DeepSeek V3.2 Cost Calculator

DeepSeek V3.2 is an open-weight MoE model with frontier-tier reasoning at fraction of US model prices. 164K context. Strong on Chinese and code. Output token cost ($0.40/1M) is among the cheapest of any production-capable model.

Input

$0.28

per 1M tokens

Output

$0.40

per 1M tokens

Context window

164K

tokens

Released

2025-09

Cutoff 2025-07

Model

≈ Estimated tokenizer·$0.28 in·$0.40 out (per 1M)

Quick start with a use case

Input tokens

Output tokens

Total cost per call$0.000480

Input$0.000280

Output$0.000200

Cost comparison

Standard

$0.000480

With Caching

Not supported

With Batch

Not supported

Run DeepSeek V3.2 on Novita AI

Hosted API for 200+ open models — pay-as-you-go, no subscription.

Try Novita AI

Affiliate link — we may earn a commission at no extra cost to you.

Detailed pricing

DeepSeek V3.2 pricing breakdown

All pricing dimensions including caching and batch discounts.

Type	Price (per 1M tokens)	Note
Input	$0.2800	Standard input tokens
Output	$0.4000	Generated output tokens

Run DeepSeek V3.2 on Novita AI

Hosted API for 200+ open models — pay-as-you-go, no subscription.

Try Novita AI

Affiliate link — we may earn a commission at no extra cost to you.

Last verified 2026-08-01 · DeepSeek official pricing · ⚠️ Spotted a wrong price? Report in 30s →

How it compares

DeepSeek V3.2 vs alternatives

Single-call cost (1000 input + 500 output tokens) ranked from cheapest.

Model	Per call	vs DeepSeek V3.2
DeepSeek V3.2 DeepSeek · this page	$0.000480	—
DeepSeek V4-Flash DeepSeek	$0.000280	−42%
GPT-5.6 Luna OpenAI	$0.000800	+67%
GPT-5 mini OpenAI	$0.001250	+160%
Mistral Large 3 Mistral	$0.001250	+160%
Gemini 3.5 Flash Lite Google	$0.001550	+223%

Recommended use

When to choose DeepSeek V3.2

DeepSeek V3.2 shines for general-purpose tasks, code generation and review, mathematical problem-solving, and complex multi-step reasoning. Token counts are estimated within ~10-20% margin.

✓Context window of 164K tokens handles typical chat and document tasks.

✓Prompt caching available — significant savings for repeated system prompts.

✓Tool / function calling supported.

FAQ

Frequently asked questions

DeepSeek V3.2 costs $0.28 per 1M input tokens and $0.40 per 1M output tokens. A typical chat call (1000 input + 500 output tokens) costs approximately $0.0005. Use the calculator above to estimate your specific use case.