o3

Approved Data Classifications

Description

OpenAI's o3 model is its most advanced reasoning AI, excelling in complex tasks across coding, mathematics, science, and visual analysis. Unlike its predecessor o3-mini, o3 integrates visual inputs—such as images and charts—into its reasoning process, enabling it to interpret and manipulate visual data as part of problem-solving. It also leverages the full suite of ChatGPT tools, including web browsing, Python execution, and file analysis. This makes o3 ideal for users tackling multifaceted challenges that require deep, multimodal reasoning and precise analysis.

Capabilities

Model	Training Data	Input	Output	Context Length	Cost (per 1 million tokens)
o3	May 2024	Text, Image	Text	200,000	$10.00/1M input $40.00/1M 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": "o3",
    "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="o3", # 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: "o3",
    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

​The o3 model from OpenAI is a cutting-edge AI system designed for deep, multimodal reasoning across complex tasks in coding, mathematics, science, and visual analysis. Unlike its predecessor, o3-mini, which offers efficient performance for straightforward tasks, o3 excels in handling intricate problems that require advanced analytical thinking and the integration of visual inputs like images and charts. It leverages the full suite of ChatGPT tools—including web browsing, Python execution, and file interpretation—to provide comprehensive assistance. This makes o3 particularly suitable for professionals, researchers, and developers seeking a powerful AI capable of delivering nuanced insights and tackling sophisticated challenges.