Home/DeepSeek/DeepSeek V4-Pro

DeepSeek pricing

DeepSeek V4-Pro API Pricing & Cost Calculator

DeepSeek V4-Pro is priced at $1.32 input / $3.96 output per 1M tokens with a 1M context window and 393K max output, and cached input at $0.04/1M. A 1,000-in / 500-out call costs $0.00330.

Input

$1.32

per 1M tokens

Output

$3.96

per 1M tokens

Context window

1000K

tokens

Released

—

Cutoff —

Model

≈ Estimated tokenizer·$1.32 in·$3.96 out (per 1M)

Quick start with a use case

Input tokens

Output tokens

Total cost per call$0.003300

Input$0.001320

Output$0.001980

Cost comparison

Standard

$0.003300

With Caching

$0.002662

Save 19% ↓

With Batch

Not supported

Run DeepSeek V4-Pro 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 V4-Pro pricing breakdown

All pricing dimensions including caching and batch discounts.

Type	Price (per 1M tokens)	Note
Input	$1.3200	Standard input tokens
Output	$3.9600	Generated output tokens
Cached input	$0.0440	Reused prompt content

Run DeepSeek V4-Pro 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 2026-08-24 · DeepSeek official pricing · ⚠️ Spotted a wrong price? Report in 30s →

How it compares

DeepSeek V4-Pro vs alternatives

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

Model	Per call	vs V4-Pro
DeepSeek V4-Pro DeepSeek · this page	$0.003300	—
DeepSeek V3.2 DeepSeek	$0.000480	−85%
GPT-5.6 Luna OpenAI	$0.000800	−76%
Gemini 3.1 Flash Lite Google	$0.001000	−70%
DeepSeek V4-Flash DeepSeek	$0.001100	−67%
GPT-5 mini OpenAI	$0.001250	−62%

Recommended use

When to choose DeepSeek V4-Pro

DeepSeek V4-Pro shines for complex multi-step reasoning, code generation and review, general-purpose tasks, and long documents and large codebases. Token counts are estimated within ~10-20% margin.

✓Context window of 1000K tokens handles entire codebases or book-length documents.

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

✓Tool / function calling supported.

FAQ

Frequently asked questions

DeepSeek V4-Pro costs $1.32 per 1M input tokens and $3.96 per 1M output tokens. A typical chat call (1000 input + 500 output tokens) costs approximately $0.0033. Use the calculator above to estimate your specific use case.

DeepSeek V4-Pro supports a 1000K token context window with a max output of 393,216 tokens.

Yes. Cached input is priced at $0.04 per 1M tokens — 97% cheaper than uncached input. This is especially valuable for repeated system prompts, long-context retrieval, and chat threads with shared history.

Token counts for DeepSeek V4-Pro are estimated from character ratios (~10-20% margin). Cost calculations use prices verified on 2026-08-24. For final billing accuracy, always verify with DeepSeek's usage dashboard.

DeepSeek V4-Pro does not currently support fine-tuning. Consider another model in the DeepSeek family if fine-tuning is required.