Academic Paper Search: arXiv, PubMed, OpenAlex & Crossref

Academic paper search across arXiv, PubMed, OpenAlex and Crossref: one query returns deduplicated research papers with abstracts, citations and open-access PDF links.

One call searches four scholarly indexes and returns a clean, deduplicated, ranked list of papers, with everything an AI agent, researcher or analyst needs:

• Title, authors, year, venue and abstract. The best abstract wins: PubMed for biomedicine, arXiv for preprints, then OpenAlex or Crossref.
• Citation counts for every result, including arXiv and PubMed hits, via OpenAlex enrichment.
• Open-access status and a free PDF or full-text link when one exists (arXiv, PubMed Central, publisher OA copies).
• DOI, arXiv ID, PMID, PMCID and OpenAlex ID, topics/MeSH terms, retraction flags, and optional ORCIDs and affiliations.
• A ready-to-paste citation and a BibTeX entry for each paper.
• Smart deduplication. A preprint and its published version are merged into one record, with the published DOI preferred.
• Fused relevance ranking. Each index's own ranking is combined with cross-source agreement and citation impact. You can also sort by newest or most cited.

All data comes from official, open scholarly APIs: OpenAlex (CC0), Crossref, the arXiv API and NCBI E-utilities. No scraping and no Google Scholar.

Why this one

	This Actor	Typical paper-search Actors
Sources per call	4, merged and deduplicated	1, or several returned separately
Citations on every result	✅	Only for the native source
Preprint ↔ published merge	✅	❌
BibTeX and formatted citation	✅	❌
DOI / arXiv / PMID lookup	✅	Partial
Price for a 25-paper search	$0.03	$0.05–0.06 per call

Use cases

• AI agents and RAG. Give your agent a "find papers" tool that returns compact JSON with abstracts and links, then fetch the PDFs it needs. This works from the Apify MCP server, the API, LangChain or n8n.
• Literature reviews. Run 50 queries, sort by citations and export to CSV or BibTeX.
• Biotech and pharma BD. Track the latest trials and papers on a target, with retraction flags.
• Competitive and technology intelligence. Monitor new arXiv and journal output on a topic with a scheduled run.

Input

{
  "queries": ["retrieval augmented generation hallucination", "\"long covid\" fatigue"],
  "identifiers": ["10.1056/NEJMoa2031054", "arXiv:1706.03762", "PMID: 33283989"],
  "maxResults": 25,
  "sortBy": "relevance",
  "yearFrom": 2020,
  "openAccessOnly": false
}

Search tips: quote exact phrases. arXiv field syntax (ti:, au:, cat:cs.CL) is passed through to arXiv.

Output (one row per paper)

{
  "query": "retrieval augmented generation hallucination",
  "rank": 1,
  "title": "Reducing hallucination in structured outputs via Retrieval-Augmented Generation",
  "authors": ["Orlando Ayala", "Patrice Bechard"],
  "year": 2024,
  "venue": "NAACL-HLT",
  "abstract": "A common and fundamental limitation of Generative AI ...",
  "doi": "10.18653/v1/2024.naacl-industry.19",
  "pdfUrl": "https://arxiv.org/pdf/2404.08189v1",
  "isOpenAccess": true,
  "citationCount": 95,
  "arxivId": "2404.08189",
  "topics": ["hallucination mitigation", "retrieval-augmented generation", "cs.LG"],
  "isRetracted": false,
  "citation": "Ayala & Bechard (2024). Reducing hallucination ... https://doi.org/10.18653/v1/2024.naacl-industry.19",
  "bibtex": "@inproceedings{ayala2024reducing, ...}",
  "sources": ["arxiv", "openalex"]
}

Dataset views: Papers (table), Abstracts and BibTeX.

Pricing (pay per event)

Event	Price
Search completed (a query that returned at least one paper)	$0.005
Paper returned	$0.001
Searches with no results, ID lookups that aren't found, candidates fetched but not returned	free

For example, a 25-paper search costs $0.03, and 100 DOI lookups cost $0.10. The Actor respects your run's maximum charge and stops cleanly when it's reached.

Optional API keys

You don't need any keys. For heavy daily use, add your own free OpenAlex key (openalex.org/settings/api) for a dedicated budget, and a free NCBI key for faster PubMed calls. If OpenAlex is unavailable, the run carries on with the other sources.

FAQ

Does it include Google Scholar or Semantic Scholar? No. Only official, openly licensed APIs are used, which keeps the Actor reliable and ToS-safe.

Can it download full text? It returns the open-access PDF or full-text link. To convert PDFs to Markdown for RAG, pair it with our Documents to AI-Ready Markdown Actor.

How fresh is the data? Every call is live: arXiv and PubMed update daily, and OpenAlex and Crossref within days.

---

Built by PewterDesk (pewterdesk.pages.dev). More tools: apify.com/pewterdesk.