API Reference
Log In
API Reference

List AI Completion Metrics by team

get
https://api.revenium.ai/profitstream/v2/api/sources/metrics/ai/completions

Retrieve a paginated list of AI completion metrics for a specified team.

Recent Requests
Log in to see full request history
TimeStatusUser Agent
Retrieving recent requests…
LoadingLoading…
Query Params
string

Filter start date/time in ISO 8601 format.

string

Filter end date/time in ISO 8601 format.

int64
0 to 60000

Minimum time to first token (in milliseconds).

int64
0 to 60000

Maximum time to first token (in milliseconds).

int64
0 to 300000

Minimum request duration (in milliseconds).

int64
0 to 300000

Maximum request duration (in milliseconds).

int64
0 to 10000

Minimum mediation latency (in milliseconds).

int64
0 to 10000

Maximum mediation latency (in milliseconds).

int64
0 to 10000000

Minimum input tokens.

int64
0 to 10000000

Maximum input tokens.

int64
0 to 10000000

Minimum output tokens.

int64
0 to 10000000

Maximum output tokens.

int64
0 to 5000000

Minimum reasoning tokens.

int64
0 to 5000000

Maximum reasoning tokens.

int64
0 to 5000000

Minimum cached tokens.

int64
0 to 5000000

Maximum cached tokens.

int64
0 to 20000000

Minimum total tokens.

int64
0 to 20000000

Maximum total tokens.

number
0 to 99999.99

Minimum input cost ($).

number
0 to 99999.99

Maximum input cost ($).

number
0 to 99999.99

Minimum output cost ($).

number
0 to 99999.99

Maximum output cost ($).

number
0 to 999999.99

Minimum total cost ($).

number
0 to 999999.99

Maximum total cost ($).

string
length between 1 and 255

Exact transaction ID match.

string
length between 1 and 255

Exact trace ID match.

string
length between 1 and 255

Filter by trace type. Use 'unknown' for metrics without traceType.

string
length between 1 and 255

Filter by trace name.

string
length between 1 and 255

Filter by organization name.

string

Filter by subscriber email.

string
length between 1 and 255

Filter by subscriber ID.

string
length between 1 and 255

Filter by subscription ID.

string
length between 1 and 255

Filter by product ID.

string
length between 1 and 255

Filter by agent name.

string
length between 1 and 255

Filter by AI provider.

string
length between 1 and 255

Filter by AI model.

string
length between 1 and 255

Filter by model source.

string
length between 1 and 255

Filter by task type.

double
0 to 2

Minimum temperature value.

double
0 to 2

Maximum temperature value.

string
enum

Filter by stop reason.

string
length between 1 and 255

Filter by error reason.

number
0 to 1

Minimum response quality score.

number
0 to 1

Maximum response quality score.

string
length between 1 and 255

Filter by credential name.

string
length between 1 and 255

Filter by system fingerprint.

boolean
required

Whether to include coding assistant metrics (e.g. Claude Code, Gemini CLI). When false (default), coding assistant records are excluded from results.

string
required

Unique identifier of the team (organization). Format: Revenium hashid (URL-safe encoded string).

integer
≥ 0
Defaults to 0

Zero-based page index (0..N)

integer
≥ 1
Defaults to 10

The size of the page to be returned

sort
array of strings
Defaults to requestTime,DESC

Sorting criteria in the format: property,(asc|desc). Default sort order is ascending. Multiple sort criteria are supported.

sort
Headers
string
enum
Defaults to application/json

Generated from available response content types

Allowed:
Responses

Updated 6 months ago

Language
Credentials
Header
LoadingLoading…
Response
Click Try It! to start a request and see the response here! Or choose an example:
application/json
application/hal+json
*/*

Updated 6 months ago