Ministral 3 8B 2512 API pricing

Mistral charges $0.15 per million input tokens and $0.15 per million output tokens for Ministral 3 8B 2512 (ministral-3-8b-2512), and $0.015 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.000225.

Prices updated November 14, 2026
Input / 1M tokens
$0.15
Output / 1M tokens
$0.15
Cached input / 1M tokens
$0.015
Typical request
$0.000225
Calculate the cost of your prompt →

Ministral 3 8B 2512 price per million tokens

Token typeStandard
Input$0.15
Cached input$0.015
Output$0.15

API model id: ministral-3-8b-2512. Ministral 3 8B 2512 supports a 262K-token context window, up to 262K output tokens, image input and tool calling.

What Ministral 3 8B 2512 costs per request

Request1 request1,000 requests1M requests
Short chat message (300 in, 200 out)$0.000075$0.075$75.00
Typical request (1K in, 500 out)$0.000225$0.23$225.00
Long document summary (20K in, 1K out)$0.00315$3.15$3,150.00
Coding agent step (50K in, 2K out)$0.0078$7.80$7,800.00

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 Ministral 3 8B 2512 compares

Ministral 3 8B 2512 price history

Ministral 3 8B 2512 has cost $0.15 per million input tokens and $0.15 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 3B 2512Mistral$0.1$0.01$0.1$0.00015
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
DeepSeek CoderDeepSeek$0.14$0.014$0.28$0.00028
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

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 Ministral 3 8B 2512 API cost?

Mistral charges $0.15 per million input tokens and $0.15 per million output tokens for Ministral 3 8B 2512 (ministral-3-8b-2512), and $0.015 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.000225.

Has the Ministral 3 8B 2512 API price changed?

No. Ministral 3 8B 2512 has cost $0.15 per million input tokens and $0.15 per million output tokens since apicost.app started tracking prices on October 22, 2026.

Is there a cheaper way to use Ministral 3 8B 2512?

Prompt caching lowers the price of input that repeats across requests to $0.015 per million tokens.

What is the context window of Ministral 3 8B 2512?

Ministral 3 8B 2512 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 $0.0393 in input tokens.

Is Ministral 3 8B 2512 cheaper than GPT-5 nano?

Yes. 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× the price of Ministral 3 8B 2512.

Source: Mistral pricing, via the LiteLLM price list.