Mistral Models
Mistral logo

Mistral: Mistral Small 3

24B

byMistral

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

Input Price$0.20/1M tokens
Output Price$0.60/1M tokens
Intelligence4.7
CodingN/A

Specifications

Technical details and pricing.

ProviderMistral
Context Window32,768 tokens
Release DateSep 17, 2024
ModalitiesText
CapabilitiesStructured Outputs, JSON Mode

Benchmarks

7 benchmark scores from Artificial Analysis.

GPQA38.1%
MMLU Pro52.9%
HLE4.3%
LiveCodeBench14.1%
MATH 50056.3%
AIME6.3%
SciCode15.6%

Composite Indices

Higher is better; speed and price are normalized

Standard Benchmarks

Only benchmarks with data are shown

Frequently Asked Questions

What is Mistral: Mistral Small 3 good for?

Use Mistral: Mistral Small 3 for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.

How much does Mistral: Mistral Small 3 cost?

Pricing is based on usage. Current rates are $0.20/1M tokens for input and $0.60/1M tokens for output.

Can I try Mistral: Mistral Small 3 for free?

Yes. You can start a chat instantly and test the model before deciding on a plan.

Does Mistral: Mistral Small 3 support images or audio?

Mistral: Mistral Small 3 focuses on text-based tasks.

Benchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.