Semantic Scholar
Free AI-assisted academic search across 200M+ papers, from Ai2
Overview
Semantic Scholar is a free academic search engine from the Allen Institute for AI (Ai2) covering 200M+ papers, with citation graphs and influential-citation markers, TLDR summaries for computer science and biomedicine, Semantic Reader, alerts, feeds and a free API with bulk datasets.
Use cases
What you can produce with Semantic Scholar
- Free academic search across 200M+ papers
- Citation graphs and influential-citation markers
- TLDR summaries for CS and biomedical papers
- Semantic Reader augmented PDF reading
- Research feeds, alerts and library
- Free API and bulk datasets
Semantic Scholar remains one of the best free tools for finding and tracing academic literature, with excellent citation data and a generous free API that other research tools build on. Its AI features are narrower than often described — TLDRs cover only computer science and biomedicine — and search works best with exact keywords. Essential for researchers on a budget; pair it with a field-specific database where coverage matters.
What we found
Semantic Scholar is a free academic search engine covering more than 200 million papers across all fields — its homepage counter showed about 238 million — built and run by Ai2, the Allen Institute for AI, in Seattle. Beyond search it offers paper pages with citation graphs and "highly influential" citation markers, author pages, sorting by relevance, citation count, influence or recency, research feeds and alerts, a personal library, and a browser extension. AI features include TLDR one-sentence summaries, which cover only computer science and biomedical papers, about 60 million of them in beta; Semantic Reader, an augmented PDF reader available for selected papers; and Ask This Paper, which answers questions about a paper using OpenAI's GPT-3.5 and is tested in English only. Search uses a relevance-ranking model, but its help pages advise searching with full keywords because it does not expand acronyms. Its classification of fields of study is limited to English-language papers.
Semantic Scholar was released publicly in November 2015 and is run by a research and product team within Ai2. In March 2026 Ai2's chief executive, Ali Farhadi, left for Microsoft with several researchers and Peter Clark became interim chief executive, and GeekWire reported that Ai2's main funder was moving to proposal-based funding; we found no sign of disruption to the service.
Everything is free. Search and paper pages need no account; alerts, feeds and the library need a free login. Its public API, covering the academic graph, recommendations and bulk datasets with SPECTER2 embeddings, is also free: unauthenticated requests share a pool of 1,000 a second, and a free API key provides one request a second to start. Other research tools, including Elicit, draw on its data.
We did not find reliable independent review data. Semantic Scholar suits students and researchers who want a free, well-connected literature search, particularly in computer science and biomedicine.
Compiled by RECATOOLS from public sources: vendor documentation and pricing, code repositories and published reporting.
Notable facts
- Semantic Scholar indexes papers from over 200,000 journals and conferences, making it more comprehensive than PubMed (medicine-only) or arXiv (physics/math/CS-only).
- The platform was built by Paul Allen, the Microsoft co-founder, specifically because he believed academic knowledge should be freely accessible without paywalls.
- Semantic Scholar's API is used by commercial research tools serving millions of users, effectively making it the free data backbone of the AI research assistance industry.
Frequently asked questions
About this listing
This entry was compiled from publicly available data including Semantic Scholar's official website, press releases, documentation, and reputable third-party publications. RECATOOLS is not affiliated with Semantic Scholar 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 Semantic Scholar 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
Alternatives to Semantic Scholar
More in Research & Data
