LLM user percentiles
Usage percentile per gateway-attributed user with usage in the range, ranked by total tokens. A percentile of 0.25 or above is what the team adoption views count as a seat in use. Filters are limited to provider and user_group, and each user's groups come back narrowed to the selected ones. Bounded rather than paged: the heaviest 500 users are returned in one response and no page params are accepted. Percentiles are always computed over the whole population, so meta.total is the real headcount and exceeds items.length exactly when the response is a sample.
Usage percentile per gateway-attributed user with usage in the range, ranked by total tokens. A percentile of 0.25 or above is what the team adoption views count as a seat in use. Filters are limited to provider and user_group, and each user's groups come back narrowed to the selected ones.
Bounded rather than paged: the heaviest 500 users are returned in one response and no page params are accepted. Percentiles are always computed over the whole population, so meta.total is the real headcount and exceeds items.length exactly when the response is a sample.
ApiKeyAuthAuthorizationBearer <token>Bearer token authentication. Send an API key (a saai_api_-prefixed token) as Authorization: Bearer <token>.
Required permission
view_user_analyticsstart_time*stringdate-timeend_time*stringdate-timeprovider?array<>user_group?array<string>The request has succeeded.
application/json- response
Per-user usage percentiles; powers the team dot strips and the "active" bar.
items*array<>The items in this page.
meta*Paging information for a list response.
curl -X GET "https://example.com/analytics/llm-user-percentiles?start_time=2019-08-24T14%3A15%3A22Z&end_time=2019-08-24T14%3A15%3A22Z"{ "items": [ { "user_id": "a169451c-8525-4352-b8ca-070dd449a1a5", "display_name": "string", "groups": [ "string" ], "percentile": 0.1, "tokens": 0 } ], "meta": { "total": 0, "offset": 0, "limit": 0 }}