Stay free if you only need 5 graphs per month and single-origin visualizations. Upgrade if you need unlimited graph generation and multi-origin graph creation. Most solo builders can start free.
Why it matters: Free plan's 5 monthly graph limit is quickly exhausted during active research phases, requiring paid subscription
Available from: Academic ($3/month)
Why it matters: Graph quality depends heavily on citation density - very recent publications or niche topics produce sparse visualizations
Available from: Academic ($3/month)
Why it matters: Coverage skews toward STEM fields; humanities and social sciences have weaker representation in underlying database
Available from: Academic ($3/month)
Why it matters: Algorithm may cluster papers differently than domain experts would, potentially missing important conceptual distinctions
Available from: Academic ($3/month)
Why it matters: Cannot replace systematic review methodology completely - requires supplementation with traditional database searches
Available from: Academic ($3/month)
Why it matters: Industry reports, patents, and non-indexed sources are excluded from analysis
Available from: Academic ($3/month)
That's $3 per feature per month
💡 Great value
Traditional databases show direct citation relationships - papers that explicitly cite each other. Connected Papers uses AI algorithms to identify conceptual similarity based on co-citation patterns and semantic analysis, revealing related papers even when they never directly cite each other. This surfaces relevant work from adjacent fields or alternative methodological approaches that citation-only searches miss completely.
Connected Papers excels as a discovery and mapping tool but should complement, not replace, systematic review protocols. Use it to identify key papers and research clusters rapidly, then validate comprehensiveness through traditional database searches (PubMed, Scopus, discipline-specific indexes). The visual approach helps define review scope and ensures you haven't missed major research streams, but formal reviews require protocol-driven search strategies.
Coverage is strongest in STEM fields including computer science, biomedicine, physics, chemistry, mathematics, and engineering, drawing from Semantic Scholar's 200M+ paper corpus. Social sciences, economics, and psychology have growing representation. Humanities coverage is more limited. The tool performs best in fields with active citation practices and substantial publication volumes.
For actively researching graduate students, absolutely. The free plan's 5 monthly graphs are consumed within days during literature review phases. At $36 annually ($3/month), the Academic plan costs less than a single academic book but can save dozens of hours on literature discovery. The multi-origin graph feature alone is invaluable for interdisciplinary dissertations or comprehensive exams.
Connected Papers builds on Semantic Scholar's regularly updated corpus, which ingests papers from major publishers, preprint servers, and conference proceedings. New papers typically appear within days to weeks of publication, though citation relationships take time to develop. For very recent work (less than 6 months old), graphs may be sparse until sufficient citation networks form.
While Connected Papers doesn't explicitly flag predatory publications, the citation network visualization can reveal isolation patterns - legitimate research typically shows connections to established work and subsequent citations. Papers with no visible connections to mainstream research warrant additional scrutiny. However, journal quality assessment requires dedicated tools like Scite AI or manual evaluation of publication venues.
Start with the free plan — upgrade when you need more.
Get Started Free →Still not sure? Read our full verdict →
Last verified March 2026