Home / Research & science / Elicit
Elicit Research, PBC (Covina, United States)Elicit
AI research assistant that searches literature and puts results into tables: for each article, the population, method and outcome side by side. Includes a workflow for systematic reviews with screening of thousands of papers.

- Provider based outside the EU
Last checked: 27 October 2026 · How we check
Is this your tool? Fill in missing detailsWhat it does
Research Agent: reports and tables with sources
Semantic search across papers and clinical trials
Research Reports per paper and topic
Summaries and chat with papers
Tables with custom columns and extractions
Routines to keep track of new researchComparable in research & science
Cradleon request (licence, no royal…
ASReview LABfree (open source)
Scholarcyfree Article Summarizer (1 same…
SciSpacefree plan
Keeniousfree plan (3 conversations per day)
Castoron requestmodel providers are not named; Elicit states it does not train on user data and says its model providers have a zero-retention agreement, plus a SOC 2 Type II report. Servers in the US, no EU hosting promised. Many tools build on a large model from, for example, OpenAI or Anthropic. If in doubt, ask for the data processing agreement: it states where your data goes.
Questions about Elicit
- Which AI model does Elicit use?
- The provider of Elicit does not disclose which AI model sits underneath. Model providers are not named; Elicit states that it does not train on user data and that its model providers have a zero-retention agreement, plus a SOC 2 Type II report. Servers in the US; no EU hosting committed.
- How much does Elicit cost?
- free Basic; Pro $49 p/m ($588 p/yr); Scale $169 p/m ($2,028 p/yr); Enterprise on request. Check the current price on the provider's website; prices change often.
- Who is Elicit for?
- Elicit is aimed at research & science. It fits work such as literature searching and exploration using semantic search and citation networks, screening titles, abstracts and full texts for systematic reviews, and extracting and summarising data and study characteristics from papers.
- What should I look out for with AI in research & science?
- Never use AI as a source: every reference must be traceable to the original article, as fabricated or wrongly attributed citations are the most common error. Unpublished data, research proposals and peer-review manuscripts are confidential or commercially sensitive, so do not enter them into a consumer account without a data processing agreement, and check whether the provider stores your input or uses it for training (publishers usually prohibit this explicitly for peer review). If you work with personal data from research participants, the GDPR and your own ethics review apply: running models locally or using an EU-hosted tool with data minimisation is then the safe route. Finally, document your search strategy and your AI use: journals and funders increasingly ask for this, and a review must remain reproducible.
Every Friday: what changed in AI for research & science
New models, prices, oversight and tools, with sources and what it means for you. One email a week, unsubscribe with one click.