OpenAI just dropped its highly-anticipated Strawberry model, officially the o1 model series. Since the announcement, the AI community on social media has been buzzing with excitement about the models. But did you know there are four easy ways you can start chatting with the o1 models today? In this blog, we’ll walk you through step-by-step how to access and use these models on 4 different platforms.

Quick Introduction

For those living under the rock, OpenAI released its new o1 models series on Friday. These models, o1-preview and o1-mini, are designed to spend more time thinking before they respond. They can reason through complex tasks and solve harder problems than previous models in science, coding, and math.

• Advanced Reasoning: o1 models use chain-of-thought reasoning to think through problems step by step, providing more refined answers.

• Features - Have 128K context and an October 2023 knowledge cutoff. At the moment, o1 models cannot browse the web, and process files and images like GPT-4o.

• Improved Multi-step Workflows: Handle multi-step processes like refactoring code, writing test suites, and solving math problems with ease.

• Coding Expertise: o1-preview and o1-mini excel in coding tasks, from debugging to optimizing complex algorithms.

• Faster Performance: o1-mini is 80% cheaper and faster, making it a cost-effective solution for tasks requiring quick reasoning.

5 Easy Ways to Use OpenAI o1

Let’s start with the fun part now. To quickly start chatting with the o1 models, here are four platforms you can use TODAY!

1. ChatGPT (obviously)

2. Via OpenAI API (for Tier 5 users only)

3. In Cursor AI

4. In ChatLLM by Abacus AI

5. In VS Code via the CodeGPT extension

Here’s a step-by-step guide and the limitations of each platform.

ChatGPT

o1 models are currently available to ChatGPT Plus and Team users. Edu and Team users will get access to the models in the coming week.

1. Log in to ChatGPT: Head over to chat.openai.com or download ChatGPT’s desktop app and log in to your account.

2. Choose the Model: In the model picker, select either O1-preview or O1-mini, depending on your needs.

   • O1-preview: Ideal for more complex reasoning tasks and multi-step workflows.

   • O1-mini: Faster and more cost-effective, great for coding and quick responses.

3.  Check Rate Limits:

   • O1-preview: You can send up to 30 messages per week.

   • O1-mini: Allows for up to 50 messages per week.

4. Start Chatting: Type in your query, whether it’s a coding challenge, math problem, or everyday question (we wouldn't recommend it however due to the rate limits; use wisely!), and watch as the O1 model generates a thoughtful, structured response.

5. Chain-of-Thought Summaries: For more advanced reasoning, the model will display its chain of thought, allowing you to understand how it arrived at the answer.

API Access

If you prefer to interact directly with OpenAI’s O1 models through the API, you can easily set it up using the following steps.

1. Sign Up for API Access: Ensure you have access to OpenAI’s Tier 5 usage, which is required to use the o1 models.

2. Install the OpenAI Python Library: Open your terminal and install the OpenAI Python package by running the following command:

pip install openai

3. Set Up Your API Key: Store your OpenAI API key as an environment variable for secure access. You can do this by running:

export OPENAI_API_KEY="your-api-key-here"

4. Make API Calls: Now, you can start making API calls using the O1 models. Here’s a simple example in Python to get you started:

import openai

openai.api_key = "your-api-key"

response = openai.ChatCompletion.create(
    model="o1-preview",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ]
)

print(response.choices[0].message.content)

Code with o1 in Cursor AI

Cursor AI is a powerful platform for developers, and it offers flexibility when integrating OpenAI’s O1 models for tasks like code generation and debugging.

1. Download and Install Cursor AI: Head over to Cursor’s official website and download the IDE. Once installed, launch it.

2. Cursor Chat: It is AI assistant that offers real-time coding help and suggestions, ideal for file-specific improvements that require manual review. Press CMD + L (in Macbook) to launch access Cursor Compose.

3. Cursor Compose: Cursor Compose is a feature that enables developers to apply changes across multiple files simultaneously with a single click. Press CMD + I to launch access Cursor Compose.

4. From the model selector, choose o1-preview to interact with the model.

5. Add o1 model in the Settings: If you don’t see the model above, open Cursor’s settings editor (you can access it via the gear icon in the top right corner).

6. Add the O1 Model: Click the “Add model” button and enter “o1-preview” to add the o1-preview model. Toggle to enable the model.

ChatLLM by Abacus AI

ChatLLM Teams by Abacus AI is a collaborative AI platform that provides access to all state-of-the-art language models, including Claude 3.5 Sonnet, GPT models, and Abacus Smaug, in one unified interface. Abacus AI has also integrated super cool features like creating custom chatbots, chatting with documents via RAG, code generation, and image generation, all for a monthly subscription of $10.

1. Log in to Abacus AI: Navigate to ChatLLM and log in with your credentials, or create an account if you don’t have one.

2. Select the Model: In the LLM selector from the dashboard, choose the OpenAI O1 model from the list of available LLMs. It is rate limited so use wisely!

VS Code via CodeGPT extension

This VS Code extension integrates AI-powered coding assistance directly within their code editor, offering features like code generation, explanation, refactoring, and error-checking. Interact with OpenAI's o1 models within VS Code through this extension.

1. Download CodeGPT from VS Code extensions.

2. Select the model provider as “OpenAI” and the model as “o1-preview” or “o1-mini”,

3. Enter your OpenAI key, and just start using!

That’s all for today 👋

If you enjoyed this tutorial, make sure to subscribe to Unwind AI for more tutorials like this. And don’t forget to share this guide with your friends!

🔗 Stay Connected: Follow us for updates, sneak peeks, and more. Your journey into the future of AI starts here!

Shubham Saboo - Twitter | LinkedIn ⎸

Unwind AI - Twitter | LinkedIn | Instagram | Facebook

Awesome LLM Apps | Sponsor Us