Consensus vs Liner: pricing, features and which to choose

Consensus is made by Consensus NLP, Inc. and presents itself as an AI search engine for research. Its documentation says it searches more than 400 million scholarly articles, including 350 million peer-reviewed papers, while an earlier company primer cited more than 200 million papers. The company says more than five million researchers, students, and clinicians use it across more than 10,000 universities. It is best understood as a retrieval and explanation layer over scholarly literature, rather than a general chatbot. Its defining feature is traceability: answer sentences link to papers, and users can inspect supporting quotations. The company does not publish a founding year or funding total in the material described here, so its identity rests mainly on product scope, audience, and scholarly-search positioning.

A typical workflow begins with a natural-language research question. Consensus searches its paper database, retrieves relevant results, and generates a response from those results rather than relying only on general model knowledge. Users can inspect citations, run Pro searches, and open Study Snapshot entries covering details such as methodology, sample size, and study duration. Pro analysis summarizes up to 20 papers, while Deep Review searches across up to 50 papers for broader literature work. The service also flags retracted papers and supports API and MCP connections. This workflow helps users form reading lists, compare findings, screen evidence, or gain orientation in an unfamiliar field. It is most useful before close reading, because important claims still require checking the full papers, methods, limitations, and surrounding evidence.

The main limitation is dependence on indexed scholarly metadata and AI summaries. Citation links make checking easier, but they cannot guarantee that a synthesis captures study quality, conflicting findings, publication bias, or methodological nuance. Consensus is less suited to citation-network exploration than ResearchRabbit, Connected Papers, or Litmaps, and less suited to full reference management than Elicit or Scite. Its 2026 privacy policy says it does not sell personal information or use queries, uploads, or personal data to train large language models, while still describing account, cookie, provider, and analytics processing. Choose Consensus for fast, citation-linked answers and evidence comparison; choose ResearchRabbit for visual discovery and iterative paper mapping. It best fits students, clinicians, researchers, and teams seeking orientation before deeper evaluation.

Liner is an AI research workspace operated by a company whose principal place of business is in Seoul, South Korea. It serves students, academic researchers, professionals, and developers with web search, Scholar search, writing tools, document analysis, and research agents. The company introduced Deep Research on March 20, 2025, with source discovery, citation checking, and long-form reports. Liner also offers developer access through search, visualization, agent, and Router APIs. Its terms say users retain ownership of submitted content while granting Liner a limited license to operate, promote, improve, and develop its services. Liner does not publish a founding year, user count, employee count, or funding total on the cited pages.

A typical Liner session starts with a question, uploaded file, or academic search request. Deep Research breaks the request into related subtasks, searches multiple sources, and returns a report with references, tables, graphs, and additional findings. Related research calls can run concurrently, which the company says reduces repeated prompting. Users can export findings to PDF, Microsoft Word, OneNote, or text. Scholar emphasizes papers, source reliability, and citation volume, drawing from more than 50 academic sources, while file uploads support questions about personal documents. Developers can call Web Search, Scholar Search, Visualization, Quick Answer Agent, Search Agent, Deep Research Agent, and Visual Answer Agent endpoints. API charges vary by feature and complexity, with requests or tokens deducted from prepaid credits. Pick Liner for cited research workflows involving papers, documents, reports, or developer integrations.

Citations do not eliminate the need to verify important claims. Liner warns that generated material can be inaccurate or biased, and its Deep Research announcement says results vary with query complexity, context length, and data recency. Its privacy update also says submitted content may be shared with third-party service providers to process requests and provide AI-powered features, so users should review the current policy before uploading confidential documents. Perplexity is a closer general web research alternative, while Elicit and Consensus focus more tightly on academic literature. ChatGPT and Claude provide broader document and writing tools. Liner’s API also has published endpoint rates, from Web and Scholar Search to long-form Deep Research Agent requests. Pick Liner for cited web and paper research with file handling, exports, and metered developer endpoints.