Mistral Large 2

Approved Data Classifications

Description

Mistral Large 2 is a state-of-the-art large language model developed by Mistral AI, designed to excel in reasoning, multilingual processing, and coding tasks. Launched in July 2024, this model boasts an impressive 123 billion parameters and features a substantial context window of 128,000 tokens, enabling it to handle extensive and complex datasets with ease. Mistral Large 2 supports dozens of languages, including major global languages such as English, French, German, and Chinese, as well as over 80 programming languages like Python and Java. The model has been fine-tuned to minimize hallucinations and improve accuracy, making it a reliable choice for generating precise information. With its advanced capabilities in math, reasoning, and coding, Mistral Large 2 positions itself as a powerful tool for developers and researchers seeking to build sophisticated AI applications across diverse domains.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
mistral-large-2	April 2024	Text	Text	32,000	$4.00/1M input $12.00/1M 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-large-2",
    "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-large-2", # 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-large-2",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)