How to Use the OpenAI o1 API

OpenAI has recently launched the o1 model, its first in a series of "reasoning" models aimed at solving complex problems faster than humans. Alongside the smaller o1-mini, this model, often referred to as the "Strawberry" model in AI circles, has garnered significant attention.

The release of o1 marks a milestone in OpenAI’s pursuit of AI models with human-like reasoning capabilities. While o1 is outstanding at handling multistep problems and coding tasks, it comes with a higher cost and slower performance compared to GPT-4o. Despite being labeled a “preview,” it offers a tantalizing glimpse into the future of AI technology.

💡 Boost Your Workflow with Apidog!

Looking for an API testing tool that simplifies your workflow? Apidog is an all-in-one solution for sending requests, debugging APIs, and optimizing development processes. Whether handling simple requests or complex cURL commands, Apidog’s intuitive interface makes API testing easy.

Sign Up for Free

How to Use OpenAI o1?

ChatGPT Plus and Team users can access both o1-preview and o1-mini via the model picker. Initially, usage is capped at 30 messages per week for o1-preview and 50 for o1-mini, but OpenAI plans to expand these limits soon.

For developers, API access is available for those in usage tier 5, with a rate limit of 20 requests per minute. The API currently lacks features like function calling, streaming, and system messages, though OpenAI is working to add these functionalities. Full API documentation is available for further details.

What Makes OpenAI o1 Stand Out?

o1 is trained using a novel optimization algorithm and dataset, applying reinforcement learning rather than the pattern-mimicking methods of previous models. This allows it to solve problems step-by-step, similar to how humans tackle complex tasks. It delivers more accurate responses with fewer hallucinations, although OpenAI acknowledges that hallucinations still occur.

Enhanced Problem-Solving Capabilities

In internal testing, o1 outperformed GPT-4o on tasks like coding and solving math problems. For example, it placed in the 89th percentile in Codeforces competitions and scored 83% on a qualifying exam for the International Mathematics Olympiad, significantly better than GPT-4o's 13%.

Limitations of OpenAI o1

While o1 excels in reasoning tasks, it does have limitations. It lacks the vast factual knowledge of GPT-4o, cannot browse the web, and is unable to process files or images. Despite these shortcomings, OpenAI views o1 as the first of a new class of AI models, representing a shift in both AI naming conventions and technical capabilities.

How to Use the OpenAI o1 API？

If you’re eager to tap into OpenAI’s latest model, o1, for its enhanced reasoning abilities, follow this quick guide to get started:

1. Get Access to the OpenAI o1 API

• Visit OpenAI’s website to sign up or log in for API access.
• Navigate to the API Keys section to generate your API key. Keep in mind that o1 is more expensive than earlier models like GPT-4o.

2. Install the OpenAI Python Library

Install the OpenAI Python library on your local machine with this command:

pip install openai

3. Make Your First API Call

With your API key, you can now make your first API call in Python:

import openai

def get_chat_completion(prompt, model="o1-preview"):
    messages = [{"role": "user", "content": prompt}]
    response = openai.ChatCompletion.create(
        model=model,
        messages=messages,
        temperature=0,
    )
    return response.choices[0].message["content"]

response = get_chat_completion("Translate into Spanish: I am learning to use OpenAI API!")
print(response)

This function sends a prompt to the o1-preview model and returns a response.

4. Integrate the OpenAI o1 API into Your project

If you’re working with a web framework like Flask or Django, you can embed OpenAI API calls into your routes or views.

Example using Flask:

from flask import Flask, request, jsonify
import openai

app = Flask(__name__)

openai.api_key = "your-api-key-here"

@app.route('/ask', methods=['POST'])
def ask_openai():
    prompt = request.json['prompt']
    response = openai.Completion.create(
        model="o1-preview",
        prompt=prompt,
        max_tokens=100
    )
    return jsonify(response.choices[0].text)

if __name__ == '__main__':
    app.run(debug=True)

This code sets up an API route /ask where users can send a prompt, and the application will return the response generated by OpenAI.

An Easier Way to Test OpenAI o1 API — Using Apidog

Apidog is a powerful API testing tool similar to Postman. You can send cURL requests to OpenAI’s API using Apidog. Here’s how to set up a POST request:

curl https://api.openai.com/v1/completions \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "o1-preview",
    "prompt": "Explain the theory of relativity in simple terms.",
    "max_tokens": 150
  }'

Copy the above cURL code and paste them into the search bar in Apidog:

Replace $OPENAI_API_KEY with your actual API bearer token. After sending the request, you’ll receive a detailed response report.

When the API is ready to go, you can generate client codes directly in Apidog and use them for direct deployment in real project.

See how to get a bearer token using Apidog.

Building Toward the Future

Although o1 is in its early stages, it represents a significant leap in AI, especially for reasoning and problem-solving tasks. Despite its higher cost and slower speed, it showcases the future of AI—where models not only recognize patterns but also reason through them.

As OpenAI continues to refine this series, the introduction of o1 lays the groundwork for future advancements in AI, bringing us closer to a world where machines can solve increasingly complex problems.