CORE similar-paper recommendations API

Use the CORE similar-paper recommendations API to retrieve related research records and their publication references. Describe a topic with free text, a title and abstract, or an existing CORE record ID, then choose a recommendation limit to retrieve related open-access paper records. Discover related publications, compare suggested reading candidates, or extend a topic search beyond an initial paper or abstract. Related-paper recommendations are discovery suggestions, not evidence that every returned item directly cites or is cited by the seed paper. The detail page provides request and response examples, supported parameters, and usage pricing.

Selected price
$0.002 / billing creditPublished pricing
Sellers / implementations
1 / 1
Requests · 30d
—Loading...
Success rate · 30d
—Loading...

Run sends a real API request. Charges follow the published API contract.

Request parameters
Optional parameters (10)
Free text describing the topic.
A paper title.
A paper abstract.
A CORE id to find papers like it.
Up to 50 (default 10).
0 leaves out the bulky `raw` source blocks (often 10-30x smaller).
Comma-separated fields to return, e.g. `posts.id,posts.title`. Call metadata is always included.
1 skips the 24-hour cache and fetches live.
JSON only for this OpenAny product. Omit output or use json; CSV and NDJSON exports are not exposed.
Native CSV/NDJSON record selector; it has no effect on this JSON-only product.

Sample response

{
  "cached": false,
  "count": 3,
  "credits_used": 1,
  "id": null,
  "items": [
    {
      "abstract": "The application of deep learning algorithms in protein structure prediction has greatly influenced drug discovery and development. Accurate …",
      "accepted": null,
      "arxiv_id": null,
      "authors": [
        "Yajie Meng",
        "Zhuang Zhang",
        "… 8 more"
      ],
      "citation_count": null,
      "contributors": [],
      "created": "2025-08-20T04:07:20+01:00",
      "data_provider": {
        "id": 645,
        "logo": "https://api.core.ac.uk/data-providers/645/logo",
        "name": "Directory of Open Access Journals",
        "url": "https://core.ac.uk/data-providers/645"
      },
      "deposited": "2025-04-03T06:13:05+01:00",
      "document_type": [
        "research article"
      ],
      "doi": "10.3389/fphar.2025.1498662",
      "download_url": "https://core.ac.uk/download/655734159.pdf",
      "field_of_study": null,
      "full_text_identifier": null,
      "id": 655734159,
      "identifiers": {
        "doi": "10.3389/fphar.2025.1498662",
        "oai": "oai:doaj.org/article:60c98d0c858d4ec5b68710ea2bc10d29"
      },
      "journals": [
        {
          "identifiers": [],
          "title": null
        }
      ],
      "kind": "output",
      "language": null,
      "links": [
        {
          "type": "download",
          "url": "https://core.ac.uk/download/655734159.pdf"
        },
        {
          "type": "reader",
          "url": "https://core.ac.uk/reader/655734159"
        },
        "… 4 more"
      ],
      "mag_id": null,
      "oai_ids": [
        "oai:doaj.org/article:60c98d0c858d4ec5b68710ea2bc10d29"
      ],
      "published": null,
      "publisher": "Frontiers Media S.A.",
      "pubmed_id": null,
      "references": [],
      "repositories": [],
      "repository_document": {
        "acceptedDate": "",
        "createdDate": "",
        "depositedDate": "",
        "id": 655734159,
        "publishedDate": "",
        "updatedDate": ""
      },
      "set_specs": [],
      "source_fulltext_urls": [
        "https://doaj.org/article/60c98d0c858d4ec5b68710ea2bc10d29"
      ],
      "subjects": [
        "article"
      ],
      "tags": [
        "article"
      ],
      "title": "Protein structure prediction via deep learning: an in-depth review",
      "updated": null,
      "url": "https://core.ac.uk/outputs/655734159",
      "urls": [
        {
          "type": "fulltext",
          "url": "https://doaj.org/article/60c98d0c858d4ec5b68710ea2bc10d29"
        }
      ],
      "year": "2025"
    },
    {
      "abstract": "Protein Structure Prediction is a central topic in Structural Bioinformatics. Since the ’60s statistical methods, followed by increasingly c…",
      "accepted": null,
      "arxiv_id": null,
      "authors": [
        "Torrisi, Mirko",
        "Pollastri, Gianluca",
        "… 1 more"
      ],
      "citation_count": null,
      "contributors": [],
      "created": "2020-09-25T13:24:59+01:00",
      "data_provider": {
        "id": 611,
        "logo": "https://api.core.ac.uk/data-providers/611/logo",
        "name": "Research Repository UCD",
        "url": "https://core.ac.uk/data-providers/611"
      },
      "deposited": "2020-09-23T00:01:08+01:00",
      "document_type": [
        "journal article"
      ],
      "doi": "10.1016/j.csbj.2019.12.011",
      "download_url": "https://core.ac.uk/download/334435519.pdf",
      "field_of_study": null,
      "full_text_identifier": null,
      "id": 334435519,
      "identifiers": {
        "doi": "10.1016/j.csbj.2019.12.011",
        "oai": "oai:researchrepository.ucd.ie:10197/11583"
      },
      "journals": [],
      "kind": "output",
      "language": null,
      "links": [
        {
          "type": "download",
          "url": "https://core.ac.uk/download/334435519.pdf"
        },
        {
          "type": "reader",
          "url": "https://core.ac.uk/reader/334435519"
        },
        "… 4 more"
      ],
      "mag_id": null,
      "oai_ids": [
        "oai:researchrepository.ucd.ie:10197/11583"
      ],
      "published": "2020-01-01T00:00:00+00:00",
      "publisher": "Elsevier",
      "pubmed_id": null,
      "references": [],
      "repositories": [],
      "repository_document": {
        "acceptedDate": "",
        "createdDate": "",
        "depositedDate": "",
        "id": 334435519,
        "publishedDate": "2020-01-01T00:00:00+00:00",
        "updatedDate": ""
      },
      "set_specs": [],
      "source_fulltext_urls": [
        "http://hdl.handle.net/10197/11583"
      ],
      "subjects": [
        "Journal Article"
      ],
      "tags": [
        "Journal Article"
      ],
      "title": "Deep learning methods in protein structure prediction",
      "updated": null,
      "url": "https://core.ac.uk/outputs/334435519",
      "urls": [
        {
          "type": "fulltext",
          "url": "http://hdl.handle.net/10197/11583"
        }
      ],
      "year": "2020"
    },
    "… 1 more"
  ],
  "text": "deep learning for protein structure prediction",
  "title": null
}

Response result

Response structure

Inferred from examples
  • cachedboolean
  • countinteger
  • credits_usedinteger
  • idnull
  • items(object | string)[]
    • abstractstring
    • acceptednull
    • arxiv_idnull
    • authorsstring[]
    • citation_countnull
    • contributorsunknown[]
    • createdstring
    • data_providerobject
      • idinteger
      • logostring
      • namestring
      • urlstring
    • depositedstring
    • document_typestring[]
    • doistring
    • download_urlstring
    • field_of_studynull
    • full_text_identifiernull
    • idinteger
    • identifiersobject
      • doistring
      • oaistring
    • journalsobject[]
      • identifiersunknown[]
      • titlenull
    • kindstring
    • languagenull
    • links(object | string)[]
      • typestring
      • urlstring
    • mag_idnull
    • oai_idsstring[]
    • publishednull | string
    • publisherstring
    • pubmed_idnull
    • referencesunknown[]
    • repositoriesunknown[]
    • repository_documentobject
      • acceptedDatestring
      • createdDatestring
      • depositedDatestring
      • idinteger
      • publishedDatestring
      • updatedDatestring
    • set_specsunknown[]
    • source_fulltext_urlsstring[]
    • subjectsstring[]
    • tagsstring[]
    • titlestring
    • updatednull
    • urlstring
    • urlsobject[]
      • typestring
      • urlstring
    • yearstring
  • textstring
  • titlenull

Common questions

Do I need a separate key for every provider?

Use your OpenAny API key for standard API access. Read it from OPENANY_API_KEY in your environment and keep it out of prompts, source code and logs.

Are these providers interchangeable?

No. Each offering has its own inputs, pricing and response contract. Selecting a catalog offering does not establish automatic routing or fallback. Confirm the service contract before calling.

How is this API billed?

API-key calls use your shared balance at the selected implementation's published rate. Check the billing unit and request-specific pricing rules before making a paid call. Recorded usage determines the final charge under that contract.

Where do the price and contract come from?

The selected implementation publishes its provider, request contract, revision and billing rules through OpenAny's public API catalog. A revision number identifies a contract version, not a price update date. A price update timestamp is not supplied; do not treat a page date as one.

How do OpenAny Balance and x402 differ?

OpenAny Balance uses an API key and one shared balance. Card, USDC and x402 top-ups, card auto top-up and USDC subscriptions fund that balance; available routes appear on the Credits page. Direct x402 is a separate pay-per-request flow, available only on listings that show it and requiring an authorized payment client.

Does Playground send a paid request?

Yes. After you sign in, Run sends a real API request using an active OpenAny API key. Charges follow the published API contract and use your shared balance. Selecting an implementation, editing inputs and viewing sample responses do not send requests.

Use CORE similar-paper recommendations API with your agent

Inspect endpoint contracts and confirm availability and pricing before a paid call.