If you're on a paid ChatGPT plan (ChatGPT Plus, Team, or Enterprise), you can switch between our default model, GPT-4 mini, GPT-4, and GPT-4o.

The OpenAI o1-preview and o1-mini models are a new series of reasoning models for solving hard problems. This is a preview and we expect regular updates and improvements. While GPT-4o is still the best option for most prompts, the o1 series may be helpful for handling complex, problem-solving tasks in domains like research, strategy, coding, math, and science.

For most use cases, especially those that involve the use of tools and vision, we recommend using GPT-4o in ChatGPT. Please note the following limitations on the OpenAI o1-preview and o1-mini models in ChatGPT:

GPT-4o is OpenAI's new flagship model that can reason across audio, vision, and text in real time. GPT-4o is available in ChatGPT and the API as a text and vision model (ChatGPT will continue to have support for voice via the pre-existing Voice Mode feature) initially. Specifically, GPT-4o is available in ChatGPT Free, Plus, Team, and Enterprise, and in the Chat Completions API, Assistants API, and Batch API.

GPT-4o mini is also our fastest model. It's great for everyday tasks. This model is available to all users. Free users that reach rate limits with GPT-4o will be automatically switched to GPT-4o mini. Unlike GPT-4o and GPT-4, tools such as data analysis and file uploads are not available.

GPT-4 is great for tasks that require creativity and advanced reasoning. This model is available to ChatGPT Plus, Team, and Enterprise users. GPT-4 will also allow you to generate images with DALL•E 3.

Check out our ChatGPT — Release Notes for the latest updates on ChatGPT.