DeepSeek V3.2 API Pricing 2026

Overview

DeepSeek V3.2 was released on December 1, 2025. Pricing starts at $0.250 per million input tokens and $0.380 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$0.250

Output$0.380

per 1M tokens

Speed

Output30 tok/s

TTFT1.25s

median latency

Capabilities

Tools

Pricing Comparison

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

Current Pricing (per 1M tokens)

11 models

Provider	Model	Input $/M	Output $/M	Context	Actions
DS Deepseek	deepseek-v3.2	$0.250	$0.380	163,840	Try
DS Deepseek	deepseek-v3.2-exp	$0.210	$0.320	163,840	Try
DS Deepseek	deepseek-v3.1-terminus	$0.210	$0.790	163,840	Try
QW Qwen	qwen3-coder	$0.220	$0.950	262,144	Try
TN Tngtech	deepseek-r1t2-chimera	$0.250	$0.850	163,840	Try
IC Inception	mercury	$0.250	$1.000	128,000	Try
IC Inception	mercury-coder	$0.250	$1.000	128,000	Try
BY Bytedance-seed	seed-1.6	$0.250	$2.000	262,144	Try
TN Tngtech	tng-r1t-chimera	$0.250	$0.850	163,840	Try
O OpenAI	gpt-5.1-codex-mini	$0.250	$2.000	400,000	Try
O OpenAI	gpt-5-mini	$0.250	$2.000	400,000	Try

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

Compare Providers

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

10

Providers

$0.250

Cheapest Input/M

$0.380

Cheapest Output/M

Chutes

Best Price

Provider Pricing

10 models

Provider	Input $/M	Output $/M	Uptime
C Chutes Best Price	$0.250	$0.380	99.7%
A AtlasCloud	$0.260	$0.380	93.0%
D DeepInfra	$0.260	$0.390	99.9%
N Novita	$0.269	$0.400	99.9%
P Phala	$0.270	$0.400	97.3%
S SiliconFlow	$0.270	$0.420	99.9%
P Parasail	$0.280	$0.450	95.1%
DeepSeek	$0.280	$0.420	81.8%
B BaseTen	$0.300	$0.450	-
Google	$0.560	$1.680	99.9%

Provider pricing data sourced from OpenRouter and Helicone

Cost vs. Quality

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

X-axis:

Y-axis:

Loading chart...

DeepSeek V3.2

Other models

Detailed Benchmark Scores

Intelligence

31.8 (83th pct)

Coding

33.2 (87th pct)

Math

59.0 (70th pct)

MMLU Pro

83.7 (86th pct)

GPQA

75.1 (81th pct)

LiveCodeBench

59.3 (72th pct)

AIME

-

Aider

-

Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try DeepSeek V3.2

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test DeepSeek V3.2 directly in your browser.

Open Playground