U-M GPT Toolkit In Depth

U-M GPT Toolkit is our most advanced and flexible service offering, providing API gateway access to those who require full control over their AI environments and models. Note that there are costs associated with this service and eligibility for U-M GPT Toolkit differs from other ITS AI Services.

U-M GPT Toolkit is intended to provide Developers with access to our AI Services API gateway so that they can more easily leverage AI capabilities when designing their own customized workflows. While we provide some guidance and documentation on our GitHub repository, it is assumed that Developers who are granted access to the API gateway already have API experience and technical expertise.

Access

Access the U-M GPT Toolkit self-service portal to create and manage your own API keys, assign co-owners, and set monthly quotas. You can also generate keys for:

Toolkit Key Lifecycle

Keys must be renewed annually to help reduce risk by limiting credential lifespan and ensuring access is periodically reviewed. See more about the new Toolkit Key Lifecycle.

Available AI Models

Toolkit provides access to a broad mix of models from OpenAI, Anthropic, Meta, and Google. 

Note that we are actively testing new features and models, so you may occasionally see models in the list that are not yet fully functional.

What You Can Do With U-M GPT Toolkit

Here are some use case examples:

Support

Sensitive Data 

Check the ITS AI Service entry in the Sensitive Data Guide to IT Services for a list of the data types that are permitted to be used with ITS AI Services.

Before using institutional and research data with third-party AI services, carefully review the ITS Safe Computing guidelines.