# How OpenEvidence uses Baseten

**78%**: “78% lower latency, from over 700 milliseconds to 160 milliseconds end-to-end”

As published on [baseten.co](https://www.baseten.co/resources/customers/openevidence-delivers-instant-medical-information-with-baseten/), September 2025. Captured by usedby on 2026-10-05.

- Company: [OpenEvidence](https://www.usedby.ai/companies/openevidence.md)
- Tool: [Baseten](https://www.usedby.ai/tools/baseten.md)
- Teams: Engineering, Research

## What the story says

OpenEvidence, a medical technology company, runs the inference for its AI-powered medical search platform on Baseten, including embeddings inference, multi-cloud compute capacity, and model training. This lets clinicians get medical information at the point of care without the team managing its own inference infrastructure.

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

> By using Baseten, OpenEvidence achieved: 78% lower latency, from over 700 milliseconds to 160 milliseconds end-to-end

- **6x**: “6x faster deployment processes, from multiple engineers spending hours on a deployment to one engineer spending less than an hour”
- **8x+**: “8x+ reduction in infrastructure maintenance time overall”
- **3x**: “With Baseten Embeddings Inference, we immediately saw 3x speed improvements.”

> Our team spent weeks researching and vetting inference providers. It was a thorough process and we confidently believe Baseten is a clear winner.
>
> Eric Lehman, Head of Clinical NLP

## What usedby checked

We compared the story with its live page on 2026-10-05.

- Checked: the figure 78% is printed word for word on the page, near the name of OpenEvidence.
- Checked: the passage quoted above is copied word for word from the page, near the name of OpenEvidence.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: OpenEvidence uses Baseten. Confirmed line. Latest check across sources: 2026-10-05.
- Not checked: the result itself. We quote it; we did not measure it.

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