Alert! As of October 14, 2025, PhoenixAI users will be able to choose between three GPT models: GPT-4.1, GPT 5.0, and o3. These GPTs are best suited for different operations as they function slightly differently.
GPT-4.1 Features
- The standard GPT automatically selected when opening the PhoenixAI tool.
- A 50 prompt limit allows users to ask frequent questions and gather information.
- Prompts are evaluated once and the resulting answers are provided to the user.
- Users may upload files to ask questions about.
- Users may create custom Assistants for specific localized sources of information.
Recommendation: This model is most useful to anyone who has a large variety of questions that need to be answered quickly. This GPT is great for most tasks.
GPT-5.0 Features
- Alternative model that must be selected via the dropdown menu.
- Restricted for PHI users.
- When the 5.0 model is selected, a message at the bottom displays directly above the prompt message box related to information that should not be entered.
- Aligning with GPT 4.1, there is a 50 prompt limit per day.
- Users may upload files to ask questions about.
- Users may create custom Assistants for specific localized sources of information.
- Optimized for coding and complex reasoning.
Recommendation: This model will be most useful to anyone who has a large variety of coding or complex reasoning questions that need to be answered in a timely manner.
o3 Features
-
- Alternative model that must be selected via the dropdown menu.
- Alternative model that must be selected via the dropdown menu.
- When the o3 model is selected, a message at the bottom displays directly above the prompt message box related to information that should not be entered.
- Restrictions for non-faculty users limit the amount of information that can be acquired in one day.
- 50 prompt limit for faculty, 10 prompt limit for all other users
- Prompts will be evaluated multiple times by the model to ensure a correct response.
- This model does not support uploading files (attachment icon does not display).
- Assistants cannot be created using the o3 model.
- Optimized for science, coding, and mathematical reasoning.
Recommendation: This model is most useful to professors and researchers who have limited questions that require precise answers. This model prioritizes response accuracy and advanced reasoning.