List runs for a prompt
Individual model answers behind the aggregates, newest first, without their text — the list stays small enough to page through. Fetch `GET /prompts/{promptId}/runs/{runId}` for the answer itself.
Individual model answers behind the aggregates, newest first, without their text — the list stays small enough to page through. Fetch GET /prompts/{promptId}/runs/{runId} for the answer itself.
Authorization
BearerAuth An instance admin key from ADMIN_API_KEYS, or an organization key (elmo_…) issued from the dashboard.
In: header
Path Parameters
uuidQuery Parameters
Inclusive lower bound of the window, an ISO 8601 timestamp such as 2026-01-01T00:00:00Z. A bare YYYY-MM-DD is rejected: that is /prompts/{promptId}/snapshot's spelling and means a local calendar day there.
date-timeExclusive upper bound of the window, an ISO 8601 timestamp. The window is half-open: a run at exactly end is outside it.
date-timeRestrict to one model, e.g. chatgpt. See GET /models.
Page number, 1-based.
1 <= value1Items per page. Values above the maximum are clamped, not rejected.
1 <= value <= 10020Response Body
application/json
application/json
application/json
application/json
application/json
application/json
application/json
curl -X GET "https://example.com/prompts/497f6eca-6276-4993-bfeb-53cbbbba6f08/runs?start=2019-08-24T14%3A15%3A22Z&end=2019-08-24T14%3A15%3A22Z"{ "data": [ { "id": "497f6eca-6276-4993-bfeb-53cbbbba6f08", "promptId": "b5415d63-4390-40ec-8c2b-33a2db2f5c67", "brandId": "string", "model": "string", "provider": "string", "webSearchEnabled": true, "brandMentioned": true, "competitorsMentioned": [ "string" ], "webQueries": [ "string" ], "citationCount": 0, "createdAt": "2019-08-24T14:15:22Z" } ], "pagination": { "page": 0, "limit": 0, "total": 0, "totalPages": 0 }}