Elicit

Elicit is the AI research assistant purpose-built for systematic literature reviews, serving 5M+ researchers globally, including teams at NASA, NIH, the U.S. CDC, Harvard, Stanford, Yale, Google, Johnson & Johnson, Takeda, Unilever, and the Gates Foundation. The platform searches 138 million academic papers and 545,000 clinical trials from Semantic Scholar, PubMed, and other academic databases, then autonomously extracts structured data (methodology, sample size, findings, limitations) from each paper for cross-study comparison. Founded as a Public Benefit Corporation in Oakland, California by Andreas Stuhlmuller, Elicit is designed around the end-to-end systematic review workflow: researchers define a question, and Elicit finds relevant papers, extracts key claims, synthesizes findings across studies, and generates structured reports with citations. More than 40 named enterprise and institutional customers are documented on the customer stories page, spanning biotech, pharma, government agencies, and research universities. Elicit publishes an official MCP server at elicit.com/api/mcp, letting Claude Desktop, Claude Code, and any MCP-compatible client access its capabilities programmatically. A full REST API provides endpoints for paper search, clinical trial search, report generation, and systematic review workflows, with API access included on the Pro tier. Zotero import is available on the free tier for bibliography management. The platform integrates with Semantic Scholar and PubMed as primary data sources, with additional academic databases providing supplementary coverage. Notable gap: no native integration with Mendeley, EndNote, or Overleaf for bidirectional reference sync, and no Zapier or Make connectors for automation with non-research tools. Elicit's pricing was restructured in 2025/2026 around three individual tiers plus enterprise. Basic (Free) provides limited Research Agent access, 2 automated reports per month, unlimited search across 138M papers, unlimited paper summaries, unlimited chat with papers including full-text access, and Zotero import. Pro at $49/month ($588/year, a 35% annual saving) provides extended Research Agent access, a dedicated systematic review workflow that can screen 5,000 papers, 144 reports or systematic reviews per year, API access, custom extractions from uploaded papers, explanations for AI-generated answers, multiple output templates, and 10 personalized research alerts. Scale at $169/month ($2,028/year, a 39% annual saving) adds 5x usage across the Research Agent, reports, and systematic reviews for collaborative teams. Enterprise pricing is custom. The earlier Plus and lower-priced Pro plans no longer appear on the pricing page. Elicit is designed exclusively for academic and scientific literature and cannot search the open web, company reports, news, or non-peer-reviewed sources. Perplexity AI ($17/mo billed annually) provides both web and academic search for broader source coverage. ChatGPT Deep Research ($20/mo) and Gemini Deep Research ($19.99/mo) handle cross-domain research without the academic-only constraint. Consensus ($12/mo billed annually) offers a lower-cost entry point for academic search with the Consensus Meter for agreement synthesis, though without dedicated systematic review workflows. SciSpace ($12/mo billed annually) provides multiple specialized agents including a Biomedical Agent and PRISMA support at lower cost for researchers not needing the systematic review depth that justifies the $49/month Pro tier. The jump from 2 free reports per month to Pro at $49/month is a significant gap for researchers needing moderate but not intensive systematic review access. Elicit raised $22M in a Series A (February 2025) led by Spark Capital and Footwork at a $100M valuation, bringing total funding to $31M. SOC 2 Type II certification was achieved in October 2025, with audit reports available under NDA. The official MCP server at elicit.com/api/mcp integrates with Claude Desktop, Claude Code, and all MCP-compatible clients. The platform now serves 5M+ researchers (up from 400,000 at the Series A), with 40+ named enterprise and institutional customers on the customer stories page, including NASA, NIH, the U.S. CDC, Harvard, Stanford, Yale, Google, Johnson & Johnson, Takeda, Unilever, Fresenius, RAND Corporation, and the Gates Foundation. The corpus expanded to 138M papers and 545,000 clinical trials. Pricing was restructured from the earlier Plus/Pro model to a Basic (Free), Pro ($49/month), and Scale ($169/month) structure.