Mistral Large 4 API pricing

Mistral charges $0.7 per million input tokens and $2.1 per million output tokens for Mistral Large 4 (mistral-large-4), and $0.07 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00175.

Prices updated November 14, 2026
Input / 1M tokens
$0.7
Output / 1M tokens
$2.1
Cached input / 1M tokens
$0.07
Typical request
$0.00175
Calculate the cost of your prompt →

The same prices apply to the model ids mistral-large-4-0.

Mistral Large 4 price per million tokens

Token typeStandard
Input$0.7
Cached input$0.07
Output$2.1

API model id: mistral-large-4. Mistral Large 4 supports a 1.05M-token context window, up to 1.05M output tokens, image input, tool calling and reasoning.

What Mistral Large 4 costs per request

Request1 request1,000 requests1M requests
Short chat message (300 in, 200 out)$0.00063$0.63$630.00
Typical request (1K in, 500 out)$0.00175$1.75$1,750.00
Long document summary (20K in, 1K out)$0.0161$16.10$16,100.00
Coding agent step (50K in, 2K out)$0.0392$39.20$39,200.00

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 Mistral Large 4 compares

Mistral Large 4 price history

Mistral Large 4's standard price changed twice since apicost.app started tracking prices on October 22, 2026. The latest, a price cut on November 3, 2026: input $1.36 → $0.7 (−49%), output $4.18 → $2.1 (−50%) per 1M tokens, which undid the change of Oct 28, 2026. It now costs $0.7 input and $2.1 output per 1M tokens.

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
GPT-5 miniOpenAI$0.25$0.025$2$0.00125
Mistral Large 3Mistral$0.5$0.05$1.5$0.00125
Gemini 2.5 FlashGoogle Gemini$0.3$0.03$2.5$0.00155
Gemini 3.5 Flash LiteGoogle Gemini$0.3$0.03$2.5$0.00155
DeepSeek R1DeepSeek$0.55$0.14$2.19$0.00164
Gemini 3 Flash PreviewGoogle Gemini$0.5$0.05$3$0.002
Grok Build 0.1xAI$1$0.2$2$0.002
Grok Code FastxAI$1$0.2$2$0.002

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 Mistral Large 4 API cost?

Mistral charges $0.7 per million input tokens and $2.1 per million output tokens for Mistral Large 4 (mistral-large-4), and $0.07 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00175.

Has the Mistral Large 4 API price changed?

Yes. Mistral Large 4's standard price changed twice since apicost.app started tracking prices on October 22, 2026. The latest, a price cut on November 3, 2026: input $1.36 → $0.7 (−49%), output $4.18 → $2.1 (−50%) per 1M tokens, which undid the change of Oct 28, 2026. It now costs $0.7 input and $2.1 output per 1M tokens.

Is there a cheaper way to use Mistral Large 4?

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

What is the context window of Mistral Large 4?

Mistral Large 4 accepts up to 1,048,576 input tokens, roughly 786,000 words of English, and writes up to 1,048,576 output tokens per response. Filling the whole context window once costs $0.73 in input tokens.

Is Mistral Large 4 cheaper than GPT-5 mini?

No. GPT-5 mini from OpenAI costs $0.25 input and $2 output per million tokens, so a typical request is $0.00125: 1.4× cheaper than Mistral Large 4.

Source: Mistral pricing, via the LiteLLM price list.