DeepSeek V4 Pro API pricing

DeepSeek charges $1.32 per million input tokens and $3.96 per million output tokens for DeepSeek V4 Pro (deepseek-v4-pro), and $0.044 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.0033.

Prices updated November 14, 2026
Input / 1M tokens
$1.32
Output / 1M tokens
$3.96
Cached input / 1M tokens
$0.044
Typical request
$0.0033
Calculate the cost of your prompt →

DeepSeek V4 Pro price per million tokens

Token typeStandard
Input$1.32
Cached input$0.044
Output$3.96

API model id: deepseek-v4-pro. DeepSeek V4 Pro supports a 1M-token context window, up to 393K output tokens, tool calling and reasoning.

What DeepSeek V4 Pro costs per request

Request1 request1,000 requests1M requests
Short chat message (300 in, 200 out)$0.00119$1.19$1,188.00
Typical request (1K in, 500 out)$0.0033$3.30$3,300.00
Long document summary (20K in, 1K out)$0.0304$30.36$30,360.00
Coding agent step (50K in, 2K out)$0.0739$73.92$73,920.00

At standard rates. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words. DeepSeek counts tokens with its own tokenizer, so the same text can be a different number of tokens.

How DeepSeek V4 Pro compares

DeepSeek V4 Pro price history

DeepSeek V4 Pro has cost $1.32 per million input tokens and $3.96 per million output tokens since apicost.app started tracking prices on October 22, 2026.

Every LLM API price increase, cut, new and retired model, dated: LLM API price changes.

Models with a similar price

ModelProviderInput / 1MCached input / 1MOutput / 1MTypical request
Grok 4.3xAI$1.25$0.2$2.5$0.0025
Grok 4.20xAI$1.25$0.2$2.5$0.0025
Gemini 3.6 FlashGoogle Gemini$0.75$0.075$3.75$0.00263
Gemini 3.7 FlashGoogle Gemini$0.75$0.075$3.75$0.00263
Gemini 3.8 FlashGoogle Gemini$0.75$0.075$3.75$0.00263
GPT-5.4 miniOpenAI$0.75$0.075$4.5$0.003
GPT-6.1 TerraOpenAI$1$0.05$5$0.0035
Claude Haiku 4.5Anthropic$1$0.1$5$0.0035

Other DeepSeek models

Every DeepSeek model side by side, with batch, caching and long-context prices: DeepSeek API pricing. Ways to pay less: batch API, prompt caching, the cheapest models.

Questions and answers

How much does the DeepSeek V4 Pro API cost?

DeepSeek charges $1.32 per million input tokens and $3.96 per million output tokens for DeepSeek V4 Pro (deepseek-v4-pro), and $0.044 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.0033.

Has the DeepSeek V4 Pro API price changed?

No. DeepSeek V4 Pro has cost $1.32 per million input tokens and $3.96 per million output tokens since apicost.app started tracking prices on October 22, 2026.

Is there a cheaper way to use DeepSeek V4 Pro?

Prompt caching lowers the price of input that repeats across requests to $0.044 per million tokens.

What is the context window of DeepSeek V4 Pro?

DeepSeek V4 Pro accepts up to 1,000,000 input tokens, roughly 750,000 words of English, and writes up to 393,216 output tokens per response. Filling the whole context window once costs $1.32 in input tokens.

Is DeepSeek V4 Pro cheaper than GPT-6.1 Terra?

They cost about the same. GPT-6.1 Terra from OpenAI costs $1 input and $5 output per million tokens, so a typical request is $0.0035: about the same price as DeepSeek V4 Pro.

Source: DeepSeek pricing, via the LiteLLM price list.