AuthorizationstringheaderRequired Bearer API key for programmatic World access.
Example: Bearer nos_sk_...
Get Events in Trend
Page through the event evidence behind one recent Event Trend bucket.
Parameters
query & pathviewenumqueryThe 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
idstringrequiredpathThe id Event Trend returned, valid until its expires_at.
Example: tr_4a45c76c941f482e
bucketdaterequiredqueryThe start of one of the trend's buckets (buckets[].start), a calendar date in YYYY-MM-DD form: required, and a 422 without it or when it is not a date. A date that starts no bucket returns no events.
Example: 2026-09-21
groupstringqueryOne of the bucket's group values (a key of buckets[].groups) to read only that group.
Example: negative
limitintegerqueryPage size from 1 to 200 (a 422 outside it); defaults to 50.
Example: 50
cursorstringquerynext_cursor of the previous page.
Example: AAAAAAAAADI
How to use this endpoint
guidanceUse this route after Event Trend to read the events behind a bucket or one of its groups, most similar first. The trend's id is valid until its expires_at, 15 minutes after the trend was last created; after that this route answers 404 trend_not_found. Create the trend again to continue: while the data is unchanged it returns the same id.
Response body
application/jsonThese are the fields you can build against. Nested names use dot notation; optional sections are called out in their descriptions.
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.
totalintegerEvents in the bucket (and group): its event_count.
countintegerEvents in this page.
limitintegerPage size applied: 50 unless limit is sent.
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. Most similar first.
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.
events[]._scorenumberSimilarity to the trend's query.
events[]._semantic_scorenumberThe same similarity.
events[]._search_datedateArchive date of the event.
events[]._retrievalstringevent_trend.
next_cursorstring | nullOpaque cursor for the next page; null at the end.
Responses and errors
HTTP200Request succeeded. The response body is shown in the panel on the right.
400
invalid_json — The request body is not JSON. Every error body, 401 included, is {error, message, status}.401
api_key_required — No API key was sent. Send it as Authorization: Bearer <key> or the api-key header.401
invalid_api_key — The API key is invalid or has been revoked.403
access_denied — The requested archive date is outside the caller's World tier.422
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.404
not_found — The requested date, entity, ticker, or event does not exist in the accessible index.410
cursor_expired — The cursor was minted against a replaced index build. Restart pagination from the first page.429
rate_limited — The request exceeded the endpoint or account rate limit. Respect Retry-After when supplied.501
backend_not_configured — The World backend is not configured for this deployment.503
api_key_auth_unavailable — API key authentication is temporarily unavailable; retry shortly.503
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.502
backend_error — The World backend could not be reached or did not return a valid response; retry shortly.504
backend_timeout — The World backend did not answer within 300 seconds; narrow the request (for example with a date window) or retry.