NEAR AI Cloud: Get per-model consumption timeseries (Admin only)
GET /v1/admin/platform/model-consumption-timeseries Get per-model consumption timeseries (Admin only) Deprecated: this endpoint is moving to cloud-platform at the same path; the cloud-platform base URL will be announced. Behaviour may differ in edge cases.
Returns consumed cost, requests, and tokens per time bucket broken down by model. Top N models by total period cost are returned as separate series; all others are collapsed into a single "Other" bucket. Model labels use the current canonical name from the models table (joined on model_id, rename-safe).
The query does not zero-fill missing (bucket, model) pairs — the frontend must impute zeros for models absent from a bucket.
Consumed cost = metered inference cost, NOT cash revenue (includes grant credits).
Admin permissions: admin session, read_write token, or read_only token. Approved read across organizations; does not mutate business state.
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.
- granularity (query, string): Time granularity: hour (≤31d), day (≤366d, default), week (≤3y), month (≤5y).
- top_n (query, integer): Top-N models to return as separate series (1-20, default 15); rest → 'Other'.
Responses: 200: Model consumption timeseries retrieved successfully
- data (array of object, required)
- bucket (string, required): ISO 8601 bucket start (truncated to granularity).
- consumed_cost_usd (number, double, required): Consumed usage cost for this (bucket, model) pair, USD.
- model_label (string, required): Current canonical model name (from
models.model_name), or "Other". - requests (integer, int64, required)
- tokens (integer, int64, required): input_tokens + output_tokens.
- granularity (string, required)
- model_labels (array of string, required): Ordered list of model labels in the response (top-N + "Other" if present).
- period_end (string, date-time, required)
- period_start (string, date-time, required) 400: Invalid request 401: Unauthorized 403: Missing admin privileges (forbidden) or insufficient token permission (insufficient_permissions). 500: Internal server error 504: Analytics statement budget exceeded