Accelerate literature reviews for research & learning with maps
Iris.ai is an AI-driven research assistant that converts papers and project briefs into semantic Research Maps and extractable claim data for literature discovery. It suits researchers and R&D teams who need rapid, evidence-linked literature mapping rather than simple keyword search. Pricing starts with a Free tier and scales to paid individual and enterprise plans (paid tiers are priced approximately; confirm on iris.ai).
Iris.ai is an AI research assistant that helps researchers, students and R&D teams discover, map and extract knowledge from scientific literature. Its core capability is converting PDFs and text prompts into semantic Research Maps that visualise topic clusters and direct links to source claims. Iris.ai differentiates itself with an extraction-focused Document Reader that surfaces claims, methods and evidence chains instead of only listing citations. The tool targets academics, patent analysts and industrial researchers in the Research & Learning category. A Free tier exists with limited searches; paid plans add project exports and team features (pricing approximate).
Iris.ai is a Norway-founded research AI platform (founded 2015) positioned as an evidence-first literature discovery and mapping tool. It was created to help academics and R&D teams move beyond keyword search by using NLP to identify conceptual relationships and extract claim-level evidence from papers. The company markets Iris.ai as a Research & Learning tool aimed at accelerating literature reviews, scoping prior art and turning large PDF collections into navigable knowledge graphs. Its value proposition is turning long, fragmented literature searches into a reproducible, visual map tied to source passages, improving transparency and traceability in literature workflows.
Iris.ai’s feature set focuses on three core capabilities. The Document Reader ingests PDFs and extracts claims, methods, and supporting sentences, tagging them with concepts for quick review and citation export. The Research Map visualiser builds a semantic graph of concepts and papers, allowing users to explore related clusters and quickly jump to primary sources; maps can span hundreds of nodes depending on dataset size. The Semantic Search engine accepts abstracts, project briefs, or research questions as input and returns semantically matched papers rather than keyword hits, and supports filtering by year and source. Iris.ai also offers project-level exports (BibTeX/CSV) and an API/enterprise integrations layer for linking maps to institutional repositories (API access and limits are gated by commercial plans).
Pricing is offered as a Free tier plus paid individual and team/enterprise plans. The Free tier allows a limited number of searches and single-user projects (basic PDF uploads and small Research Maps). Paid individual plans and Team subscriptions add higher monthly upload/search quotas, full Document Reader exports, BibTeX/CSV export and team collaboration features; Iris.ai lists Enterprise/academic site licensing as custom-priced. Exact monthly prices for Pro and Team tiers should be confirmed on iris.ai (the vendor often uses region and volume-based pricing, so publicly listed rates may vary and are approximate). Nonprofit and institutional deals are commonly negotiated directly.
Real-world users include academic researchers mapping a literature field and R&D teams scoping patents and prior art. Example: a PhD candidate uses Iris.ai to reduce literature screening time by identifying 30–50 highly relevant papers from 1,000 PDFs. Example: a patent analyst uses the Document Reader to extract claim-evidence chains for freedom-to-operate reports. Iris.ai compares directly to tools like Connected Papers and Semantic Scholar, but it leans more heavily on claim-level extraction and project exports than connected-graph visualisers that prioritize citation networks.
Three capabilities that set Iris.ai apart from its nearest competitors.
Current tiers and what you get at each price point. Verified against the vendor's pricing page.
| Plan | Price | What you get | Best for |
|---|---|---|---|
| Free | Free | Limited searches, single-user projects, basic PDF uploads and small maps | Students or trial users exploring core features |
| Pro (Individual) | Approx $49/month | Higher upload/search quota, full Document Reader exports, BibTeX/CSV | Individual researchers who need exports and larger maps |
| Team | Approx $199/month | Shared projects, team seats, larger quotas, collaboration and admin controls | Research teams needing shared projects and collaboration |
| Enterprise | Custom | Site licensing, API access, SSO, custom quotas and SLAs | Institutions and enterprises requiring integrations and support |
Choose Iris.ai over Connected Papers if you need extractable claim-level passages and exportable Research Maps for reproducible reviews.
Head-to-head comparisons between Iris.ai and top alternatives: