Distribution queries
Aggregated snapshots of model metrics over a time window. Every 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 request wrapper is identical to the one in 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}. To target virtual models, flip the value to false and swap groupBy: ["modelName"] for groupBy: ["virtualModel"] (the alias used in groupBy/aggregations).Count by model name
Count by model name
Request counts grouped by model:
Sum tokens by model
Sum tokens by model
Total input and output tokens per model:
Latency percentiles by model
Latency percentiles by model
p50, p90, and p99 latency grouped by model:
Group by metadata
Group by metadata
Group by model and a custom metadata key:
Multi-dimensional grouping
Multi-dimensional grouping
Group by multiple dimensions (model + subject):
Filter high-latency requests
Filter high-latency requests
Requests slower than 1 second, grouped by model:
Filter by latency range
Filter by latency range
Requests within a latency band:
Filter by token counts
Filter by token counts
Combine input and output token thresholds:
Filter by team
Filter by team
Filter to specific teams using array operators:
Filter by metadata
Filter by metadata
Restrict by a custom metadata value:
Virtual-model metrics only
Virtual-model metrics only
Only requests routed through a virtual model. Note
virtualModel in groupBy/aggregations but virtualModelName in filters:Complex filter combination
Complex filter combination
Combine multiple filter types: