DeepSeek V3 API pricing

DeepSeek charges $0.27 per million input tokens and $1.1 per million output tokens for DeepSeek V3 (deepseek-v3), and $0.07 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00082.

Prices updated November 14, 2026
Input / 1M tokens
$0.27
Output / 1M tokens
$1.1
Cached input / 1M tokens
$0.07
Typical request
$0.00082
Calculate the cost of your prompt →

DeepSeek V3 price per million tokens

Token typeStandard
Input$0.27
Cached input$0.07
Output$1.1

API model id: deepseek-v3. DeepSeek V3 supports a 65.5K-token context window, up to 8.19K output tokens and tool calling.

What DeepSeek V3 costs per request

Request1 request1,000 requests1M requests
Short chat message (300 in, 200 out)$0.000301$0.30$301.00
Typical request (1K in, 500 out)$0.00082$0.82$820.00
Long document summary (20K in, 1K out)$0.0065$6.50$6,500.00
Coding agent step (50K in, 2K out)$0.0157$15.70$15,700.00

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 V3 compares

DeepSeek V3 price history

DeepSeek V3 has cost $0.27 per million input tokens and $1.1 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
Codestral 2508Mistral$0.3$0.03$0.9$0.00075
GPT-5.6 LunaOpenAI$0.2$0.02$1.2$0.0008
GPT-5.4 nanoOpenAI$0.2$0.02$1.25$0.000825
DeepSeek V4 1 Flash 1017Mistral$0.3$0.007$1.2$0.0009
DeepSeek FlashDeepSeek$0.3$0.006$1.2$0.0009
DeepSeek V4 FlashDeepSeek$0.3$0.006$1.2$0.0009
Gemini 3.1 Flash LiteGoogle Gemini$0.25$0.025$1.5$0.001
GPT-4.1 miniOpenAI$0.4$0.1$1.6$0.0012

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 V3 API cost?

DeepSeek charges $0.27 per million input tokens and $1.1 per million output tokens for DeepSeek V3 (deepseek-v3), and $0.07 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00082.

Has the DeepSeek V3 API price changed?

No. DeepSeek V3 has cost $0.27 per million input tokens and $1.1 per million output tokens since apicost.app started tracking prices on October 22, 2026.

Is there a cheaper way to use DeepSeek V3?

Prompt caching lowers the price of input that repeats across requests to $0.07 per million tokens.

What is the context window of DeepSeek V3?

DeepSeek V3 accepts up to 65,536 input tokens, roughly 49,000 words of English, and writes up to 8,192 output tokens per response. Filling the whole context window once costs $0.0177 in input tokens.

Is DeepSeek V3 cheaper than GPT-5.4 nano?

They cost about the same. GPT-5.4 nano from OpenAI costs $0.2 input and $1.25 output per million tokens, so a typical request is $0.000825: about the same price as DeepSeek V3.