Deepseek

DeepSeek V3.2 Speciale API Pricing 2026

Compare pricing, benchmarks, and providers for DeepSeek V3.2 Speciale. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

DeepSeek V3.2 Speciale was released on December 1, 2025. Pricing starts at $0.270 per million input tokens and $0.400 per million output tokens. The model supports a context window of up to 164K tokens. API access is available through Deepseek.

Context Window
164K
tokens
Pricing
Input$0.270
Output$0.400
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
ReasoningToolsCaching

DeepSeek V3.2 Speciale is priced at $0.270 per million input tokens and $0.400 per million output tokens. It has a context window of 163,840 tokens.

Pricing Comparison

Compare DeepSeek V3.2 Speciale with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.270
$0.400
—
—
—
163,840
Try
$0.250
$0.500
—
—
—
131,072
Try
$0.250
$1.000
—
—
—
163,840
Try
$0.250
$1.250
—
—
—
200,000
Try
$0.250
$0.750
—
—
—
128,000
Try
$0.250
$1.500
—
—
82.2
1,048,576
Try
$0.260
$0.780
—
—
—
1,000,000
Try
$0.260
$0.780
—
—
—
1,000,000
Try
$0.260
$1.560
—
—
—
1,000,000
Try
$0.260
$0.900
—
—
—
262,144
Try
$0.270
$0.950
—
—
—
196,608
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

DeepSeek V3.2 Speciale is available from multiple providers with different pricing and availability.

No multi-provider data available for this model

This model may only be available from a single provider

Community Rankings

How does DeepSeek V3.2 Speciale perform? Vote based on your experience.

Cost vs. Quality

Compare DeepSeek V3.2 Speciale's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Other models

Try DeepSeek V3.2 Speciale

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test DeepSeek V3.2 Speciale directly in your browser.

Open Playground

Frequently Asked Questions

DeepSeek V3.2 Speciale costs $0.000270 per 1,000 input tokens and $0.000400 per 1,000 output tokens.
We compare DeepSeek V3.2 Speciale with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Deepseek Models

See pricing for all Deepseek models.

View all Deepseek models →