Magistral Small

Approved Data Classifications

Description

Magistral Small is Mistral AI’s first open-weight reasoning model, featuring 24 billion parameters and released under the Apache 2.0 license for self-deployment. Launched in June 2025, it builds upon the Mistral Small 3.1 architecture with supervised fine-tuning from Magistral Medium traces and reinforcement learning, enabling robust step-by-step logical reasoning. With a 40 000-token context window, Magistral Small excels at domain-specific tasks such as math, coding, and multilingual analysis, and its efficient design allows local deployment.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
magistral-small	June 2025	Text	Text	40,000	$0.99/1M input $0.99/1M 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": "magistral-small",
    "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="magistral-small", # 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: "magistral-small",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)

---

References

1. MistralAI
   https://mistral.ai/
2. LLM Stats
   https://llm-stats.com
3. Artificial Analysis
   https://artificialanalysis.ai