What is a model?
A model refers to a version of an AI system, each with its own capabilities, behavior, and strengths depending on how it was trained.
What is GPT-4o?
GPT-4o is a highly capable model that can interface with multiple modalities such as text, image, and audio input. GPT-4o is available to Free, Plus, Pro, Team, and Enterprise plans.
What is GPT-4o mini?
GPT-4o mini is a smaller, faster, more efficient version of GPT-4o that is designed to deliver quick responses for a wide range of everyday tasks and questions. It does not have access to the same multimodal tools that are supported by GPT-4o.
Which model should I use?
Choosing a model depends on your use case. Here is a brief overview of the differences between GPT-4o and GPT-4o mini:
GPT-4o
Great model for most tasks.
128k token context length.
Text and image input/output.*
Audio input/output.**
GPT-4o mini
Faster for everyday tasks.
128k token context length.
Text and image input/output.*
Audio input/output.**
Does not have access to advanced tools that GPT-4o has (data analysis, file uploads, vision)
* Read this article for more information about image generation.
** Read this article for more information about voice mode.
ChatGPT Free plan
Users on the Free plan will default to GPT-4o with a limit on the number of messages they can send. The free message limit is based on overall ChatGPT demand. When GPT-4o has reached capacity for free users, they must use GPT-4o mini instead.
Free plan users can use GPT-4o a limited number of times within a five hour window. ChatGPT will inform you once you’ve reached the message limit but you can continue your conversation using GPT-4o mini or by upgrading to Plus or Pro plans.
Free users receive limited access to messages using advanced tools through GPT-4o, such as:
Data analysis
File uploads
Search
Vision
Deep research
Free users can upgrade to Plus or Pro at any time by visiting our pricing page.
ChatGPT Plus, Team, and Pro plans
ChatGPT Plus, Team, and Pro subscribers have GPT-4o access with substantial usage caps.
Plus users can send up to 80 messages using GPT-4o within a three-hour window. We may reduce the limit during peak hours to keep GPT-4o accessible to the widest number of people.
Team workspace users have a higher GPT-4o usage cap than that of ChatGPT Plus.
Pro users have nearly unlimited GPT-4o usage caps.
Please note that unused messages do not accumulate over time. For example, a Plus user cannot accrue a 160 message limit for GPT-4o after waiting six hours.
ChatGPT Enterprise
The ChatGPT Enterprise plan is designed specifically to meet the needs of large enterprises: ChatGPT Enterprise offers enterprise-grade security and privacy, longer context windows for processing larger inputs, unlimited, high speed access to advanced tools like data analysis, and more.
If you'd like to purchase ChatGPT Enterprise for your organization, please contact our sales team.
API Support
GPT-4o and GPT-4o mini are available in the OpenAI API. You can also try out the models with the Playground. To gain API access to both models you must be on at least usage tier 1.