o1-mini

Approved Data Classifications

Description

The o1-mini model from OpenAI is a streamlined, cost-effective AI solution designed to enhance reasoning capabilities, particularly in STEM fields such as mathematics and coding. Launched as a more accessible alternative to the more robust o1-preview model, o1-mini focuses on delivering efficient problem-solving without the extensive resource requirements of larger models. It excels at handling logical tasks and coding challenges, making it ideal for users who need quick responses and straightforward solutions. With its user-friendly interface and zero cost for access, o1-mini democratizes advanced AI technology, allowing a broader audience to leverage its capabilities for various applications while maintaining a strong emphasis on effective reasoning and analysis.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
o1-mini	May 2024	Text	Text	128,000	$3.00/1M 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": "o1-mini",
    "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="o1-mini", # 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: "o1-mini",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Write a haiku about an Alligator.",
        },
    ],
});

print(completion.choices[0].message)

When to use

You might choose to use the o1-mini model when you need a lightweight and efficient AI solution for tasks that require quick reasoning and problem-solving, particularly in educational or coding contexts. This model is ideal for users who seek immediate assistance with logical puzzles, mathematical problems, or programming challenges without the overhead of more complex models. Its cost-free access makes it an attractive option for students, educators, and developers looking to integrate AI into their workflows without incurring expenses. Additionally, o1-mini is well-suited for applications where speed and simplicity are prioritized over the depth of analysis, such as generating code snippets, providing homework help, or offering instant feedback on logical queries. Its accessibility and ease of use make it a practical choice for those new to AI or those seeking a reliable tool for everyday tasks.