OpenAI o1 mini available to all for free: How can you use it

Last week, OpenAI introduced the o1 model across the world. This advanced model is engineered to tackle intricate tasks in Mathematics, Coding and complex problem-solving. According to the company, future updates will also enable the model to answer PhD-level scientific questions. It will provide solutions to highly specialised and advanced scientific enquiries in th future. The OpenAI o1 model was accompanied by o1-mini. As the name suggests, the OpenAI o1-mini is much cheaper and has limited features as compared to the preview variant. The mini-version is a faster and cheaper reasoning model that is particularly effective at coding.
The o1-mini model features comparable reasoning capabilities, making it an ideal, cost-effective solution for applications prioritising logical reasoning over extensive knowledge. Where ChatGPT Plus and Team users can access o1 models in ChatGPT, the good news is that o1-mini is available to all for free. Both o1-preview and o1-mini can be selected manually in the model picker, and at launch, weekly rate limits will be 30 messages for o1-preview and 50 for o1-mini. Here is how you can use the free version.
Before getting into it, you must know that the OpenAI o1 model is rolling out in a phased manner. Hence, it is possible that it might take a while before it works for you. To use o1-mini, users will have to open ChatGPT from their desktop and initiate a conversation.
Once done, navigate to the top of the window and click “ChatGPT Auto” and select “o1-mini” from the “Alpha Models” dropdown. When done, you will see that the ChatGPT Auto text has been replaced with ChatGPT Alpha.
To switch models on the mobile app, long press on a ChatGPT response and tap “Change model” at the bottom of the context menu. You will see “Alpha [gpt-4o]” model, select to start using the o1-mini version.
OpenAI confirmed that the new o1 model lacks several features that can be found in the ChatGPT 4o model. This initial model has limitations. It cannot browse the internet to solve problems and does not gives you an option to uplaod images. This means that, for now, it can only take text prompts. So, if you think you can just click a picture, upload it here and it solves the problem; you are ahead of time.
In short, the OpenAI o1 version will only help you solve complex math problems and other academic problems that require reasoning.
The company has also stated that it has trained these models to spend more time thinking through problems before it responds, much like a human would. Through training, it learned to refine their thinking process, try different strategies, and recognise their mistakes.