Consensus
AI search engine that shows what the research says
Overview
Consensus is an AI search engine for scientific literature. Ask a question and it synthesises a cited answer from peer-reviewed papers, with a Consensus Meter showing how far studies agree on yes/no questions. There is a free tier, plus Pro ($12 a month billed annually, $20 monthly) and Deep ($45 annually, $65 monthly).
Pricing
Pricing shown for reference only. These figures reflect RECATOOLS research as of 12 Oct 2026 and may be out of date or incomplete.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.
- 10 Pro messages a month
- Up to 3 Deep reviews a month
- Unlimited Pro messages
- 15 Deep reviews a month
- All research tools
- 500 API and MCP uses a month
- Everything in Pro
- 200 Deep reviews a month
- 2,000 API and MCP uses a month
- Up to 200 seats
- 50 Deep reviews a month
- Centralised billing
- Consensus Search API
- SAML SSO
- Research-library integration
- Dedicated support
Use cases
What you can produce with Consensus
- Cited answers synthesised from academic papers
- A Consensus Meter showing how far studies agree on yes/no questions
- Deep Search literature reviews that follow the citation graph
- Medical mode for clinical guidelines and leading medical journals
- Figures and tables pulled from cited papers and a Research Gaps Matrix
- Connectors for ChatGPT, Claude and Microsoft 365 Copilot
Consensus answers research questions from academic literature rather than the open web: a cited synthesis, natural-language filters for population, design and time frame, and a Consensus Meter showing how far studies agree. Deep Search runs a longer review pass, and Medical mode narrows to clinical sources.
Like any AI summary layer it can flatten nuance, so open the cited papers before relying on a claim. The free tier allows ten Pro messages a month; Pro is $12 a month billed annually, and Deep at $45 suits heavy reviewers.
What we found
Consensus is an AI search engine for academic literature from Consensus NLP, Inc., a San Francisco company led by co-founders Eric Olson and Christian Salem, who started it in 2021. You ask a research question in plain English; it retrieves papers and writes a cited synthesis of what they found. The corpus draws on Semantic Scholar and OpenAlex plus full-text deals with publishers including Wiley, Taylor & Francis, Sage and the APA, and the vendor's own count ranges from 200 million to 250 million papers depending on the page.
The feature people remember is the Consensus Meter: ask a yes-or-no question and it shows how far the retrieved studies agree. Filters can be written straight into the prompt, covering time frame, population and study design; a Medical mode narrows results to clinical guidelines and leading medical journals; and Deep Search runs a longer literature-review pass that expands search terms and follows the citation graph. Recent additions include figures and tables pulled from cited papers, a Research Gaps Matrix, ready-made Skills workflows, and connectors for ChatGPT, Claude and Microsoft 365 Copilot. OpenAI published a customer story in October 2025 about Consensus building its agent on GPT-5; that is partner marketing, not independent testing.
The free tier gives basic search, ten Pro messages and up to three Deep reviews a month. Pro costs $12 a month billed annually or $20 monthly, with unlimited Pro messages and 15 Deep reviews; Deep is $45 a month annually or $65 monthly for 200. Teams starts at $20 a seat billed annually. Students, faculty and US clinicians can get up to 40 per cent off. Earlier versions of this page listed older, lower prices and a more generous free tier.
In May 2026 Consensus raised $30 million led by GreatPoint Ventures, and the company puts total funding at $45 million. The usual caution applies: a short synthesis can smooth over study quality and context, so open the cited papers before you quote a finding.
Compiled by RECATOOLS from public sources: vendor documentation and pricing, code repositories and published reporting.
Notable facts
- Consensus can answer 'Does melatonin help with sleep?' by analysing 300+ clinical trials and presenting the consensus percentage — in seconds rather than hours of manual literature review.
- The platform's training dataset includes papers from PubMed, Semantic Scholar, and arXiv, covering medicine, biology, psychology, economics, and computer science.
- Consensus was built because the founders noticed that most people form opinions on health and policy questions without access to what the scientific evidence actually says.
Frequently asked questions
About this listing
This entry was compiled from publicly available data including Consensus's official website, press releases, documentation, and reputable third-party publications. RECATOOLS is not affiliated with Consensus 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 Consensus directly →
Spotted something out of date? Suggest an update →
Consensus in the news
Finance
Bitcoin Breaks $80,000 on the Eve of Consensus 2026 as ETF Inflows Hit $1.97 Billion in Ap...
Science
Fossil From Fujian Suggests Some of the Earliest Birds Had Already Given Up Flying
Health & Wellness
Fine-Particle Air Pollution Linked to Higher Hospital Admission Risk for Up to 21 Days, St...
Alternatives to Consensus
More in Research & Data
