DeepSeek V4 1 Flash 1017 API pricing

Mistral charges $0.3 per million input tokens and $1.2 per million output tokens for DeepSeek V4 1 Flash 1017 (deepseek-v4-1-flash-1017), and $0.007 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.0009.

Prices updated November 14, 2026
Input / 1M tokens
$0.3
Output / 1M tokens
$1.2
Cached input / 1M tokens
$0.007
Typical request
$0.0009
Calculate the cost of your prompt →

DeepSeek V4 1 Flash 1017 price per million tokens

Token typeStandard
Input$0.3
Cached input$0.007
Output$1.2

API model id: deepseek-v4-1-flash-1017. DeepSeek V4 1 Flash 1017 supports a 1.05M-token context window, up to 131K output tokens, image input, tool calling and reasoning.

What DeepSeek V4 1 Flash 1017 costs per request

Request1 request1,000 requests1M requests
Short chat message (300 in, 200 out)$0.00033$0.33$330.00
Typical request (1K in, 500 out)$0.0009$0.90$900.00
Long document summary (20K in, 1K out)$0.0072$7.20$7,200.00
Coding agent step (50K in, 2K out)$0.0174$17.40$17,400.00

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

How DeepSeek V4 1 Flash 1017 compares

DeepSeek V4 1 Flash 1017 price history

DeepSeek V4 1 Flash 1017 has cost $0.3 per million input tokens and $1.2 per million output tokens since it was added to the price list on October 28, 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
DeepSeek V3DeepSeek$0.27$0.07$1.1$0.00082
GPT-5.4 nanoOpenAI$0.2$0.02$1.25$0.000825
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 Mistral models

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

Questions and answers

How much does the DeepSeek V4 1 Flash 1017 API cost?

Mistral charges $0.3 per million input tokens and $1.2 per million output tokens for DeepSeek V4 1 Flash 1017 (deepseek-v4-1-flash-1017), and $0.007 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.0009.

Has the DeepSeek V4 1 Flash 1017 API price changed?

No. DeepSeek V4 1 Flash 1017 has cost $0.3 per million input tokens and $1.2 per million output tokens since it was added to the price list on October 28, 2026.

Is there a cheaper way to use DeepSeek V4 1 Flash 1017?

Prompt caching lowers the price of input that repeats across requests to $0.007 per million tokens.

What is the context window of DeepSeek V4 1 Flash 1017?

DeepSeek V4 1 Flash 1017 accepts up to 1,048,576 input tokens, roughly 786,000 words of English, and writes up to 131,072 output tokens per response. Filling the whole context window once costs $0.31 in input tokens.

Is DeepSeek V4 1 Flash 1017 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 V4 1 Flash 1017.

Source: Mistral pricing, via the LiteLLM price list.