> ## Documentation Index > Fetch the complete documentation index at: https://docs.together.ai/llms.txt > Use this file to discover all available pages before exploring further. # 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. ## OpenAPI ````yaml GET /projects/{projectId}/endpoints/{id}/analytics openapi: 3.1.0 info: title: Together APIs description: The Together REST API. See https://docs.together.ai for more details. version: 2.0.0 termsOfService: https://www.together.ai/terms-of-service contact: name: Together Support url: https://www.together.ai/contact license: name: MIT url: https://github.com/togethercomputer/openapi/blob/main/LICENSE servers: - url: https://api.together.ai/v1 description: Default environment for APIs - url: https://api-inference.together.ai/v2 description: Optimized environment for inference security: - bearerAuth: [] paths: /projects/{projectId}/endpoints/{id}/analytics: get: tags: - EndpointService summary: Get endpoint analytics description: >- 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. operationId: EndpointService_GetEndpointAnalytics parameters: - name: projectId in: path required: true schema: description: Project identifier. type: string - name: id in: path required: true schema: description: Endpoint identifier. type: string - name: deploymentId in: query schema: type: string description: Restrict to a single deployment under this endpoint. - name: startTime in: query schema: type: string format: date-time description: >- Inclusive start of the time range. Defaults to 24 hours ago if unset. - name: endTime in: query schema: type: string format: date-time description: Exclusive end of the time range. Defaults to now if unset. - name: includeTimeSeries in: query schema: type: boolean description: When true, include per-bucket time series in the response. - name: granularity in: query schema: type: string description: >- Time-series bucket duration, such as `1m`, `1h`, or `1d`. Defaults to `1d`. responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/DE.AnalyticsData' default: description: Default error response content: application/json: schema: $ref: '#/components/schemas/ErrorData' servers: - url: https://api.together.ai/v2 components: schemas: DE.AnalyticsData: type: object properties: endpointId: type: string description: ID of the endpoint summarized by these analytics. timeRange: $ref: '#/components/schemas/DE.MetricsTimeRange' description: Closed-open time range covered by the analytics. metrics: allOf: - $ref: '#/components/schemas/DE.EndpointMetrics' description: Aggregated metrics over the time range. timeSeries: type: array items: $ref: '#/components/schemas/DE.TimeSeriesDataPoint' description: >- Per-bucket metric samples, included only when `includeTimeSeries` is true. deploymentAnalytics: type: array items: $ref: '#/components/schemas/DE.DeploymentAnalyticsData' description: Per-deployment analytics. description: >- Endpoint-wide usage and performance analytics with optional time-series and per-deployment breakdowns. ErrorData: type: object required: - error properties: error: type: object properties: message: type: string nullable: false type: type: string nullable: false param: type: string nullable: true default: null code: type: string nullable: true default: null required: - type - message DE.MetricsTimeRange: type: object properties: startTime: type: string description: Inclusive start of the time range. format: date-time endTime: type: string description: Exclusive end of the time range. format: date-time description: Closed-open time range used by metrics and analytics responses. DE.EndpointMetrics: type: object properties: endpointId: type: string description: The endpoint these metrics describe. timeRange: allOf: - $ref: '#/components/schemas/DE.MetricsTimeRange' description: Time range covered by the metrics. requestMetrics: $ref: '#/components/schemas/DE.RequestMetrics' description: Request counts and rates. latencyMetrics: $ref: '#/components/schemas/DE.LatencyMetrics' description: >- Time-to-first-token, end-to-end, and inter-token latency percentiles. throughputMetrics: $ref: '#/components/schemas/DE.ThroughputMetrics' description: Token, request, and batching throughput. errorMetrics: $ref: '#/components/schemas/DE.ErrorMetrics' description: Error rate and counts by error type. resourceUtilization: $ref: '#/components/schemas/DE.ResourceUtilization' description: Average CPU, GPU, memory, and network utilization. tokenMetrics: $ref: '#/components/schemas/DE.TokenMetrics' description: Input and output token totals and averages. deploymentMetrics: type: array items: $ref: '#/components/schemas/DE.DeploymentMetrics' description: Per-deployment breakdown, if the endpoint has multiple deployments. description: >- Operational metrics aggregated across all deployments receiving traffic for an endpoint. DE.TimeSeriesDataPoint: type: object properties: timestamp: type: string format: date-time description: Start time of the metric bucket. values: type: object additionalProperties: type: number description: Metric names mapped to their numeric values for this bucket. description: Timestamped bucket containing one or more named metric values. DE.DeploymentAnalyticsData: type: object properties: deploymentId: type: string description: ID of the deployment summarized by these analytics. endpointId: type: string description: ID of the deployment's parent endpoint. timeRange: $ref: '#/components/schemas/DE.MetricsTimeRange' description: Closed-open time range covered by the analytics. metrics: $ref: '#/components/schemas/DE.DeploymentMetrics' description: Aggregate operational metrics for the deployment. timeSeries: type: array items: $ref: '#/components/schemas/DE.TimeSeriesDataPoint' description: Per-bucket metric samples for the deployment. description: Usage and performance analytics for one deployment under an endpoint. DE.RequestMetrics: type: object properties: totalRequests: type: string description: Total requests received during the time range. successfulRequests: type: string description: Requests completed successfully during the time range. failedRequests: type: string description: Requests that failed during the time range. requestsPerSecond: type: number description: Average requests per second over the time range. requestsByStatusCode: type: object additionalProperties: type: string description: Request counts keyed by HTTP status code. description: Request counts, rate, and status-code distribution over a time range. DE.LatencyMetrics: type: object properties: ttftP50Ms: type: number description: 50th-percentile time to first token, in milliseconds. ttftP90Ms: type: number description: 90th-percentile time to first token, in milliseconds. ttftP99Ms: type: number description: 99th-percentile time to first token, in milliseconds. latencyP50Ms: type: number description: 50th-percentile end-to-end request latency, in milliseconds. latencyP90Ms: type: number description: 90th-percentile end-to-end request latency, in milliseconds. latencyP99Ms: type: number description: 99th-percentile end-to-end request latency, in milliseconds. itlP50Ms: type: number description: 50th-percentile inter-token latency, in milliseconds. itlP90Ms: type: number description: 90th-percentile inter-token latency, in milliseconds. itlP99Ms: type: number description: 99th-percentile inter-token latency, in milliseconds. description: >- Time-to-first-token, end-to-end, and inter-token latency percentiles in milliseconds. DE.ThroughputMetrics: type: object properties: tokensPerSecond: type: number description: Average generated tokens per second. requestsPerSecond: type: number description: Average completed requests per second. avgBatchSize: type: number description: Average number of requests processed in each runtime batch. avgBatchDepth: type: number description: Average number of batches queued or in flight in the serving engine. description: Token, request, and batching throughput over a time range. DE.ErrorMetrics: type: object properties: errorRate: type: number description: Percentage in [0, 100]. errorsByType: type: object additionalProperties: type: string description: >- Counts of errors keyed by error type (e.g. HTTP status code or error kind). description: >- Error rate and aggregate counts by error type. Individual error samples are not included. DE.ResourceUtilization: type: object properties: cpuUtilization: type: number description: Average CPU utilization across replicas, as a percentage. gpuUtilization: type: number description: Average GPU compute utilization across replicas, as a percentage. memoryUtilization: type: number description: Average system memory utilization across replicas, as a percentage. gpuMemoryUtilization: type: number description: Average GPU memory utilization across replicas, as a percentage. networkBandwidthMbps: type: number description: Average network throughput across replicas, in megabits per second. description: >- Average compute, memory, and network utilization for replicas over a time range. DE.TokenMetrics: type: object properties: totalInputTokens: type: string description: Total input tokens processed during the time range. totalOutputTokens: type: string description: Total output tokens generated during the time range. avgInputTokens: type: number description: Average input tokens per request. avgOutputTokens: type: number description: Average output tokens per request. description: Aggregate and per-request token usage over a time range. DE.DeploymentMetrics: type: object properties: deploymentId: type: string description: ID of the deployment summarized by these metrics. endpointId: type: string description: ID of the deployment's parent endpoint. timeRange: $ref: '#/components/schemas/DE.MetricsTimeRange' description: Closed-open time range covered by the metrics. requestMetrics: $ref: '#/components/schemas/DE.RequestMetrics' description: Request counts and rates. latencyMetrics: $ref: '#/components/schemas/DE.LatencyMetrics' description: >- Time-to-first-token, end-to-end, and inter-token latency percentiles. throughputMetrics: $ref: '#/components/schemas/DE.ThroughputMetrics' description: Token, request, and batching throughput. errorMetrics: $ref: '#/components/schemas/DE.ErrorMetrics' description: Error rate and counts by error type. resourceUtilization: $ref: '#/components/schemas/DE.ResourceUtilization' description: Average CPU, GPU, memory, and network utilization. tokenMetrics: $ref: '#/components/schemas/DE.TokenMetrics' description: Input and output token totals and averages. description: Operational metrics for one deployment under an endpoint. securitySchemes: bearerAuth: type: http scheme: bearer x-bearer-format: bearer x-default: default ````