# How Sully AI uses Baseten

**90%**: “Sully reports over 90% reduction in inference costs”

As published on [baseten.co](https://www.baseten.co/resources/customers/sully-ai-returns-30m-clinical-minutes-using-open-source/), February 2026. Captured by usedby on 2026-10-09.

- Company: [Sully AI](https://www.usedby.ai/companies/sully-ai.md)
- Tool: [Baseten](https://www.usedby.ai/tools/baseten.md)

## What the story says

Sully.ai moved the inference behind its healthcare AI agents (clinical notes, decision support, medical coding) from closed-source models to open-source models served on Baseten. The aim was lower cost and latency and more control over model quality.

Summary written by usedby from the source page, in English. The figures are those of Baseten and Sully AI, not ours.

> Sully reports over 90% reduction in inference costs by switching from closed-source platforms to open-source models accessed via Baseten. It enabled them to reinvest these savings in the business to improve agents that help provide more value to practitioners and their patients.

- **65%**: “This 65% reduction in median latency resulted in faster, more predictable responses during clinical workflows, improving overall experience for physicians.”
- **29 million**: “December 2025: Sully has added ~29 million minutes to their customers' workforce overall”
- **2.4+ hours**: “2.4+ hours time saving per physician”

> At our scale, inference efficiency matters as much as model quality. Baseten enabled us to cut costs by 90% while delivering significantly faster, more predictable performance. That efficiency is what allows us to add millions of productive minutes back into our customers.
>
> Ahmed Omar, CB=NB/SDER AND CEO

Source: [baseten.co](https://www.baseten.co/resources/customers/sully-ai-returns-30m-clinical-minutes-using-open-source/), captured 2026-10-09.

## What usedby checked

We compared the story with its live page on 2026-10-09.

- Checked: the figure 90% is printed word for word on the page, near the name of Sully AI.
- Checked: the passage quoted above is copied word for word from the page, near the name of Sully AI.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: Sully AI uses Baseten. Confirmed line. Latest check across sources: 2026-10-09.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/sully-ai-baseten · How we check: https://www.usedby.ai/methodology