AuthorizationstringheaderRequired Bearer API key. Programmatic access to the World API needs a key; browsing nosible.world in a browser does not.
Example: Bearer nos_sk_...
Retrieve events classified into one ontology field and value, including ranked top-three matches.
viewenumqueryThe record each event is returned as: lite (the default), the event without its evidence, or full, the complete record. Any other value is a 422 validation_error. About records on Event details lists both.
Example: lite
include_vectorbooleanquerytrue adds each event's embedding, oai_vector (3,072 values, comma-separated), to either view. Defaults to false.
Example: false
fieldstringqueryIndexed ontology field, such as gics_sector. Supply field, or supply both ontology and level instead.
Example: gics_sector
valuestringrequiredqueryOntology class to retrieve.
Example: Energy
matchstringquerytop1 precision match or top3 recall match.
Example: top3
fromdatequeryInclusive lower date bound in YYYY-MM-DD format.
Example: 2026-01-01
todatequeryInclusive upper date bound in YYYY-MM-DD format.
Example: 2026-07-20
limitintegerqueryPage size.
Example: 100
cursorstringqueryOpaque cursor returned by the previous page.
Example: eyJ2Ijox...
orderenumqueryEvent ordering, newest or oldest first.
Example: desc
ontologystringqueryOntology id or slug from the directory, such as gics. Required with level when field is omitted.
Example: gics
levelstringqueryLocal level name returned by the directory, such as sector for GICS or tier_1 for IAB. Required with ontology when field is omitted.
Example: sector
include_livebooleanqueryDefaults to true. Include published slices after the archive index, including today and yesterday (UTC). Set false for archive-only retrieval. GET uses the query string; POST uses a JSON boolean.
Example: true
Use ontology retrieval to turn a taxonomy class into a clean event universe. Select the class with either field=gics_sector&value=Energy or ontology=gics&level=sector&value=Energy. Directory levels are local names such as sector or tier_1, and are not necessarily the indexed filter field names; copy a hierarchy node's events_url to use the correct pair. Choose top1 for precision; choose top3 when recall matters and you are comfortable with parent/child class overlap. include_live defaults to true, as on the entity, ticker and polygon timelines. Both top1 and top3 include today and yesterday within the requested UTC dates; set include_live=false for archive-only retrieval.
These are the fields you can build against. Nested names use dot notation; optional sections are called out in their descriptions.
schemastringResponse schema name.
viewstringThe view the events are returned in: lite (the default) or full. See About records on Event details.
include_vectorbooleantrue when the request asked for the embedding with include_vector=true; absent otherwise.
classificationobjectThe class requested: field, value and match (top1 or top3), and ontology and level when the request names them instead of field.
classification.fieldstringTaxonomy field, such as gics_sector.
classification.valuestringClass value.
classification.matchstringtop1 (the event's most probable class) or top3 (any of its three most probable).
totalintegerEvents matching the request before paging.
countintegerEvents in this page.
orderstringEvent order: desc (newest first, the default) or asc.
date_windowobjectThe effective inclusive window searched: from, to, index_last_date (the last date with indexed events), archive_cutoff (the last archive date) and include_live. Entity and ticker timelines with include_live=true default to today (UTC) and accept a window wholly after the archive boundary, such as today alone. Their live_events are records in the same format, constrained by both bounds, marked ephemeral and returned on the first page only, outside archive total and cursor paging. Without include_live the default upper bound is the archived index.
date_window.fromdateFirst date searched.
date_window.todateLast date searched.
eventsobject[]The events, as lite records unless view=full (About records on Event details lists both). A full record adds provenance, availability, triples, each ticker's why and v2_preview_success.
events[].event_idstringStable event identifier.
events[].versionstringEvent record version: "2.0-preview".
events[].eventobjectThe event in its original language: date, language, title, description and points.
events[].event.datedateWorld archive date of the event.
events[].event.languagestringISO 639-1 code of the event's original language.
events[].event.titlestringHeadline, in the original language.
events[].event.descriptionstringShort narrative, in the original language.
events[].event.pointsstring[]Key facts of the event, one sentence each.
events[].englishobjectThe event in English: title, description and points, translated when the original language is not English.
events[].coverageobjecttotal_coverage, total_netlocs, coverage_concentration_index, first_seen, last_seen and most_seen, as in Event details.
events[].locationsobject[]Places of the event, its own place first, then places named in it, as in Event details.
events[].signalsobjectSentiment, materiality, time horizon and forward-looking signals with their class probabilities, as in Event details.
events[].tickersobject[]Listed companies the event concerns, in the Event details format without why. Empty when has_tickers is false.
events[].has_tickersbooleanWhether tickers is non-empty.
events[].entitiesobjectNamed entities by NER type, {TYPE: [{name, mention_count, confidence}]}, as in Event details.
events[].sentimentsobjectEntity-level sentiment grouped by entity type. Each item has name, sentiment_label (positive, neutral or negative), and sentiment_score, the final Percentage Margin Z-score.
events[].ontologiesobject[]Classifications of the event, most probable first, as in Event details.
events[].oai_vectorstringOnly with include_vector=true: the event's 3,072-dimension embedding (text-embedding-3-large), comma-separated.
next_cursorstring | nullOpaque cursor for the next page; send it back unchanged. null when there are no more events.
hydration_missesintegerEvents that matched but could not be read; normally 0.
as_ofobjectindex_build and archive_cutoff: the index that answered. Store them with results to reproduce them.
took_msintegerServer time in milliseconds.
languagestring[]Languages the events were filtered to with the language parameter; empty when not filtered.
invalid_json — The request body is not JSON. Every error body, 401 included, is {error, message, status}.api_key_required — No API key was sent. Send it as Authorization: Bearer <key> or the api-key header.invalid_api_key — The API key is invalid or has been revoked.access_denied — The requested archive date is outside the caller's World tier.validation_error — The request is well formed but the API cannot decode or validate it: an unknown body field or query parameter, a missing required parameter, a value of the wrong type, an empty and, or or not, a date that is not a calendar date (in the path, the query or the body), an unknown enum value or a reversed range. The message names the parameter and what is wrong.not_found — The requested date, entity, ticker, or event does not exist in the accessible index.cursor_expired — The cursor belongs to a replaced index build; restart from the first page.rate_limited — The request exceeded the endpoint or account rate limit. Respect Retry-After when supplied.backend_not_configured — The World backend is not configured for this deployment.api_key_auth_unavailable — API key authentication is temporarily unavailable; retry shortly.api_key_metering_unavailable — API key usage metering is temporarily unavailable, so the request was not served; wait for the Retry-After header (30 seconds) and retry.backend_error — The World backend could not be reached or did not return a valid response; retry shortly.backend_timeout — The World backend did not answer within 300 seconds; narrow the request (for example with a date window) or retry.unknown_ontology_value — The field/value combination is valid but the requested class has no indexed match; check the schema or resolve the class again.cursor_filter_mismatch — The cursor was created for a different ontology field, value, or match mode.