DeepSeek Coder API pricing

DeepSeek charges $0.14 per million input tokens and $0.28 per million output tokens for DeepSeek Coder (deepseek-coder), and $0.014 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00028.

Prices updated November 14, 2026
Input / 1M tokens
$0.14
Output / 1M tokens
$0.28
Cached input / 1M tokens
$0.014
Typical request
$0.00028
Calculate the cost of your prompt →

DeepSeek Coder price per million tokens

Token typeStandard
Input$0.14
Cached input$0.014
Output$0.28

API model id: deepseek-coder. DeepSeek Coder supports a 128K-token context window, up to 4.1K output tokens and tool calling.

What DeepSeek Coder costs per request

Request1 request1,000 requests1M requests
Short chat message (300 in, 200 out)$0.000098$0.098$98.00
Typical request (1K in, 500 out)$0.00028$0.28$280.00
Long document summary (20K in, 1K out)$0.00308$3.08$3,080.00
Coding agent step (50K in, 2K out)$0.00756$7.56$7,560.00

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 Coder compares

DeepSeek Coder price history

DeepSeek Coder has cost $0.14 per million input tokens and $0.28 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
Ministral 3 8B 2512Mistral$0.15$0.015$0.15$0.000225
Ministral 8B 2512Mistral$0.15$0.015$0.15$0.000225
GPT-5 nanoOpenAI$0.05$0.005$0.4$0.00025
Mistral SmallMistral$0.1$0.01$0.3$0.00025
Gemini 2.5 Flash LiteGoogle Gemini$0.1$0.01$0.4$0.0003
Ministral 3 14B 2512Mistral$0.2$0.02$0.2$0.0003
Ministral 14B 2512Mistral$0.2$0.02$0.2$0.0003
GPT-6 LunaOpenAI$0.1$0.01$0.5$0.00035

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 Coder API cost?

DeepSeek charges $0.14 per million input tokens and $0.28 per million output tokens for DeepSeek Coder (deepseek-coder), and $0.014 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00028.

Has the DeepSeek Coder API price changed?

No. DeepSeek Coder has cost $0.14 per million input tokens and $0.28 per million output tokens since apicost.app started tracking prices on October 22, 2026.

Is there a cheaper way to use DeepSeek Coder?

Prompt caching lowers the price of input that repeats across requests to $0.014 per million tokens.

What is the context window of DeepSeek Coder?

DeepSeek Coder accepts up to 128,000 input tokens, roughly 96,000 words of English, and writes up to 4,096 output tokens per response. Filling the whole context window once costs $0.0179 in input tokens.

Is DeepSeek Coder cheaper than GPT-5 nano?

No. GPT-5 nano from OpenAI costs $0.05 input and $0.4 output per million tokens, so a typical request is $0.00025: 1.1× cheaper than DeepSeek Coder.