Consensus

Consensus is an academic search engine that finds, ranks and synthesizes peer-reviewed research, returning evidence-backed answers with inline citations. The homepage states it draws on 250M+ research papers including licensed full text from leading publishers, while the product sidebar and the vendor machine-readable file both say 200M+, so the vendor is inconsistent on its own corpus size. Sources include Semantic Scholar, OpenAlex, PubMed and publisher feeds, with licensed content from Wiley, Taylor and Francis, Sage, ACS Publications, the American Psychological Association, De Gruyter Brill and AAAS. Consensus was founded in 2021 by Christian Salem and Eric Olson. Best fit: researchers, clinicians and students who need evidence drawn only from the peer-reviewed literature. The Consensus Meter answers a yes-or-no research question by showing how far the evidence agrees or disagrees. Deep Search builds a search strategy on its own, expanding key terms, identifying conflicting arguments and exploring the citation graph. Medical Mode narrows results to roughly 50,000 clinical guidelines and 8M articles from the top 1,000 medical journals. Over 170 university libraries partner with Consensus for student and faculty access, and the vendor reports 10 million researchers, students and clinicians using it. Institutions named on the site include Michigan, Rice, Virginia, Carnegie Mellon, Kansas, Texas A&M, William & Mary, Vanderbilt, McGill, Cardiff, Lucerne and Virginia Tech. Consensus publishes an official Model Context Protocol server at mcp.consensus.app/mcp, which its own documentation calls the recommended surface for any LLM client and names Claude Desktop, Claude Code, Cursor, Codex and ChatGPT among those clients. The server exposes the same primitives as the REST API. A Consensus Search API is available on approval at $0.10 per request with rate limits. Zotero libraries can be imported into My Library for search and analysis, although that import is one-way rather than a bidirectional citation sync. A Chrome extension provides browser-based access. Pricing is in USD and the pricing page carries a monthly and annual toggle, with the annual view selected by default. Free costs nothing and includes 15 Pro messages and up to 3 Deep reviews per month. Pro is $12 per month billed annually at $144 per year, against $20 per month month to month, and lifts the allowance to unlimited Pro messages and 15 Deep reviews. Deep is $45 per month billed annually at $540 per year, against $65 month to month, and raises Deep reviews to 200. Teams is $30 per seat per month for up to 200 seats, adding 50 Deep reviews and centralized billing. Enterprise is quoted rather than published. Students and faculty receive 40% off and clinicians 25% off with verification. What the entry tier does not buy is Deep Search volume. The distance between Pro at 15 Deep reviews and Deep at 200 is the reason to move up, and the advertised annual saving is 40% on Pro but 31% on Deep, so the headline does not apply evenly across tiers. Consensus also searches only peer-reviewed literature and cannot reach the open web, company reports or news. Perplexity AI ($17/mo billed annually) covers both web and academic sources, ChatGPT Deep Research ($20/mo) and Gemini Deep Research ($19.99/mo) handle cross-domain work, and SciSpace ($12/mo billed annually) and Elicit ($49/mo billed annually) target structured systematic review. Current state Q3 2026: Consensus publishes no third-party security certification, and none is claimed on any surface reviewed. Its privacy policy states plainly that it does not use customer data to train large language models, that the commitment extends to every vendor relationship it maintains, and that it does not send user data to third parties for training. The same policy states that Consensus is not subject to the California Consumer Privacy Act, so no CCPA claim is recorded on this listing. Buyers who require SOC 2 or ISO 27001 documentation for procurement will not find it published.