DeepSeek/DeepSeek-V3.2-Exp-Thinking

Name: DeepSeek/DeepSeek-V3.2-Exp-Thinking
Brand: deepseek
SKU: deepseek/deepseek-v3.2-exp-thinking

deepseek·deepseek/deepseek-v3.2-exp-thinking·GA·Closed·deepseek-thinking series

DeepSeek chat model for instruction following, coding, and analysis

Specs & pricing

Input / output per 1M tokens

Reference priceNanoGPT

$0.28 / $0.42

Blended $0.32 · Cache read $0.14

Lowest paidNanoGPTGateway

$0.28 / $0.42

Blended $0.32

Context

163,840

Output limit

65,536

Knowledge cutoff

—

Released / updated

2025-09-29 / 2025-09-29

Capabilities

✓ ReasoningTool useStructured output✓ TemperatureAttachments

⚠ Providers report capability flags inconsistently

Modalities

Text

Available at 2 providers1 with public prices

Priced only

Provider	Tier	Input	Output	Cache read	Cache write	Context	Output limit	Status
NanoGPT	Gateway	$0.28	$0.42	$0.14	—	163,840	65,536
Qiniu	Gateway	—	—	—	—	128,000 ⚠	32,000	hostTable.undisclosed

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

Upstream provides no control info

2 / 2 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Input tokens / month

Output tokens / month

Cache hit rate

Common scenarios

1NanoGPT$60.20

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended

DeepSeek/DeepSeek-V3.2-Exp-Thinking

Specs & pricing

Available at 2 providers1 with public prices

Reasoning control

Your usage cost

Price historyone sample accumulated per data sync

Related models

DeepSeek/DeepSeek-V3.2-Exp-Thinking

Specs & pricing

Available at 2 providers1 with public prices

Reasoning control

Your usage cost

Price historyone sample accumulated per data sync

Related models