Timeseries queries
Time-bucketed model metrics over a window. Every timeseries query must includeinterval (or the deprecated intervalInSeconds). Buckets are expressed as <positive integer> <unit> strings like "5 minute", "1 hour", or "1 day". Each example below posts JSON to:
Authorization: Bearer <your_api_key> and Content-Type: application/json. To keep the snippets short, only the JSON body is shown; the wrapper is identical to the Overview Quick Start.
By default, model metrics include both models and virtual models. The examples below pin the model side with
{"fieldName": "virtualModelName", "operator": "IS_NULL", "value": true}. Flip the value to false (and swap groupBy: ["modelName"] for groupBy: ["virtualModel"]) for virtual-model-only series.Basic hourly counts
Basic hourly counts
Hourly request counts:
5-minute intervals
5-minute intervals
Fine-grained traffic with 5-minute buckets:
Hourly counts by model
Hourly counts by model
Hourly counts grouped by model:
Hourly p99 latency by model
Hourly p99 latency by model
Track p99 latency regressions per model:
Hourly counts by team
Hourly counts by team
Track per-team adoption over time:
Timeseries with model + latency filter
Timeseries with model + latency filter
Restrict to specific models and a latency threshold:
Hourly cost by model
Hourly cost by model
Cost burn-down per model over time:
Hourly metadata breakdown
Hourly metadata breakdown
Group hourly counts by a custom metadata key:
Daily over a week
Daily over a week
Daily traffic across a 7-day window:
Complex timeseries query
Complex timeseries query
Filters + groupBy + metadata together: