Endpoint Service
Get endpoint analytics
Returns aggregated request, token, latency, throughput, error, and resource-utilization metrics for an endpoint over a time range. Optionally includes time-series buckets and a per-deployment breakdown.
Authorization
bearerAuth AuthorizationBearer <token>
In: header
Path Parameters
projectId*string
Project identifier.
id*string
Endpoint identifier.
Query Parameters
deploymentId?string
Restrict to a single deployment under this endpoint.
startTime?string
Inclusive start of the time range. Defaults to 24 hours ago if unset.
Format
date-timeendTime?string
Exclusive end of the time range. Defaults to now if unset.
Format
date-timeincludeTimeSeries?boolean
When true, include per-bucket time series in the response.
granularity?string
Time-series bucket duration, such as 1m, 1h, or 1d. Defaults to 1d.
Response Body
application/json
application/json
curl -X GET "https://example.com/projects/string/endpoints/string/analytics"{ "endpointId": "string", "timeRange": { "startTime": "2019-08-24T14:15:22Z", "endTime": "2019-08-24T14:15:22Z" }, "metrics": { "endpointId": "string", "timeRange": { "startTime": "2019-08-24T14:15:22Z", "endTime": "2019-08-24T14:15:22Z" }, "requestMetrics": { "totalRequests": "string", "successfulRequests": "string", "failedRequests": "string", "requestsPerSecond": 0, "requestsByStatusCode": { "property1": "string", "property2": "string" } }, "latencyMetrics": { "ttftP50Ms": 0, "ttftP90Ms": 0, "ttftP99Ms": 0, "latencyP50Ms": 0, "latencyP90Ms": 0, "latencyP99Ms": 0, "itlP50Ms": 0, "itlP90Ms": 0, "itlP99Ms": 0 }, "throughputMetrics": { "tokensPerSecond": 0, "requestsPerSecond": 0, "avgBatchSize": 0, "avgBatchDepth": 0 }, "errorMetrics": { "errorRate": 0, "errorsByType": { "property1": "string", "property2": "string" } }, "resourceUtilization": { "cpuUtilization": 0, "gpuUtilization": 0, "memoryUtilization": 0, "gpuMemoryUtilization": 0, "networkBandwidthMbps": 0 }, "tokenMetrics": { "totalInputTokens": "string", "totalOutputTokens": "string", "avgInputTokens": 0, "avgOutputTokens": 0 }, "deploymentMetrics": [ { "deploymentId": "string", "endpointId": "string", "timeRange": { "startTime": "2019-08-24T14:15:22Z", "endTime": "2019-08-24T14:15:22Z" }, "requestMetrics": { "totalRequests": "string", "successfulRequests": "string", "failedRequests": "string", "requestsPerSecond": 0, "requestsByStatusCode": { "property1": "string", "property2": "string" } }, "latencyMetrics": { "ttftP50Ms": 0, "ttftP90Ms": 0, "ttftP99Ms": 0, "latencyP50Ms": 0, "latencyP90Ms": 0, "latencyP99Ms": 0, "itlP50Ms": 0, "itlP90Ms": 0, "itlP99Ms": 0 }, "throughputMetrics": { "tokensPerSecond": 0, "requestsPerSecond": 0, "avgBatchSize": 0, "avgBatchDepth": 0 }, "errorMetrics": { "errorRate": 0, "errorsByType": { "property1": "string", "property2": "string" } }, "resourceUtilization": { "cpuUtilization": 0, "gpuUtilization": 0, "memoryUtilization": 0, "gpuMemoryUtilization": 0, "networkBandwidthMbps": 0 }, "tokenMetrics": { "totalInputTokens": "string", "totalOutputTokens": "string", "avgInputTokens": 0, "avgOutputTokens": 0 } } ] }, "timeSeries": [ { "timestamp": "2019-08-24T14:15:22Z", "values": { "property1": 0, "property2": 0 } } ], "deploymentAnalytics": [ { "deploymentId": "string", "endpointId": "string", "timeRange": { "startTime": "2019-08-24T14:15:22Z", "endTime": "2019-08-24T14:15:22Z" }, "metrics": { "deploymentId": "string", "endpointId": "string", "timeRange": { "startTime": "2019-08-24T14:15:22Z", "endTime": "2019-08-24T14:15:22Z" }, "requestMetrics": { "totalRequests": "string", "successfulRequests": "string", "failedRequests": "string", "requestsPerSecond": 0, "requestsByStatusCode": { "property1": "string", "property2": "string" } }, "latencyMetrics": { "ttftP50Ms": 0, "ttftP90Ms": 0, "ttftP99Ms": 0, "latencyP50Ms": 0, "latencyP90Ms": 0, "latencyP99Ms": 0, "itlP50Ms": 0, "itlP90Ms": 0, "itlP99Ms": 0 }, "throughputMetrics": { "tokensPerSecond": 0, "requestsPerSecond": 0, "avgBatchSize": 0, "avgBatchDepth": 0 }, "errorMetrics": { "errorRate": 0, "errorsByType": { "property1": "string", "property2": "string" } }, "resourceUtilization": { "cpuUtilization": 0, "gpuUtilization": 0, "memoryUtilization": 0, "gpuMemoryUtilization": 0, "networkBandwidthMbps": 0 }, "tokenMetrics": { "totalInputTokens": "string", "totalOutputTokens": "string", "avgInputTokens": 0, "avgOutputTokens": 0 } }, "timeSeries": [ { "timestamp": "2019-08-24T14:15:22Z", "values": { "property1": 0, "property2": 0 } } ] } ]}Delete an endpoint DELETE
Permanently deletes an endpoint. Delete its deployments first; use `etag` to reject the request if the endpoint changed after it was read.
List endpoint events GET
Lists an endpoint's audit and lifecycle events newest first. The feed combines endpoint changes with provisioning, scaling, readiness, rollout, and other events from deployments under the endpoint.