Search DataCite DOI metadata for datasets, software, samples, workflows, and other research outputs. Combine plain words (`text`) or OpenSearch query syntax (`query`) with filters for resource type, creator (ORCID iD or name), affiliation (ROR ID or name), affiliation country, funder (ROR ID, Crossref Funder ID, or name), subject, field of science, repository, provider, license, language, geographic place, publication-year range, and minimum citation count. Returns the total match count and compact rows — DOI, title, first creators, year, type, repository, licenses, and citation/view/download counts — plus optional top facet counts. The total counts DOIs, so a versioned work counts once per DOI — its concept DOI and each version DOI, as Zenodo registers them; set version_scope to series to count each version series once, or releases to count only the versions. Page numbers reach the first 10,000 ranked matches; pass cursor "*" to walk any result set in full, in registration order.
View input schema
{
"type": "object",
"properties": {
"text": {
"description": "Plain words and phrases, searched literally: query-syntax characters are escaped, so \"Climate change: impacts\" works. Angle brackets are removed; nonblank text with no remaining searchable clause is rejected. Blank text is unset. Terms are ANDed.",
"type": "string",
"maxLength": 2000
},
"query": {
"description": "OpenSearch query-string syntax — field paths (titles.title:\"…\", creators.name:…, relatedIdentifiers.relationType:…), AND/OR/NOT, ranges, wildcards. Field paths: datacite_list_reference topic query_syntax. ANDed with text and the filters.",
"type": "string",
"maxLength": 2000
},
"resource_types": {
"description": "resourceTypeGeneral values (any match): dataset, software, computational-notebook, workflow, model, physical-object, … PascalCase accepted. Full list: datacite_list_reference topic resource_types.",
"maxItems": 10,
"type": "array",
"items": {
"type": "string",
"enum": [
"audiovisual",
"award",
"book",
"book-chapter",
"collection",
"computational-notebook",
"conference-paper",
"conference-proceeding",
"data-paper",
"dataset",
"dissertation",
"event",
"image",
"instrument",
"interactive-resource",
"journal",
"journal-article",
"model",
"other",
"output-management-plan",
"peer-review",
"physical-object",
"poster",
"preprint",
"presentation",
"project",
"report",
"service",
"software",
"sound",
"standard",
"study-registration",
"text",
"workflow"
]
}
},
"creator": {
"description": "A creator ORCID iD (0000-0002-1825-0097, 16 digits, or an orcid.org URL; checksum verified) or a name — every name token must appear in one creator field.",
"type": "string",
"maxLength": 500
},
"affiliation": {
"description": "A ROR ID (021nxhr62 or a ror.org URL) — matches creator and contributor affiliations — or an affiliation name phrase.",
"type": "string",
"maxLength": 500
},
"affiliation_country": {
"description": "Current or formerly assigned ISO 3166 alpha-2 country of a creator or contributor affiliation, plus XK; any case (DE, us). UK aliases to GB with a notice. Unassigned codes, alpha-3 codes and names are rejected.",
"type": "string",
"pattern": "^\\s*[A-Za-z]{2}\\s*$"
},
"funder": {
"description": "A funder ROR ID, a Crossref Funder ID (10.13039/100000001, its doi.org URL, or the bare digits), or a funder name — every name token must appear in one funding reference.",
"type": "string",
"maxLength": 500
},
"include_child_funders": {
"default": false,
"description": "Also match the funder's child organizations in ROR. Needs funder as a ROR ID, or a Crossref Funder ID that resolves to exactly one ROR ID; rejected with a funder name or no funder.",
"type": "boolean"
},
"subject": {
"description": "A subject phrase, matched case-insensitively against subject terms.",
"type": "string",
"maxLength": 500
},
"fields_of_science": {
"description": "OECD Fields of Science ids or labels (any match), e.g. computer_and_information_sciences or \"Earth and related environmental sciences\". List: datacite_list_reference topic fields_of_science.",
"maxItems": 10,
"type": "array",
"items": {
"type": "string",
"enum": [
"natural_sciences",
"mathematics",
"computer_and_information_sciences",
"physical_sciences",
"chemical_sciences",
"earth_and_related_environmental_sciences",
"biological_sciences",
"other_natural_sciences",
"engineering_and_technology",
"civil_engineering",
"electrical_engineering_electronic_engineering_information_engineering",
"mechanical_engineering",
"chemical_engineering",
"materials_engineering",
"medical_engineering",
"environmental_engineering",
"environmental_biotechnology",
"industrial_biotechnology",
"nanotechnology",
"other_engineering_and_technologies",
"medical_and_health_sciences",
"basic_medicine",
"clinical_medicine",
"health_sciences",
"medical_biotechnology",
"other_medical_sciences",
"agricultural_sciences",
"agriculture_forestry_and_fisheries",
"animal_and_dairy_science",
"veterinary_science",
"agricultural_biotechnology",
"other_agricultural_sciences",
"social_sciences",
"psychology",
"economics_and_business",
"educational_sciences",
"sociology",
"law",
"political_science",
"social_and_economic_geography",
"media_and_communications",
"other_social_sciences",
"humanities",
"history_and_archaeology",
"languages_and_literature",
"philosophy_ethics_and_religion",
"arts_arts_history_of_arts_performing_arts_music",
"other_humanities"
]
}
},
"repository_ids": {
"description": "Repository ids (any match), shaped provider.repository — e.g. dryad.dryad or cern.zenodo — as datacite_search_repositories returns them in repositoryId. Any case.",
"maxItems": 10,
"type": "array",
"items": {
"type": "string",
"maxLength": 100,
"pattern": "^\\s*[A-Za-z0-9-]+\\.[A-Za-z0-9-]+\\s*$"
}
},
"provider_ids": {
"description": "Provider ids (any match), e.g. dryad — the providerId datacite_search_repositories returns. Any case.",
"maxItems": 10,
"type": "array",
"items": {
"type": "string",
"maxLength": 100,
"pattern": "^\\s*[A-Za-z0-9-]+\\s*$"
}
},
"licenses": {
"description": "The work's own license ids (any match), e.g. cc-by-4.0, cc0-1.0, cc0 1.0, mit. Trimmed and lowercased, then matched exactly, preserving internal spaces; reuse ids from the licenses facet or datacite_list_reference topic licenses.",
"maxItems": 10,
"type": "array",
"items": {
"type": "string",
"maxLength": 100,
"pattern": "^\\s*[A-Za-z0-9.+_-](?:[A-Za-z0-9.+_ -]*[A-Za-z0-9.+_-])?\\s*$"
}
},
"language": {
"description": "ISO 639-1 language code of the work, any case (en, de).",
"type": "string",
"pattern": "^\\s*[A-Za-z]{2}\\s*$"
},
"place": {
"description": "A place name, matched anywhere inside deposited place names, so India also matches Indiana. Tried as typed, in lowercase, in uppercase, with every word capitalized, and with the first word capitalized: give a multi-word name its usual capitalization (Gulf of Mexico). For one exact, case-sensitive name, use query geoLocations.geoLocationPlace:\"Svalbard\" instead.",
"type": "string",
"maxLength": 500
},
"published_from": {
"description": "Earliest publication year (inclusive). Alone, the range is open-ended.",
"type": "integer",
"minimum": 1000,
"maximum": 2100
},
"published_to": {
"description": "Latest publication year (inclusive). Alone, the range is open-ended.",
"type": "integer",
"minimum": 1000,
"maximum": 2100
},
"min_citations": {
"description": "Only works DataCite records at least this many citations for.",
"type": "integer",
"minimum": 1,
"maximum": 9007199254740991
},
"version_scope": {
"description": "Which DOIs of a versioned work count. all (default): every DOI, so a Zenodo upload counts at least twice — its concept DOI and each version DOI. series: drops every record asserting IsVersionOf, so a version series counts once, through its concept DOI; a version whose concept DOI fails another filter (a later publication year, a changed creator or affiliation) or lies outside DataCite is not counted at all. releases: drops every record asserting HasVersion, so each version counts and concept DOIs drop out. Neither collapses Figshare's .vN DOIs, which point at their base DOI with IsIdenticalTo, so those pairs still count twice.",
"type": "string",
"enum": [
"all",
"series",
"releases"
]
},
"sort": {
"description": "relevance, newest, oldest, recently_updated, most_cited, most_viewed, or most_downloaded. Omitted: relevance when text or query is set, else newest. Not with cursor.",
"type": "string",
"enum": [
"relevance",
"newest",
"oldest",
"recently_updated",
"most_cited",
"most_viewed",
"most_downloaded"
]
},
"limit": {
"description": "Requested rows per page, a positive integer (default 20); values above 1,000 apply 1,000 with a notice unless strict limits are configured.",
"default": 20,
"type": "number",
"minimum": 1,
"multipleOf": 1
},
"page": {
"description": "Ranked page number, 1 when omitted. page × limit may not exceed 10,000; not with cursor.",
"type": "integer",
"minimum": 1,
"maximum": 9007199254740991
},
"cursor": {
"description": "Cursor walk over the full result set in registration order: \"*\" to start, then the nextCursor of the previous page, unchanged, with the same query and filters. Not with page or sort.",
"type": "string",
"maxLength": 2048,
"pattern": "^\\s*(?:\\*|[A-Za-z0-9_-]+)\\s*$"
},
"include_facets": {
"default": false,
"description": "Add top facet counts (resource types, years, repositories, providers, affiliations, fields of science, licenses). Adds 2–8 s.",
"type": "boolean"
}
},
"$schema": "https://json-schema.org/draft/2020-12/schema",
"additionalProperties": false
}