API reference · Schema
EndpointAnalytics
objectstringrequiredAlways `endpoint_analytics`: the type of this object
One of
endpoint_analyticsendpoint_idstringrequiredID of the endpoint
startstring (date-time)requiredStart of the period (inclusive)
endstring (date-time)requiredEnd of the period (exclusive)
bucketstringrequiredWidth of each `series` bucket (UTC)
One of
minutehourdaytotalsobjectrequiredThe whole endpoint over the whole period
ShowHide 8 fields of
totalsrequestsintegerrequiredRequests that finished in the period
errorsintegerrequiredOf those, requests that did not complete successfully (errors and aborts)
input_tokensstringrequiredDecimal string
output_tokensstringrequiredDecimal string
latency_msobjectrequiredTotal time per request, from when the platform received it until the response finished
ShowHide 3 fields of
latency_msavginteger | nullrequiredMean request latency in milliseconds; null without requests
p50integer | nullrequiredMedian (p50) request latency in milliseconds; null without requests
p95integer | nullrequired95th percentile (p95) request latency in milliseconds; null without requests
first_byte_ms_avginteger | nullrequiredMean time to the first byte of the response in milliseconds; null without requests
replica_secondsstringrequiredBilled ready replica-seconds (a 2-GPU replica-second counts 2), decimal string
replica_coststringrequiredWhat those seconds were charged
pattern ^-?[0-9]+$
deploymentsarray of objectrequiredThe same figures per deployment that had requests or replica time
ShowHide 9 fields of
deploymentsdeployment_idstringrequiredID of the deployment
requestsintegerrequiredRequests that finished in the period
errorsintegerrequiredOf those, requests that did not complete successfully (errors and aborts)
input_tokensstringrequiredDecimal string
output_tokensstringrequiredDecimal string
latency_msobjectrequiredTotal time per request, from when the platform received it until the response finished
ShowHide 3 fields of
latency_msavginteger | nullrequiredMean request latency in milliseconds; null without requests
p50integer | nullrequiredMedian (p50) request latency in milliseconds; null without requests
p95integer | nullrequired95th percentile (p95) request latency in milliseconds; null without requests
first_byte_ms_avginteger | nullrequiredMean time to the first byte of the response in milliseconds; null without requests
replica_secondsstringrequiredBilled ready replica-seconds (a 2-GPU replica-second counts 2), decimal string
replica_coststringrequiredWhat those seconds were charged
pattern ^-?[0-9]+$
seriesarray of objectrequiredRequest figures per bucket and deployment in time order; buckets without requests are left out
ShowHide 8 fields of
seriesbucket_startstring (date-time)requiredStart of the bucket (UTC)
deployment_idstring | nullrequiredID of the deployment
requestsintegerrequiredRequests that finished in the period
errorsintegerrequiredOf those, requests that did not complete successfully (errors and aborts)
input_tokensstringrequiredDecimal string
output_tokensstringrequiredDecimal string
latency_msobjectrequiredTotal time per request, from when the platform received it until the response finished
ShowHide 3 fields of
latency_msavginteger | nullrequiredMean request latency in milliseconds; null without requests
p50integer | nullrequiredMedian (p50) request latency in milliseconds; null without requests
p95integer | nullrequired95th percentile (p95) request latency in milliseconds; null without requests
first_byte_ms_avginteger | nullrequiredMean time to the first byte of the response in milliseconds; null without requests
{
"object": "endpoint_analytics",
"endpoint_id": "string",
"start": "2026-01-01T00:00:00.000Z",
"end": "2026-01-01T00:00:00.000Z",
"bucket": "minute",
"totals": {
"requests": 1,
"errors": 1,
"input_tokens": "string",
"output_tokens": "string",
"latency_ms": {
"avg": 1,
"p50": 1,
"p95": 1
},
"first_byte_ms_avg": 1,
"replica_seconds": "string",
"replica_cost": "1500000000"
},
"deployments": [
{
"deployment_id": "string",
"requests": 1,
"errors": 1,
"input_tokens": "string",
"output_tokens": "string",
"latency_ms": {
"avg": 1,
"p50": 1,
"p95": 1
},
"first_byte_ms_avg": 1,
"replica_seconds": "string",
"replica_cost": "1500000000"
}
],
"series": [
{
"bucket_start": "2026-01-01T00:00:00.000Z",
"deployment_id": "string",
"requests": 1,
"errors": 1,
"input_tokens": "string",
"output_tokens": "string",
"latency_ms": {
"avg": 1,
"p50": 1,
"p95": 1
},
"first_byte_ms_avg": 1
}
]
}Used by
- Requests, errors, tokens, latency and billed replica time, by deployment and over time
GET /v1/endpoints/{dedicated_endpoint_id}/analytics