OpenEvidence
Cited clinical answers for verified doctors, paid for by advertising
Overview
OpenEvidence is a medical AI platform that answers clinicians' questions with references to licensed sources including NEJM, JAMA, Cochrane and NCCN guidelines. It is free for clinicians verified by NPI in the US or MINC in Canada and is funded by advertising. Since September 2026 users choose between the Osler, Sackett and Snow models by how long they can wait.
Pricing
Pricing shown for reference only. These figures reflect RECATOOLS research as of 14 Oct 2026 and may be out of date or incomplete. This is not financial or purchasing advice — always confirm the current price on the provider’s official website before making any decision.
Use cases
What you can produce with OpenEvidence
- A cited answer to a clinical question, with references to licensed journals and guidelines
- A choice of depth: Osler in about 5 seconds, Sackett in about 30, or a Snow literature report in about 5 minutes
- EvidenceGrade ratings of how strong the evidence behind an answer is
- Accredited CE and MOC credit earned from routine clinical searches
- Answers launched from inside Epic at participating health systems
- A HIPAA-compliant dialer for telemedicine calls, messaging and faxing
ASEAN Perspective
OpenEvidence in Southeast Asia
OpenEvidence is effectively US-only in practice: access requires a US National Provider Identifier (NPI), which ASEAN and broader APAC clinicians do not hold, blocking the automated verification pathway. The company's published expansion roadmap targets English-speaking markets first (UK, Canada, Australia) with no stated timeline for Southeast Asian or broader APAC rollout, and no localization for regional clinical guidelines (MOH Singapore, Thai FDA, BPOM Indonesia, etc.). Data residency is US-centric with no disclosed PDPA, HIPAA-equivalent, or regional data-sovereignty arrangements for APAC users. Until OpenEvidence opens a non-NPI verification path and integrates ASEAN guidelines, clinicians in Singapore, Malaysia, Indonesia, the Philippines, Thailand, and Vietnam will find it of limited practical utility — though the free access model and quality standard it sets is closely watched by regional health-tech players and investors.
OpenEvidence is the easiest way for a verified clinician to get a referenced answer fast: it is free, the licensed sources are strong, and the Osler, Sackett and Snow models let you trade speed for depth. EvidenceGrade and accredited CE credit make routine use more defensible.
The limits are real. Outside testing on hard subspecialty questions found accuracy below 50%, a small study found it mostly confirms plans rather than changing them, and the business runs on pharmaceutical-adjacent advertising. Use it to find and check evidence, not to make the decision; it is closed to anyone who cannot verify as a clinician.
What we found
OpenEvidence is a clinical question-answering service for doctors, run by OpenEvidence Inc. of Miami and led by founder and chief executive Daniel Nadler, who previously built Kensho. A clinician types a question or a case and gets a written answer with numbered references, drawn from licensed content that its about page lists as NEJM, JAMA and the JAMA Network, Nature, Cochrane and NCCN treatment algorithms, joined in 2026 by Wiley, Springer Nature and Sage. It is free to clinicians who verify their identity, with an NPI in the US and, since September 2026, a MINC number in Canada. Advertising pays for it, and its advertising policy says ads run on a system kept separate from the answers.
In September 2026 the old consult modes became a family of named models. Osler answers in about five seconds, Sackett in about thirty, and Snow, the successor to Deep Consult, in about five minutes. A fourth, Darwin, is available by application only; the company says it scored 100% on MedQA, which is its own result. Around them sit EvidenceGrade ratings of the cited evidence, accredited CE and MOC credit, a telehealth dialer and Epic launch at health systems such as Northwestern Medicine.
Outside tests are more sobering. A medRxiv preprint from December 2025, not yet peer-reviewed, put 100 subspecialty board-style questions to it and found best accuracy of 41% for Deep Consult and 34% for the quick mode, although eleven general models had scored between 14% and 46% on the same question set in earlier work. A small 2025 study of five primary-care cases rated its answers highly for clarity and relevance but found they mostly confirmed what the physicians already planned. In a Sermo poll, 44% of doctors named accuracy as their main concern.
Valuations climbed fast: $1 billion in February 2025 and $12 billion in January 2026, per CNBC. Its trade-secrets suit against Doximity in Massachusetts federal court continues, with parts of both sides' claims allowed to proceed.
Compiled by RECATOOLS from public sources: vendor documentation and pricing, code repositories and published reporting.
Notable facts
- OpenEvidence's AI model scored 100% on the US Medical Licensing Examination (USMLE) in 2025 — the first clinical AI to achieve this benchmark.
- CEO Daniel Nadler previously built Kensho, an AI company acquired by S&P Global for ~$550 million — he has now applied the same literature-synthesis playbook to medicine.
- The platform generates revenue through pharmaceutical advertising at CPMs of $70–$1,000+, orders of magnitude higher than social media CPMs, targeting prescribing physicians at the moment of clinical decision-making.
- By early 2026, a physician aboard a commercial flight used OpenEvidence mid-air to determine whether a passenger's immunosuppression warranted an emergency landing — an anecdote that circulated widely in medical communities.
Frequently asked questions
About this listing
This entry was compiled from publicly available data including OpenEvidence's official website, press releases, documentation, and reputable third-party publications. RECATOOLS is not affiliated with OpenEvidence unless explicitly stated.
Third-party AI tools update their pricing, features, availability, and policies frequently. Information here may be outdated by the time you read this — we make reasonable efforts to keep listings current, but cannot guarantee absolute accuracy.
For the latest details, please refer to OpenEvidence directly →
Spotted something out of date? Suggest an update →
Related reading
Health & Wellness
Brown Fat Linked to Less Diabetes, Heart Disease and Depression in Scans of 101,243 Cancer...
Health & Wellness
Malaysia's MediAsas Medical Plan Launches in January, With Premiums Payable From EPF
Health & Wellness
WHO Does Not Recommend Obesity Drugs for Under-10s and Sets Strict Conditions for Teenager...
Alternatives to OpenEvidence
More in Research & Data
