Text Generation Model

Mistral Small 24.02

Single-node inference model with 128k context window supporting dozens of languages and 80+ coding languages.

Start Building with Mistral Small 24.02 View All Models

Publisher

Mistral

Type Text

Context Window 128,000 tokens

Training Data n/a

Input $1.00/MTok

Output $3.00/MTok

Provider

Amazon Bedrock

Try Mistral Small 24.02 →

About Mistral Small 24.02

128k context window across dozens of languages

Mistral Small 24.02 is a text generation model developed by Mistral, designed to run on a single node while supporting a 128,000-token context window. It covers dozens of natural languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, as well as over 80 coding languages such as Python, Java, C, C++, JavaScript, and Bash. The model has 123 billion parameters, which enables high-throughput inference without requiring multi-node infrastructure.

This model is well-suited for long-context applications where fitting large documents or extended conversations into a single prompt is necessary. Its broad language coverage makes it applicable to multilingual workflows, while its coding language support makes it useful for code generation and analysis tasks. The single-node inference design is a practical consideration for teams managing deployment costs and infrastructure complexity.

Capabilities

What Mistral Small 24.02 supports

Long Context Window

Supports up to 128,000 tokens in a single context, enabling processing of long documents or extended multi-turn conversations without truncation.

Multilingual Text Generation

Generates and understands text in dozens of natural languages including French, German, Spanish, Arabic, Hindi, Chinese, Japanese, and Korean.

Code Generation

Supports over 80 coding languages including Python, Java, C, C++, JavaScript, and Bash for code writing and analysis tasks.

Single-Node Inference

Runs at large throughput on a single node due to its 123 billion parameter architecture, reducing multi-node infrastructure requirements.

Instruction Following

Responds to structured prompts and instructions, making it applicable for task-oriented workflows such as summarization, translation, and Q&A.

Ready to build with Mistral Small 24.02?

Get Started Free

Performance

Benchmark scores

Scores represent accuracy — the percentage of questions answered correctly on each test.

Benchmark	What it tests	Score
MMLU-Pro	Expert knowledge across 14 academic disciplines	52.9%
GPQA Diamond	PhD-level science questions (biology, physics, chemistry)	38.1%
MATH-500	Undergraduate and competition-level math problems	56.3%
AIME 2024	American math olympiad problems	6.3%
LiveCodeBench	Real-world coding tasks from recent competitions	14.1%
HLE	Questions that challenge frontier models across many domains	4.3%
SciCode	Scientific research coding and numerical methods	15.6%

FAQ

Common questions about Mistral Small 24.02

What is the context window size for Mistral Small 24.02?

Mistral Small 24.02 supports a context window of 128,000 tokens, allowing large documents or long conversations to be processed in a single prompt.

Which natural languages does this model support?

The model supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, among others.

How many coding languages does Mistral Small 24.02 support?

The model supports over 80 coding languages, including Python, Java, C, C++, JavaScript, and Bash.

What infrastructure is required to run this model?

Mistral Small 24.02 is designed for single-node inference. Its 123 billion parameters allow it to run at large throughput on a single node without requiring multi-node setups.

Is a training data cutoff date available for this model?

The training date is listed as not available in the current metadata. For the most accurate information, refer to Mistral's official documentation.

Resources