#  New AI API offerings available through Harvard’s API Portal 

 





May 27, 2025

 

 

In addition to the current [suite of AI tools that HUIT offers](https://www.huit.harvard.edu/ai/tools), new API-based solutions are now available to help developers and researchers integrate AI into their work more efficiently. APIs are a scalable and practical option for embedding AI into systems, scripts, or applications.

These [expanded AI API offerings](https://www.huit.harvard.edu/ai-developer-tools) streamline access and eliminate the need to set up individual accounts with providers and handle payments and reimbursements. AI APIs can be accessed securely through the [API Portal](https://portal.apis.huit.harvard.edu/apis?ci=4c6efb90-d349-4050-9944-3f90f533b0bb) (HarvardKey sign-in required) in the following ways, depending on your School/Unit affiliation:

- **Pay-as-you-go:** Pay for your usage as you go; requires a HUIT Billing ID. 
    - [AWS Bedrock API](https://www.huit.harvard.edu/portal.apis.huit.harvard.edu/docs/ais-bedrock-llm/1/overview) for interactions with the Anthropic, Meta, and Mistral models.
    - [Google Gemini API](https://portal.apis.huit.harvard.edu/docs/ais-gemini-llm/1/overview) for interactions with Flash 2.5 Pro, Flash 2.0 lite, embedding-005, and all other Gemini models.
    - [OpenAI Direct API](https://portal.apis.huit.harvard.edu/docs/ais-openai-direct/1/overview) for interactions with all of the OpenAI models.
    - [OpenAI via Azure](https://portal.apis.huit.harvard.edu/docs/ais-azure-openai/1/overview) for interactions with the OpenAI models hosted in the HUIT Azure account.
- **Credit-based access:** Work within a predetermined set of OpenAI credits; limited availability.
    - [OpenAI “Community Developer" API](https://portal.apis.huit.harvard.edu/docs/ais-openai-direct-limited/1/overview)**:** $10/month in OpenAI API credits for students, faculty, staff, and researchers in FAS and Harvard College.
    - [OpenAI Credit Redemption APIs](https://portal.apis.huit.harvard.edu/apis?search=LLM) for approved administrative, research, and teaching & learning use cases in FAS, SEAS, and Central Administration.

If you are considering using Generative AI tools for Harvard work, you must [follow the University’s initial guidelines for use](https://huit.harvard.edu/ai/guidelines). For additional guidance on these and other AI offerings, [request a consultation with HUIT](https://harvard.service-now.com/ithelp?id=submit_ticket&sys_id=3f1dd0320a0a0b99000a53f7604a2ef9).