DeepSeek V4 Pro API pricing

DeepSeek V4 Pro costs $1.32 per million input tokens and $3.96 per million output tokens. A typical chatbot request (about 1,500 input + 400 output tokens) costs $0.0037, or $3.66 per 1,000 requests.

0 characters0 words0 tokens (GPT o200k)

ModelInput tokensPrice / 1M (in → out)Per requestPer month
DeepSeek V4 Pro$1.32 → $3.96

≈ = estimated token count: only OpenAI publishes its tokenizer. Claude counts use Anthropic’s published ratios; use the count_tokens API for an exact number.

DeepSeek V4 Pro price per million tokens

USD, DeepSeek standard tier. Prices checked on October 28, 2026.

Token typePrice per 1M
Input$1.32
Cached input$0.044
Output$3.96

Note: Peak price. Off-peak is half: outside 01–04 and 06–10 UTC on weekdays, plus weekends and Chinese public holidays.

Model ID: deepseek-v4-pro · Source: api-docs.deepseek.com

What a DeepSeek V4 Pro request costs

RequestPer requestPer 1,000
Short chat reply
500 input + 200 output tokens
$0.0015$1.49
Chatbot turn with context
1,500 input + 400 output tokens
$0.0037$3.66
Document Q&A (RAG)
8,000 input + 500 output tokens
$0.01$13.07
Long-document summary
150,000 input + 2,000 output tokens
$0.22$216

Token counts are measured with GPT's o200k tokenizer and converted for DeepSeek V4 Pro (see below). No caching or batch discount.

Similarly priced models

ModelChatbot requestvs DeepSeek V4 Pro
GPT-5.4 mini OpenAI$0.0029−20%
Grok 4.3 xAI$0.0030−19%
Grok 4.20 xAI$0.0030−19%
o4-mini OpenAI$0.0034−7%
GPT-6.1 Terra OpenAI$0.0035−4%
Claude Haiku 4.5 Anthropic$0.0037same

Frequently asked questions

How much does the DeepSeek V4 Pro API cost?

DeepSeek V4 Pro costs $1.32 per million input tokens and $3.96 per million output tokens on DeepSeek's standard tier. Prices checked on October 28, 2026.

How much does one DeepSeek V4 Pro request cost?

A typical chatbot request with about 1,500 input and 400 output tokens costs about $0.0037, or $3.66 per 1,000 requests. Paste your own prompt into the calculator on this page for an exact estimate.

Does DeepSeek V4 Pro support prompt caching?

Yes. Cached input costs $0.044 per million tokens, 97% less than regular input.

Does DeepSeek V4 Pro have a Batch API discount?

No, DeepSeek V4 Pro has no Batch API discount.

How are DeepSeek V4 Pro tokens counted?

DeepSeek V4 Pro's tokenizer is not published. We estimate about 1.05× the GPT o200k count for the same text.

DeepSeek V4 Pro comparisons

More pricing