The use case: how OpenEvidence deploys Baseten
OpenEvidence runs inference for its AI medical search platform on Baseten, serving LLM and embedding workloads for clinicians. It also uses Baseten Training for model training and relies on multi-cloud capacity management to handle traffic spikes.
More reported results
Figures published in Baseten’s case study. They are not independently measured by usedby.
6x faster deployment processes, from multiple engineers spending hours on a deployment to one engineer spending less than an hour
8x+ reduction in infrastructure maintenance time overall
With Baseten Embeddings Inference, we immediately saw 3x speed improvements.
In the customer’s words
Our team spent weeks researching and vetting inference providers. It was a thorough process and we confidently believe Baseten is a clear winner.Baseten helped us train models to be 23x faster and is projected to save us $1.9M—while making the process so easy that even non-ML engineers could get results in under 30 minutes.Baseten supports billions of custom, fine-tuned LLM calls per week from OpenEvidence, serving high-stakes medical information to healthcare providers in every major healthcare facility in the country. If you see a doctor today, chances are that they are leveraging OpenEvidence for up-to-date medical information.No other product lets you launch ten different training jobs on four different datasets. You can sweep anything that you care about to get signal on what’s important. And you only have to pay for compute when you use it, which makes this a scalable process for us. It’s made training so much easier. It would have basically been impossible to do before.Other AI tools used by OpenEvidence
Other public relationships recorded on usedby.
Explore OpenEvidence’s AI stackBaseten users in HealthTech & Digital Health
Companies in the same sector, with public evidence.
See all Baseten customersGo straight to the source
Based on Baseten’s published case study. We check the public evidence; the results are reported by the vendor.
baseten.co- Last checked
- Nov 11, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 78%Checked
Printed word for word on the page, near the name of OpenEvidence.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of OpenEvidence.
- OpenEvidence uses BasetenChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
By using Baseten, OpenEvidence achieved: 78% lower latency, from over 700 milliseconds to 160 milliseconds end-to-end






