Skip to content
LLM Pricing Calc
Pricing last verified

DeepSeek V4 Pro pricing calculator

DeepSeek's flagship API model with very cheap cache hits.

Input
$1.32 / 1M
Cached input
$0.044 / 1M
Output
$3.96 / 1M
Context window
1M
Batch API
No
Reasoning
Yes

Official pricing ↗

NotePeak price shown. DeepSeek offers 50% off during off-peak hours.

Workload

Quick presets

1,000 tokens ≈ 750 English words.

Pro / Agent mode

Caching, batch, multi-turn loops, reasoning tokens

Cost comparison

Cheapest / month

$87.46

Grok 4.3

Most expensive / month

$108.42

DeepSeek V4 Pro

Tokens / request

1.5K in

400 out (cheapest model)

Estimated cost per model
Remove
Grok 4.3CheapestxAI · $1.25 / $2.50$0.00287$2.88$87.46$1,049
Claude Haiku 4.5Anthropic · $1.00 / $5.00$0.0035$3.50$106.47$1,278
GPT-6.1 TerraOpenAI · $1.00 / $5.00$0.0035$3.50$106.47$1,278
DeepSeek V4 ProDeepSeek · $1.32 / $3.96$0.00356$3.56$108.42$1,301

Monthly = daily × 30.42. Prices are list prices for the standard context tier. Long-context surcharges, regional pricing and taxes are not included.Official pricing: DeepSeek ↗ · Anthropic ↗ · OpenAI ↗ · xAI ↗

What DeepSeek V4 Pro costs for common workloads

Monthly estimates using the presets above, at list price.

WorkloadPer request / sessionMonthlyYearly
Small Chatbot1K chats/day, short prompts$0.00198$60.23$722.70
RAG App5K queries/day, 4K-token retrieved context$0.00482$733.49$8,801
Coding Agent200 sessions/day × 25 turns$0.4083$2,484$29,809
Enterprise Scale250K requests/day, batched$0.00408$31,019$372,191

Official pricing ↗ (DeepSeek) · API model ID deepseek-v4-pro

DeepSeek V4 Pro pricing FAQ

How much does DeepSeek V4 Pro cost per 1M tokens?

DeepSeek V4 Pro costs $1.32 per 1M input tokens and $3.96 per 1M output tokens. Cached input is $0.044 per 1M. Prices were last verified on Nov 21, 2026.

How much does one DeepSeek V4 Pro request cost?

A typical request with 1,000 input tokens and 500 output tokens costs about $0.0033. At 1,000 such requests per day that is $100.39 per month.

Does DeepSeek V4 Pro support prompt caching?

Yes. Cached input tokens cost $0.044 per 1M, 97% less than regular input. Turn on Pro mode above to model your cache hit rate.

Is there a Batch API discount for DeepSeek V4 Pro?

No 50% batch discount is listed for DeepSeek V4 Pro. DeepSeek offers off-peak discounts instead.

What is the context window of DeepSeek V4 Pro?

DeepSeek V4 Pro supports up to 1M tokens of context and up to 375K output tokens per response. Peak price shown. DeepSeek offers 50% off during off-peak hours.

Is DeepSeek V4 Pro cheaper than Claude Haiku 4.5?

For a 1,000-in / 500-out request, DeepSeek V4 Pro costs $0.0033 and Claude Haiku 4.5 costs $0.0035, so DeepSeek V4 Pro is 6% cheaper. Quality, speed and caching behaviour differ, so compare on your own workload above.

More AI cost tools