Get performance (response time) by model

get

https://api.revenium.ai/profitstream/v2/api/sources/metrics/ai/performance-metric-by-model

Returns the request duration in milliseconds per model over the whole window, with no time buckets. group chooses the statistic: MEAN (the default), MEDIAN, MAXIMUM or MINIMUM duration of a single call, or TOTAL, the sum of all call durations.

Recent Requests

Time	Status	User Agent
Retrieving recent requests…

Loading…

Query Params

teamId

string

required

ID of the team that owns this data.

period

string

enum

Predefined time window to aggregate results (e.g., TWELVE_MONTHS). Ignored if both startDate and endDate are provided. Defaults to TWELVE_MONTHS when no custom date range is specified.

group

string

enum

Aggregation group for the metric.

Allowed:

startDate

string

Start of a custom date range in ISO 8601 format (e.g., 2025-09-01T00:00:00Z). Must be provided together with endDate. When both are provided, the period parameter is ignored and this custom range is used instead.

endDate

string

End of a custom date range in ISO 8601 format (e.g., 2025-09-30T23:59:59Z). Must be provided together with startDate. When both are provided, the period parameter is ignored and this custom range is used instead.

models

array of strings

Optional list of AI models to filter. Valid models can be obtained using the /sources/ai/models endpoint. Omit to include all models.

models

Headers

string

enum

Defaults to application/json

Generated from available response content types

Allowed:

Responses

Language

Credentials

Header

Loading…

Response

Click Try It! to start a request and see the response here! Or choose an example:

application/json

*/*

200Returns model performance metrics over time.

400Invalid input data

401Unauthorized - Authentication required

403Forbidden - Insufficient permissions

404Not Found

409Conflict

422Unprocessable Content

429Too Many Requests

504Gateway Timeout