $0.078 · Cache read $0.013

Lowest paidNanoGPTGateway

$0.05 / $0.16

Blended $0.078

Context

1,000,000

Output limit

131,072

Knowledge cutoff

2025-05

Released / updated

2026-07-31 / 2026-07-31

Capabilities

✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments

Modalities

Text

Available at 1 providers1 with public prices

Priced only

Provider	Tier	Input	Output	Cache read	Cache write	Context	Output limit	Status
NanoGPT deepseek/deepseek-v4-flash-0731:thinking	Gateway	$0.05	$0.16	$0.013	—	1,000,000	131,072

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = noneeffort = loweffort = higheffort = max

Your usage cost

Input tokens / month

Output tokens / month

Cache hit rate

Common scenarios

1NanoGPT$13.56

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended

DeepSeek V4 Flash 0731 (Thinking)

Specs & pricing

Available at 1 providers1 with public prices

Reasoning control

Your usage cost

Price historyone sample accumulated per data sync

Related models

DeepSeek V4 Flash 0731 (Thinking)

Specs & pricing

Available at 1 providers1 with public prices

Reasoning control

Your usage cost

Price historyone sample accumulated per data sync

Related models