Mistral Small 3.1

Generic Info

• Publisher: Mistral AI
• Release Date: January 2025 (3.0), March 2025 (3.1)
• Parameters: 24B
• Context Window: 128k tokens
• License: Apache 2.0
• Key Capabilities: Multimodal, Function Calling, Multilingual (11 languages)

Mistral Small 3.1 redefines efficiency in AI. Despite being a "small" model, it competes head-to-head with Llama 3.3 70B and Qwen 32B while running 3x faster. Its Apache 2.0 license and ability to run on a single RTX 4090 make it perfect for local deployment.

Hello World Guide

Use the official mistralai Python client or OpenAI-compatible API.

from mistralai import Mistral

client = Mistral(api_key="YOUR_API_KEY")

response = client.chat.complete(
    model="mistral-small-latest",
    messages=[
        {
            "role": "user",
            "content": "Write a haiku about efficient AI models."
        }
    ]
)

print(response.choices[0].message.content)

Industry Usage