> ## Documentation Index > Fetch the complete documentation index at: https://www.truefoundry.com/llms.txt > Use this file to discover all available pages before exploring further. # Get metric data for a cluster chart > Get the metric data for a single cluster chart. Call `GET /metrics/cluster/{id}/charts` (tool: `list_cluster_metric_charts`) first to get the chart and its input `params`. ## OpenAPI ````yaml /openapi.json get /api/svc/v1/metrics/cluster/{id}/charts/{chart} openapi: 3.1.0 info: title: TrueFoundry API description: API for TrueFoundry version: 0.1.0 contact: {} servers: - url: https://{controlPlaneURL} variables: controlPlaneURL: default: app.truefoundry.com description: Control Plane URL security: [] tags: - name: Agent - name: Agent Skills - name: Applications - name: Metrics - name: Apply - name: Artifacts - name: Audit Logs - name: Clusters - name: Jobs - name: Logs - name: MCP Servers V2 - name: MLRepos - name: Model Deployments - name: Models - name: Personal Access Tokens - name: Prompts - name: Provider Integrations - name: SCIM v2 - name: Secret Groups - name: Secrets - name: Teams - name: Traces - name: Users - name: Virtual Accounts - name: Role Bindings - name: Workspaces paths: /api/svc/v1/metrics/cluster/{id}/charts/{chart}: get: tags: - Metrics summary: Get metric data for a cluster chart description: >- Get the metric data for a single cluster chart. Call `GET /metrics/cluster/{id}/charts` (tool: `list_cluster_metric_charts`) first to get the chart and its input `params`. operationId: Metrics.getClusterChartData parameters: - name: chart required: true in: path description: Chart identifier returned by `list_cluster_metric_charts`. schema: type: string enum: - cpuUsage - quantileOverTimeCpuUsage - cpuThrottling - memoryUsage - networkBytes - diskThroughput - pvcUsage - workbenchHomeDirectoryUsage - requestVolume - requestDuration - successfulRuns - failedRuns - averageDuration - maximumDuration - dcgmGpuUtilization - dcgmGpuMemoryUsed - dcgmGpuTemperature - dcgmGpuPowerUsage - asyncServiceMessagesInProcess - asyncServiceMessagesProcessed - asyncServiceProcessingTime - asyncServiceOutputMessagePublishTime - asyncServiceProcessingFailures - asyncServiceOutputMessagePublishFailures - asyncServiceInputMessageFetchFailuresRate - asyncServiceInputMessageFetchAckFailuresRate - asyncServiceProcessingTimeHistogramMs - asyncServiceInputLatencyNs - asyncServiceKedaScalerMetricValue - kedaScalerMetricValue - rateOfInputTokensPerUser - rateOfEmbeddingInputTokensPerUser - rateOfOutputTokensPerUser - modelInferenceRequestLatency - rateOfModelInferenceRequest - rateOfModelInferenceError - rateOfModelInferenceErrorByPageType - rateOfModelInferenceErrorPercentage - embeddingModelInferenceRequestLatency - costOfInference - modelInferenceRequestPerResponseCode - inputTokensConsumed - outputTokensConsumed - configAffectedRequests - uniqueActiveUsers - timeToFirstToken - interTokenLatency - perOutputTokenLatency - modelUsageByUserOrVirtualAccount - virtualModelUsageByUserOrVirtualAccount - modelErrorDistribution - podStatus - clusterNodes - clusterPods - clusterCpuUsage - clusterMemoryUsage - clusterGpuNodes - clusterGpuCount - clusterGpuMemory - clusterVolumeUsage - clusterNetworkBytes - sparkJobCpuUsageForExecutors - sparkJobMemoryUsageForExecutors - sparkJobCpuUsageForDriver - sparkJobMemoryUsageForDriver - sparkJobNoOfExecutors - rateLimitingConfig - loadBalancingConfig - fallbackConfig - guardrailsConfig - budgetConfig - rateLimitRPS - rateLimitBlocked - loadBalanceRPS - loadBalanceAllModelFailed - loadBalanceModelDistribution - ratelimitRuleIdNominatedVsAppliedDistribution - budgetRuleIdNominatedVsAppliedDistribution - ratelimitBlockedDistributionByCreatedBySubject - budgetBlockedDistributionByCreatedBySubject - budgetRPS - budgetBlocked - containerRestarts - probeFailures - imagePullTime - rateOfRequestsPerMcpServer - latencyPerMcpServer - mcpServerErrors - mcpMethodCallsByMcpServer - requestFailuresByMcpServer - requestFailuresByMcpServerDistribution - rateOfRequestsPerTool - latencyPerTool - toolErrors - requestFailuresByTool - latencySummaryPerTool - requestsPerTool - mcpServerUsageBreakdown - mcpServerErrorBreakdown - rateOfRequestsPerMcpServerPerUser - latencyPerMcpServerPerUser - mcpServerErrorsPerUser - toolUsageBreakdown - toolErrorBreakdown - rateOfRequestsPerToolPerUser - latencyPerToolPerUser - toolErrorsPerUser - requestFailuresPerTool - requestFailuresSummaryPerTool - mcpErrorBreakdown - rateOfRequestsPerGuardrail - requestsPerSecondByResult - latencyPerGuardrail - flaggedRateOfRequestsPerGuardrail - mutatedRateOfRequestsPerGuardrail - inputRequestsBreakdownPerGuardrail - outputRequestsBreakdownPerGuardrail - flagAndMutationResultsBreakdownPerUser - guardrailErrors - latencySummaryPerGuardrail - requestBudgetLimited - topNUsersByUsage - topNVirtualAccountsByUsage - topNModelsByUsage - topNModelProvidersByUsage - topNMcpServersByUsage - topNToolsByUsage - topNUsersByMcp - topNVirtualAccountsByMcp - incomingRequestsByType - guardrailsOverview - errorBreakdown - errorBreakdownDetailed - mcpErrorBreakdownDetailed - meterLlmRequests - meterMcpRequests - meterTotalCost - guardrailResultsBreakdownByPage - guardrailBlockedByGuardrailsByPage - guardrailMutatedByGuardrailsByPage - guardrailUsageByPage - routingRuleTargetModelDistribution - routingDecisionsPerSecond - routingFailureRate - routingRuleUsageRate - rateLimitChecksRate - rateLimitExceededRate - rateLimitResultBreakdown - budgetLimitChecksRate - budgetLimitExceededRate - budgetLimitResultBreakdown - routingRuleUsageRateByUser - routingFailureRateByUser - routingRuleUsageBreakdown - rateLimitChecksRateByUser - rateLimitExceededRateByUser - rateLimitRuleUsageBreakdown - rateLimitRuleExceededBreakdown - rateLimitCheckResultBreakdown - budgetLimitChecksRateByUser - budgetLimitExceededRateByUser - budgetLimitRuleUsageBreakdown - budgetLimitRuleExceededBreakdown - budgetLimitCheckResultBreakdown - cacheEligibleRequests - cacheHitPercentage - cacheCostSavings - cacheErrors - cacheLookupLatency - providerCacheUsagePercentage - requestsPerSecondAgent - requestLatencyAgent - agentFailureRateByErrorType - agentRequestFailureRate - agentRequestFailuresBreakdown - agentUsageBreakdown - agentErrorBreakdown - name: id required: true in: path description: Unique identifier of the cluster. schema: type: string - name: startTs required: true in: query description: Start timestamp in milliseconds from epoch schema: example: '1735201111814' type: number - name: endTs required: true in: query description: End timestamp in milliseconds from epoch schema: example: '1735204711814' type: number - name: utcOffsetSeconds required: true in: query description: Caller UTC offset in seconds. schema: type: number - name: params required: true in: query description: >- JSON-encoded string describing the chart configuration. Call `GET /metrics/cluster/{id}/charts` (tool: `list_cluster_metric_charts`) to get available charts and pass `graphs[*].params` from that response unchanged. schema: type: string responses: '200': description: Returns the metric data for the cluster chart. content: application/json: schema: $ref: '#/components/schemas/ChartDataResponseDto' '404': description: Not Found. Cluster with provided id not found security: - jwt: [] externalDocs: description: Get all Charts for Cluster url: https://your.documentation.link/metrics components: schemas: ChartDataResponseDto: type: object properties: graph: description: Chart data payload. allOf: - $ref: '#/components/schemas/MetricsGraph' stepSize: type: number description: Query step size in seconds. required: - graph - stepSize title: ChartDataResponseDto x-fern-type-name: ChartDataResponseDto MetricsGraph: type: object properties: name: type: string description: Chart identifier (e.g. `cpuUsage`). displayName: type: string description: Human-readable chart name. description: type: string description: What this chart measures. aggregateValue: type: number description: Single aggregate value summarising the chart. aggregateUnit: type: string description: Unit label for `aggregateValue`. example: '% success rate' unit: type: string description: Y-axis unit for plotted values. example: cores graphLines: description: Data series plotted on this chart. type: array items: $ref: '#/components/schemas/MetricsGraphData' queryTypes: description: Series labels available on this chart. type: array items: type: string chartType: type: string enum: - line - vertical_line - stacked_bar - stacked_area - bubble - horizontal_bar - horizontal_stacked_bar - horizontal_box_plot - bar_list description: Chart visualisation type. thresholds: description: Reference thresholds for the series. type: array items: $ref: '#/components/schemas/Threshold' required: - name - graphLines title: MetricsGraph x-fern-type-name: MetricsGraph MetricsGraphData: type: object properties: name: type: string description: Series name. queryType: type: string description: Series identifier from the chart definition. values: type: array items: oneOf: - $ref: '#/components/schemas/MetricValue' - $ref: '#/components/schemas/BarGraphMetricValue' description: Series data points. totalCount: type: number description: Total observation count for this series. aggregateValue: type: object additionalProperties: type: number description: Per-key aggregate values for this series. required: - name - values title: MetricsGraphData x-fern-type-name: MetricsGraphData Threshold: type: object properties: mode: type: string enum: - absolute description: Interpretation mode for `value`. name: type: string description: Threshold name. value: type: number description: Threshold value in the same unit as the chart. required: - mode - name - value title: Threshold x-fern-type-name: Threshold MetricValue: type: object properties: timestamp: type: string format: date-time example: '2026-05-20T12:00:00.000Z' description: Data point timestamp. value: oneOf: - type: number - type: string description: Data point value. required: - timestamp - value title: MetricValue x-fern-type-name: MetricValue BarGraphMetricValue: type: object properties: name: type: string description: Bar label. value: type: number description: Bar value. required: - name - value title: BarGraphMetricValue x-fern-type-name: BarGraphMetricValue securitySchemes: jwt: type: http scheme: bearer bearerFormat: JWT ````