Skip to main content
usedby
Search tools, companies

How OpenEvidence uses Baseten

78%

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

As published on baseten.co, September 2025. Captured by usedby on Oct 5, 2026.

What happened

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.

  • 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.”

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

From the page. baseten.co, captured Oct 5, 2026

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, OpenEvidence. Source, captured Oct 5, 2026

What the story claims, and what we checked

We compared the story with its live page on Oct 5, 2026.

  • The figure: 78%CheckedPrinted word for word on the page, near the name of OpenEvidence.
  • The passage quoted aboveCheckedCopied word for word from the page, near the name of OpenEvidence.
  • The publication dateCheckedRead from the page’s own metadata, never guessed.
  • OpenEvidence uses BasetenCheckedConfirmed line. Latest check across sources: Oct 5, 2026.
  • The result itselfNot checkedWe quote it; we did not measure it.

Same company, same tool or same industry.

< 10msSearch latency with high recallOpenEvidence uses Zilliz. Another tool at OpenEvidence3x“3x cost savings when moving from closed-source to open-source models”Parallel Web Systems uses Baseten. Another customer of Baseten60%“~60% reduction in inference costs”EliseAI uses Baseten. Another customer of Baseten