DOI to Citation: ABNT, APA, Vancouver & BibTeX Formatter

Turn DOIs, DOI links or messy references into clean, consistent citations in ABNT NBR 6023:2018, APA 7, Vancouver and BibTeX, for one paper or a list of thousands. Metadata comes from doi.org (Crossref, DataCite and the other DOI agencies), and references without a DOI are matched in Crossref, with a confidence score so wrong matches are not silently accepted.

Most citation tools are one-at-a-time web forms, and almost none produce ABNT, the standard required by Brazilian universities and journals. This Actor does it in bulk through an API, with the structured metadata (authors, journal, volume, pages, citation count) next to each formatted reference.

Typical uses: fixing the reference list of a thesis or paper, converting a bibliography to BibTeX for LaTeX, research tools and reference managers, and AI agents that must cite real sources with verified DOIs.

What you get per reference

• Formatted citations: abnt, apa, vancouver and bibtex
• DOI, type, title, authors, journal or book, publisher, year, volume, issue, pages, link
• Citation count from Crossref (when the DOI is registered there)
• How it was found (doi or search) and, for free-text references, a matchConfidence from 0 to 1

Input

Field	Description
references	DOIs, DOI links or free-text references, one per line. Up to 2,000.
styles	Any of abnt, apa, vancouver, bibtex. Default: all.
minConfidence	Free-text only: minimum title match (0 to 1, default 0.5).
contactEmail	Optional e-mail sent to Crossref as mailto (its etiquette for large lists).

{
  "references": [
    "10.1038/nature14539",
    "https://doi.org/10.1145/3065386",
    "Vaswani A, et al. Attention is all you need. Advances in Neural Information Processing Systems, 2017"
  ],
  "styles": ["abnt", "bibtex"]
}

Output

One dataset item per reference:

{
  "input": "10.1038/nature14539",
  "matchedBy": "doi",
  "matchConfidence": null,
  "doi": "10.1038/nature14539",
  "type": "article-journal",
  "title": "Deep learning",
  "authors": [
    "Yann LeCun",
    "Yoshua Bengio",
    "Geoffrey Hinton"
  ],
  "containerTitle": "Nature",
  "publisher": "Springer Science and Business Media LLC",
  "year": 2015,
  "volume": "521",
  "issue": "7553",
  "pages": "436-444",
  "url": "https://doi.org/10.1038/nature14539",
  "citedByCount": 70000,
  "citations": {
    "abnt": "LECUN, Yann; BENGIO, Yoshua; HINTON, Geoffrey. Deep learning. Nature, v. 521, n. 7553, p. 436-444, maio 2015. DOI: 10.1038/nature14539. Disponível em: https://doi.org/10.1038/nature14539. Acesso em: 1 nov. 2026.",
    "apa": "LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539",
    "vancouver": "LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436-444. doi:10.1038/nature14539",
    "bibtex": "@article{lecun2015deep,\n  title = {Deep learning},\n  author = {LeCun, Yann and Bengio, Yoshua and Hinton, Geoffrey},\n  journal = {Nature},\n  publisher = {Springer Science and Business Media LLC},\n  year = {2015},\n  volume = {521},\n  number = {7553},\n  pages = {436--444},\n  doi = {10.1038/nature14539},\n  url = {https://doi.org/10.1038/nature14539}\n}"
  },
  "error": null
}

References that cannot be resolved (unknown DOI, no confident match) come back with error filled in, and the best candidate when there is one. They are not charged.

How much does it cost?

Pay per event: one citation per reference resolved, with all styles included. Unknown DOIs and doubtful matches are free.

$0.002 per citation (citation event, pay per event). Charged once per reference resolved and formatted (all styles included). DOIs not found and doubtful matches are free.

You get	Free tier	Bronze tier (10% off)	Gold tier (30% off)
100 citations	$0.20	$0.18	$0.14
1,000 citations	$2.00	$1.80	$1.40
10,000 citations	$20.00	$18.00	$14.00

Discounts follow your Apify subscription tier: Bronze 10%, Silver 20%, Gold and above 30%. No subscription to this Actor and no charge for platform usage: you pay only for results. The Apify Free plan includes $5 of monthly credit, enough for about 2,500 citations at the list price. You can cap the cost of any run with Maximum cost per run; the Actor stops when it is reached.

Data source and limits

Metadata from the DOI registration agencies through doi.org content negotiation (CSL-JSON) and the Crossref REST API (api.crossref.org). Crossref metadata is open (CC0). Formatting follows ABNT NBR 6023:2018, APA 7th edition and the NLM/ICMJE Vancouver style as plain text, so italics and bold are not included.

Limits: the quality of each citation depends on the metadata the publisher deposited (missing pages or issue numbers stay missing). Free-text matching works best with the title in the reference. ABNT lists up to three authors and uses "et al." beyond that, as NBR 6023 allows.

Use it via API

Run it from any language and get the results as JSON. Replace <YOUR_API_TOKEN> with your Apify API token.

curl -X POST "https://api.apify.com/v2/acts/br_data_hub~doi-citation-formatter/run-sync-get-dataset-items?token=<YOUR_API_TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{"references": ["10.1038/nature14539", "https://doi.org/10.1145/3065386", "Vaswani A, et al. Attention is all you need. Advances in Neural Information Processing Systems, 2017"]}'

from apify_client import ApifyClient

client = ApifyClient("<YOUR_API_TOKEN>")
run = client.actor("br_data_hub/doi-citation-formatter").call(run_input={'references': ['10.1038/nature14539',
                                                     'https://doi.org/10.1145/3065386',
                                                     'Vaswani A, et al. Attention is all you need. Advances in Neural '
                                                     'Information Processing Systems, 2017']})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

You can also schedule runs, send results to webhooks, or connect the Actor to Make, Zapier, n8n, Google Sheets and other integrations.

Use it with AI agents (MCP)

This Actor is ready for AI agents: typed input and output schemas, pay-per-event pricing, limited permissions and short runs.

• Apify MCP server: add https://mcp.apify.com/?tools=br_data_hub/doi-citation-formatter to Claude, ChatGPT, Cursor, VS Code or any MCP client, and the agent can call this Actor as a tool.
• Agent frameworks: call it from LangChain, LlamaIndex, CrewAI or the OpenAI Agents SDK through the Apify integrations, or with the API call above.
• Results come as structured JSON with stable field names, documented in the Output tab.

FAQ

Where does the data come from?

Metadata from the DOI registration agencies through doi.org content negotiation (CSL-JSON) and the Crossref REST API (api.crossref.org). Crossref metadata is open (CC0). Formatting follows ABNT NBR 6023:2018, APA 7th edition and the NLM/ICMJE Vancouver style as plain text, so italics and bold are not included.

How much does it cost?

$0.002 per citation. Discounts follow your Apify subscription tier: Bronze 10%, Silver 20%, Gold and above 30%. See How much does it cost? above for examples.

Do I pay for errors or empty results?

No. Charged once per reference resolved and formatted (all styles included). DOIs not found and doubtful matches are free.

Can I run it on a schedule or connect it to other tools?

Yes. Use Apify schedules to run it daily or weekly, webhooks to get notified, and integrations such as Make, Zapier, n8n and Google Sheets. Everything also works through the API.

Can AI agents use it?

Yes. It works as a tool in the Apify MCP server and in agent frameworks, and AI agents can pay per event. See Use it with AI agents (MCP).

Is it legal to use this data?

The Actor reads only public sources. You are responsible for how you use the data and for complying with the source's terms and with privacy laws such as GDPR.

I found a bug or need a feature. What should I do?

Open an issue in the Issues tab. We answer within 14 days, usually much sooner.

More Actors from BR Data Hub

Actor	What it does
Documents to Markdown for RAG (Docling)	Convert PDF and DOCX files to clean Markdown with Docling: page count, detected tables, metadata and optional
Website to llms.txt Generator	Crawl one website (robots.txt and sitemap aware), generate spec-compliant llms.txt and llms-full.txt files, au
RSS & Atom Feed Reader with Full Text	Read RSS, Atom and JSON Feed (or find the feed of any website) and get clean items with ISO dates, full articl
Research Papers Search for RAG, from OpenAlex data	Search 250M+ scholarly papers from OpenAlex data, or look up DOIs: authors with institutions, venue, citations

See all our Actors at apify.com/br_data_hub.

Usar em português

Gera referências ABNT NBR 6023:2018, APA 7, Vancouver e BibTeX a partir de DOIs, links ou referências bagunçadas, em lote. Os metadados vêm do doi.org e do Crossref; referências sem DOI são procuradas pelo título, com grau de confiança. Cobrança só pelas referências encontradas; DOI inexistente e correspondência duvidosa não são cobrados.

Quanto custa: $0.002 por resultado (citation); 1.000 resultados saem por $2.00. Desconto pelo nível da assinatura Apify: Bronze 10%, Silver 20%, Gold ou acima 30%. Erros e consultas sem resultado não são cobrados. Use também pela API ou por agentes de IA no servidor MCP da Apify (https://mcp.apify.com/?tools=br_data_hub/doi-citation-formatter).