Consensus
AI search engine that shows what the science actually says
Overview
Consensus is an AI search engine for scientific literature: ask a question and it synthesizes an answer from 220M+ peer-reviewed papers with citations and a Consensus Meter showing what share of studies agree. Runs on GPT-5; free tier plus Pro ($10/mo) and Deep ($45/mo).
Pricing
Pricing shown for reference only. These figures reflect RECATOOLS research as of 11 Jul 2026 and may be out of date or incomplete.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.
- 15 Pro messages/mo
- 3 Deep Searches/mo (50 papers each)
- Basic AI summaries
- Unlimited Pro Searches
- 15 Deep Searches/mo
- Student rate $6/mo
- 200 Deep Searches/mo
- Everything in Pro
- Priority processing
Use cases
ASEAN Perspective
Consensus in Southeast Asia
ASEAN-region availability and pricing notes coming soon. Drop the editorial team a note via /contact/ if you can supply local context (Singapore/Malaysia/Indonesia/Thailand/Vietnam).
Consensus answers research questions by pulling from peer-reviewed literature rather than the open web: type a question, get a synthesized answer with citations, a Consensus Meter showing what share of studies actually agree, and filters for study type, year, and citation count. It runs on GPT-5 via OpenAI's Responses API and indexes 220 million-plus papers, updated weekly, which OpenAI has cited as a flagship case for compressing weeks of literature review into minutes. It's genuinely useful for clinicians, journalists fact-checking claims, and students doing rapid scoping — but coverage skews toward what's indexed and open-access, and like any AI layer it can flatten nuance, so high-stakes claims still need a primary-source check. Free tier covers casual use; Pro ($10/mo) and Deep ($45/mo) unlock more Deep Searches for frequent reviewers. A fresh $30M raise in May 2026 funds a push beyond search toward a full research workflow.
What people say
220 million peer-reviewed papers, updated weekly, is the number Consensus leads with — and OpenAI itself has cited the product as a flagship case for GPT-5's Responses API, framing it as a tool that compresses weeks of literature review into minutes.
Clinicians, journalists, and grad students are the core audience, and the appeal is specific: instead of a list of paper titles, Consensus returns a direct answer with a Consensus Meter showing what percentage of the indexed studies support, contradict, or split on a claim. Filtering by study type — RCT, meta-analysis, cohort — and citation count lets users triage quickly, and the Copilot feature strings several papers together into a longer synthesis rather than a one-line answer.
Pricing stayed approachable: a free tier with 15 Pro messages and 3 Deep Searches a month, Pro at $10/mo for unlimited Pro Searches plus 15 Deep Searches, and Deep at $45/mo for 200 Deep Searches aimed at people doing frequent literature reviews. Students get a 40% discount, bringing Pro down to $6/mo.
The catch that shows up across AI research tools generally, and applies here too: coverage leans toward what's indexed and open-access, so a clean 'consensus' on a niche or newly published question can mean thin underlying data rather than settled science. It's a fast way to ground a claim in literature, not a substitute for reading the actual paper on anything that matters. A $30M raise in May 2026, led by GreatPoint Ventures with DJ Patil joining the board, is now funding an expansion beyond search into a broader research workflow.
Summary of public user & expert reviews, compiled by RECATOOLS.
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 →
More in Research & Data
