Elicit
AI literature search, extraction and systematic reviews with sentence-level citations
Overview
Elicit is an AI research assistant that searches more than 138 million academic papers and 545,000 clinical trials, extracts findings into tables, and writes cited research reports. It also runs screening and extraction for systematic reviews, offers a Research Agent, API and MCP server, and has a free plan with separate academic and industry pricing.
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 These figures reflect RECATOOLS research as of 14 Oct 2026 and may be out of date or incomplete.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.
- Unlimited search across 138M+ papers
- Unlimited summaries and chat with full-text papers
- Limited Research Agent and Research Reports usage
- Import from Zotero
- Export to RIS, CSV, BIB, PDF and DOCX
- Search across 500,000+ clinical trials
- 5 table columns at a time
- Standard Research Agent, Reports and Systematic Review usage
- Systematic Review workflow screening 5,000 papers
- 20 table columns at a time; reports from up to 135 sources
- Routines, custom extractions from uploads, API access
- Standard usage (industry) or 5x usage (academic)
- Figure extraction and interpretation
- Live editing and real-time team collaboration
- 30 table columns; reports from up to 200 sources
- Admin panel with usage tracking and seat management
- Screen 40,000 papers and extract 40 columns
- No training on your data by default
- SSO and SAML, 2FA, domain verification, single-tenancy options
- Dedicated customer success and unlimited API access
Use cases
What you can produce with Elicit
- A list of relevant papers from 138M+ papers and 545,000 clinical trials, found by semantic search
- Extraction tables pulling methods, populations and findings from many papers at once
- Research reports with sentence-level citations back to the source text
- A systematic-review workflow that screens up to 5,000 papers (40,000 on Enterprise)
- Routines that rerun a question and report new evidence as it appears
- Programmatic access through the Elicit API and MCP server on paid plans
Elicit is the most complete AI tool for structured literature work: search, screening, extraction tables and cited reports in one place, with every claim tied to a source sentence. Published studies support it as a second reviewer for data extraction, where it comes close to human accuracy.
Search is the weak link for publication-grade reviews. A 2025 study in Cochrane Evidence Synthesis and Methods found it recovered 39.5% of included studies on average, so it cannot replace database searching. The free plan is genuinely useful, and academic pricing starts at $11 a month billed yearly. A strong accelerator for researchers who check its work.
What we found
Elicit is an AI research assistant for scientific literature. It began inside Ought, a non-profit machine-learning lab, and in September 2023 spun out as an independent public benefit corporation with a $9 million seed round led by Fifty Years. A $22 million Series A at a $100 million valuation, led by Spark Capital and Footwork, followed in February 2025. The company has an office in Oakland, California. It searches more than 138 million papers and, by its own count, 545,000 clinical trials, then turns the results into extraction tables, cited reports and full systematic-review workflows. Since mid-2026 it has added a Research Agent, an API and MCP server, a shared library and Routines that keep a review current.
The accuracy evidence needs reading carefully, and an earlier version of this page got it wrong. Elicit's own May 2026 evaluation on 994 Cochrane reviews reports 95.0% search recall and 96.9% abstract-screening sensitivity. A separate study by Lau and Golder in Cochrane Evidence Synthesis and Methods (September 2025) tested search alone against four completed reviews and found average sensitivity of 39.5%, against 94.5% for the original searches, though Elicit's precision was far higher. Those figures measure different tasks, so they cannot be set against each other.
Extraction looks stronger. One 2025 study in the same journal found 92% precision and recall with four confabulated data points, and a December 2025 paper in Social Science Computer Review put Elicit at 81.4% against 86.7% for human reviewers, a gap that was not statistically significant. Both sets of authors recommend Elicit as a second reviewer, not a replacement.
The free Basic plan includes unlimited search, summaries and paper chat. Paid plans differ by audience: academics pay from $11 a month billed yearly for Plus, while industry Pro costs $49 a month yearly or $75 monthly. For ASEAN researchers working in English-language literature, it is a strong first pass that still needs a conventional database search behind it.
Compiled by RECATOOLS from public sources: vendor documentation and pricing, code repositories and published reporting.
Notable facts
- Elicit has access to over 200 million academic papers via the Semantic Scholar database, one of the largest open academic literature databases in the world.
- The tool can extract specific data columns from a set of papers in seconds — a task that previously required a team of research assistants working for weeks.
- Elicit was built by Ought, a non-profit organisation, with a mission to make rigorous research methods more accessible rather than to maximise revenue.
Frequently asked questions
About this listing
This entry was compiled from publicly available data including Elicit's official website, press releases, documentation, and reputable third-party publications. RECATOOLS is not affiliated with Elicit 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 Elicit directly →
Spotted something out of date? Suggest an update →
Related reading
Health & Wellness
Fine-Particle Air Pollution Linked to Higher Hospital Admission Risk for Up to 21 Days, St...
Health & Wellness
A Guide for New Mothers Missed Its Main Goal but Nearly Doubled Primary Care Visits
Health & Wellness
Only 1 in 32 Young Americans With Opioid Addiction Stayed on Medication for Six Months
More in Research & Data
