Codestral 22b

Approved Data Classifications

Description

Codestral-22B is a powerful AI model developed by Mistral AI, specifically designed for code generation tasks across a wide array of programming languages. Launched in May 2024, this model features 22 billion parameters and is trained on a diverse dataset encompassing over 80 programming languages, including popular ones like Python, Java, C++, and JavaScript. Codestral-22B excels in various coding-related tasks, such as generating code snippets, completing partial code using its fill-in-the-middle mechanism, and providing explanations or documentation for existing code. Its advanced capabilities allow developers to streamline their workflow, reduce errors, and enhance productivity in software development projects. However, it is important to note that Codestral-22B lacks built-in moderation mechanisms, which may limit its deployment in environments that require controlled outputs.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
codestral-22b	May 2024	Text	Text	32,000	$0.20/1M input $0.60/1M 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": "codestral-22b",
    "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="codestral-22b", # 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: "codestral-22b",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)