Mistral Small

Approved Data Classifications

Description

Mistral Small is Mistral AI's compact yet powerful language model, designed for efficiency and optimized for low-latency applications. Launched in May 2024, this model stands out as the smallest proprietary offering from Mistral, outperforming larger models like Mixtral 8x7B while maintaining rapid response times. With a context window of up to 32,000 tokens, Mistral Small excels in a variety of language-based tasks, including code generation and multilingual processing, supporting languages such as French, German, Spanish, and Italian. Its architecture is specifically tailored for high-volume workloads, making it an ideal choice for developers seeking to integrate AI capabilities into applications that demand quick and reliable performance. Additionally, Mistral Small incorporates built-in safety features to ensure responsible usage, further enhancing its appeal for deployment in real-world scenarios.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
mistral-small	February 2024	Text	Text	32,000	$1.00/1M input $3.00/1M 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",
    "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", # 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",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)