Skip to main content
POST
The search queries an AI generates behind the scenes when answering a prompt. Coverage is partial: metrics cover only runs that emitted fanout data (see info.coverage_note).
  • Metrics: total_fanouts (query count), fanouts_per_execution (avg queries per execution), query_variations (distinct fanout queries), share.
  • group_by: prompt (default), query, model, region, date.
  • query requires prompt in group_by; share requires query; query_variations can’t be combined with query.
  • analysis_type filter defaults to visibility.
New to the v2 reports? See Filtering & concepts for the shared request shape, filter tree, grouping, and pagination.
POST /v2/reports/query-fanouts/stream takes the same request body and returns Server-Sent Events: one summary event (the info block), then one result event per row. limit/cursor are ignored; it returns everything by default. Pass max_results to cap.
Response (text/event-stream)

Authorizations

X-API-Key
string
header
required

Body

application/json
category_id
string
required
start_date
string
required

YYYY-MM-DD, ET, inclusive

end_date
string
required

YYYY-MM-DD, ET, inclusive

group_by
enum<string>[]
Available options:
date,
model,
region,
prompt,
query
metrics
enum<string>[] | null
Available options:
fanouts_per_execution,
total_fanouts,
share,
query_variations
interval
enum<string>
default:day
Available options:
day,
week,
month
filter
FilterNode · object | null

A leaf (field/op/value) or an and/or/not group.

sort
SortSpec · object | null
limit
integer | null

Page size; default 10, max 50.

Required range: 0 < x <= 50
max_results
integer | null

Stream endpoint only: cap the number of streamed rows (default: all).

Required range: x > 0
cursor
string | null

Response

Successful Response

The response is of type Response Query Fanouts V2 V2 Reports Query Fanouts Post · object.