Mistral Medium 3 API pricing

Mistral charges $1.5 per million input tokens and $7.5 per million output tokens for Mistral Medium 3 (mistral-medium-3), and $0.15 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00525.

Prices updated November 14, 2026
Input / 1M tokens
$1.5
Output / 1M tokens
$7.5
Cached input / 1M tokens
$0.15
Typical request
$0.00525
Calculate the cost of your prompt →

mistral-medium-3 has the same prices as Mistral Medium (mistral-medium), so that page is the main one for both.

Mistral Medium 3 price per million tokens

Token typeStandard
Input$1.5
Cached input$0.15
Output$7.5

API model id: mistral-medium-3. Mistral Medium 3 supports a 262K-token context window, up to 262K output tokens, image input, tool calling and reasoning.

What Mistral Medium 3 costs per request

Request1 request1,000 requests1M requests
Short chat message (300 in, 200 out)$0.00195$1.95$1,950.00
Typical request (1K in, 500 out)$0.00525$5.25$5,250.00
Long document summary (20K in, 1K out)$0.0375$37.50$37,500.00
Coding agent step (50K in, 2K out)$0.09$90.00$90,000.00

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 Medium 3 compares

Mistral Medium 3 price history

Mistral Medium 3 has cost $1.5 per million input tokens and $7.5 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 4.5xAI$2$0.3$6$0.005
Grok 4.6xAI$2$0.5$6$0.005
Grok 4.7xAI$2$0.5$6$0.005
Gemini 4 HydrogenGoogle Gemini$1.5$0.075$7.5$0.00525
GPT-4.1OpenAI$2$0.5$8$0.006
o3OpenAI$2$0.5$8$0.006
Gemini 3.5 FlashGoogle Gemini$1.5$0.15$9$0.006
Gemini Omni 1.1 FlashGoogle Gemini$1.5–$9$0.006

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 Medium 3 API cost?

Mistral charges $1.5 per million input tokens and $7.5 per million output tokens for Mistral Medium 3 (mistral-medium-3), and $0.15 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00525.

Has the Mistral Medium 3 API price changed?

No. Mistral Medium 3 has cost $1.5 per million input tokens and $7.5 per million output tokens since apicost.app started tracking prices on October 22, 2026.

Is there a cheaper way to use Mistral Medium 3?

Prompt caching lowers the price of input that repeats across requests to $0.15 per million tokens.

What is the context window of Mistral Medium 3?

Mistral Medium 3 accepts up to 262,144 input tokens, roughly 197,000 words of English, and writes up to 262,144 output tokens per response. Filling the whole context window once costs $0.39 in input tokens.

Is Mistral Medium 3 cheaper than GPT-4.1?

Yes. GPT-4.1 from OpenAI costs $2 input and $8 output per million tokens, so a typical request is $0.006: 1.1× the price of Mistral Medium 3.

Source: Mistral pricing, via the LiteLLM price list.