Mistral Small 3.1

Approved Data Classifications

Description

Mistral Small 3.1 is an advanced, open‑source language model from Mistral AI designed to deliver best‑in‑class performance within its 24‑billion‑parameter weight class. Launched in March 2025 under an Apache 2.0 license, it features a massive 128,000‑token context window and full multimodal support for both text and images. The model excels across dozens of languages—including English, French, German, Spanish, Italian, Japanese, and Korean—showcasing robust multilingual proficiency. Optimized for efficiency, Mistral Small 3.1 achieves inference speeds of up to 150 tokens per second, excelling at instruction following, conversational AI, code generation, mathematical reasoning, and long‑document comprehension. Its lightweight design, low latency, and permissive licensing make it an ideal choice for developers building fast, accurate, and flexible AI applications across diverse domains.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
mistral-small-3.1	October 2023	Image, Text	Text	128,000	$0.10/1M input $0.30/1M output

info

• 1M represents 1 Million Tokens
• All prices listed are based on 1 Million Tokens

Availability

Cloud Provider

Usage

curl

curl -X POST https://api.ai.it.ufl.edu/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <API_TOKEN>" \
-d '{
    "model": "mistral-small-3.1",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Write a haiku about an Alligator."
        }
    ]
}'

python

from openai import OpenAI
  client = OpenAI(
      api_key="your_api_key",
      base_url="https://api.ai.it.ufl.edu/v1"
  )

  response = client.chat.completions.create(
      model="mistral-small-3.1", # model to send to the proxy
      messages = [
          { role: "system", content: "You are a helpful assistant." },
          {
              "role": "user",
              "content": "Write a haiku about an Alligator."
          }
      ]
  )

  print(response.choices[0].message)

javascript

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: 'your_api_key',
  baseURL: 'https://api.ai.it.ufl.edu/v1'
});

const completion = await openai.chat.completions.create({
    model: "mistral-small-3.1",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)