NEAR AI Cloud: Get the per-model consumption ranking (Admin only)
GET /v1/admin/platform/model-revenue Get the per-model consumption ranking (Admin only) Models for the selected period ranked by consumed cost, with requests, tokens, unique orgs, verifiable flag, provider type, and latency. Paginated and filterable.
Parameters:
- start (query, string): Start of time range (ISO 8601). Defaults to 30 days ago.
- end (query, string): End of time range (ISO 8601). Defaults to now.
- limit (query, integer): Page size (1-1000, default 100).
- offset (query, integer): Page offset (default 0).
- verifiable (query, boolean): Filter to verifiable (true) or non-verifiable (false) models.
- provider_type (query, string): Filter by provider type (e.g. vllm, external, chutes).
- sort (query, string): Sort: revenue (default), requests, tokens.
Responses: 200: Model revenue retrieved successfully
- data (array of object, required)
- avg_ttft_ms (number, double)
- consumed_cost_usd (number, double, required): Consumed usage cost, USD.
- fallback_consumed_cost_usd (number, double, required)
- fallback_requests (integer, int64, required)
- model_name (string, required)
- p95_ttft_ms (number, double)
- provider_type (string)
- requests (integer, int64, required)
- served_provider_breakdown (array of object, required)
- consumed_cost_usd (number, double, required)
- provider_tier (string)
- provider_type (string)
- requests (integer, int64, required)
- served_via_fallback (boolean, required)
- tokens (integer, int64, required)
- tokens (integer, int64, required)
- unique_orgs (integer, int64, required)
- verifiable (boolean, required): Current model metadata (may differ from when the usage occurred).
- limit (integer, int64, required)
- offset (integer, int64, required)
- period_end (string, date-time, required)
- period_start (string, date-time, required)
- total (integer, int64, required): Total matching models (before limit/offset). 400: Invalid request 401: Unauthorized 500: Internal server error