DeepseekDeepSeek V3Tool use

DeepSeek V3.2 Speciale pricing

DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement learning... Below you will find 2 current rows with input and output dollars per million. Right now the lowest input is $0.400 and the lowest output is $1.20.

164K context·2 providers·verified Apr 7, 2026
Best input$0.400per 1M tokens · Openrouter
Best output$1.20per 1M tokens · Openrouter

Pricing across providers

Use this table to read DeepSeek V3.2 Speciale list prices. We show 2 sources right now. Lowest input in the grid: Openrouter. The chart below the table helps when output prices are much higher than input prices.

O
Openrouter
Input / 1M
$0.400
Output / 1M
$1.20
A
Azure
Input / 1M
$0.580
Output / 1M
$1.68

Input vs output · per provider

Cost calculator

Use this block to stress test DeepSeek V3.2 Speciale cost without a spreadsheet. All estimates come from public list rates in this page.

Provider

In: $0.400/M·Out: $1.20/M

0.040000¢ / req

0.060000¢ / req

Daily
$10
Monthly
$300
Annual
$3.6K

Model specifications

Quick spec sheet for DeepSeek V3.2 Speciale before you dive back into pricing. Family: DeepSeek V3. Reported under Deepseek.

Context window
163,840 tokens
Max output
163,840 tokens
Vision (images)
No
Tool / function calling
Yes
Streaming
No
Released
Dec 2025
Primary provider
Deepseek
Model family
DeepSeek V3

Compare DeepSeek V3.2 Speciale

Open a pair page to see DeepSeek V3.2 Speciale next to another model with a shared provider matrix. 6 shortcuts below.

Frequently asked questions

Read these after the table if you want plain language around DeepSeek V3.2 Speciale rates. The short model note from our index: DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales p...

Yes. DeepSeek V3.2 Speciale is available on Openrouter, Azure.

Also from Deepseek

Other models by Deepseek with live pricing in our catalog.