FAQ

HopGPT is a generative AI platform that provides members of the Johns Hopkins University and Medicine community with secure, JHED-authenticated access to multiple Large Language Models (LLMs) like ChatGPT and Claude through a familiar interface.

Your chat prompts and AI-generated responses are purged after 30 days. Please review our Data Retention Notice for more information.

Yes. We host monthly Office Hours on the last Thursday of every month. These hour-long sessions include a presentation on new features and updates, followed by Q&A and community sharing. It’s a great opportunity to learn, ask questions, and connect with other HopGPT users across Johns Hopkins. Learn more about Office Hours

Models options available through HopGPT can (and do) change frequently. Each has its own strengths and weaknesses. When making your selection, we include subtitles to highlight each model’s strengths. A web search, given your use case, for example, “best llm for document summary,” might reveal GPT-5.5 or Claude Sonnet 4.5 as an excellent choice. Please visit Choosing a Model in HopGPT for more information.

The Sheridan Libraries has assembled a number of AI literacy resources. Please visit Artificial Intelligence for Research & Scholarship.

Yes, please refer to the glossary in the New to AI section of GenAI website.

While HopGPT is approved for sensitive data, including PHI and PII, you must act in a manner consistent with appropriate use of PHI / PII and be a responsible steward of the data you enter into and collect from HopGPT. In accordance with Johns Hopkins University and Johns Hopkins Medicine policies, you should always minimize the amount of sensitive information used to accomplish your intended goal.

HopGPT is safe to use with sensitive data, including student information, but should not be used to perform student-related academic assessments as inputs and outputs are only retained for 30 days. Further, you are responsible for acting in a manner consistent with the Terms of Use and applicable Johns Hopkins University and Medicine policies.

The exact file size varies due to the way in which the content inside your file is tokenized, or transformed from images and text into tokens, which are readable by the model. Generally, files up to several MB can be processed, but larger files may need to be split or summarized.

Limits:

• Limits vary by model, typically ranging from about 50,000 to 200,000 tokens.
• A token is roughly 4 characters or 3/4 of an English word.
• For example, in HopGPT, Claude Sonnet of 50,000 tokens, while Llama Maverick can handle up to 1,000,000 tokens.

Longer documents may need to be summarized or split into smaller chunks. HopGPT can analyze large files but may not be able to hold the entire content in its “memory” at once.

Responses in HopGPT do not generate file downloads such as .docx, .pdf, or .pptx like other chatbots you may be familiar with. Currently, you may export your chat to .png, .txt, .md, .json, or .csv. To do so, click the Export button:

ChatGPT Edu is available to faculty and staff in the Whiting School of Engineering. Key differences from HopGPT include:

• Access to additional OpenAI models
• Ability to create and share custom GPTs or assistants with your team or department

ChatGPT Edu requires an annual subscription and does not provide access to models outside of the OpenAI portfolio. For more information about this service, please contact [email protected].

HopGPT is a product governed by several organizations. To request consideration of an additional model, email [email protected]. Be sure to include your use case in your correspondence.

API access to models available through HopGPT is available by request through the API Key Request Form.

We have released a pilot version of our Agent Builder, which allows users to create custom AI agents and assistants tailored to their specific needs. This feature is currently available to a select group of users as we gather feedback and refine the experience. If you are interested in joining the pilot program and gaining early access, please email us at [email protected].

What is a context window limit?

A context window is the amount of information an AI model can actively “remember” at one time. When a discussion becomes very long, earlier parts may fall outside this window and are no longer considered when generating responses. 

Why does this happen?

This is a technical limitation of the AI model itself. Every AI model has a maximum amount of text it can process at once. Once that limit is reached, older content must be dropped to make room for new messages. 

What might I notice when the limit is reached?

You may see things like: 

• The AI forgetting earlier details 
• The AI asking for information already discussed 
• Responses that seem to ignore older context 

This does not mean anything is broken — it just may not be ideal for what you’re attempting to do.

How can I work around this?

Keep your chat short and stick to one topic per chat. You may engage in multiple chats at once! If you have multiple scenarios to explore, we recommend using HopGPT’s Forking tools.

Forking tools allow you to explore different scenarios through multiple chats while preserving relevant context. These options will appear each time the model responds to your prompt.

Fork: Visual Messages Only

Use this when:

• Your conversation relies heavily on screenshots or diagrams 
• You want to remove long text history

Fork: Include Related Branches

Use this when:

• You have multiple connected threads 
• You want continuity without clutter

Fork: Include All to/from Here

Use this when:

• The conversation is very long 
• You want a clean restart with full context

Our platform supports a variety of commonly used file formats. Below is a quick guide to each file type, what it’s typically used for, and any important notes. 

Multi-Conversation Mode allows you to compare AI responses side by side in real time. When you send a message, two different models process your request simultaneously, displaying their outputs in parallel columns. This helps you evaluate different perspectives, compare writing styles, or find the best answer for your needs.

Why would I use this feature?

• Compare model capabilities – See how different models handle the same prompt 
• Get diverse perspectives – Receive varied approaches to creative or analytical tasks 
• Test accuracy – Cross-reference responses for research or fact-checking 
• Evaluate tone and style – Find which model best matches your communication needs 
• Experiment with agents – Compare how specialized agents approach domain-specific questions

Which Models can I combine?

You can pair any two models and/or agents that are currently available in the model selection dropdown.

Where do I enable Multi-Conversation Mode?

1. Select your first model and select your second model from the dropdown
2. Click the multi-conversation mode icon located next to the model selection dropdown  
3. Select the second model that you would like to utilize from the model dropdown