Cast AI Optimization API

openapi: 3.2.0
info:
  title: Reporting Optimization API
  version: 0.0.1
  description: Manages Optimization API.
servers:
- url: https://api.cast.ai/
  description: US endpoint
- url: https://api.eu.cast.ai/
  description: EU endpoint
security:
- BearerAuth: []
- ApiKeyAuth: []
tags:
- name: OptimizationAPI
  description: Manages Optimization API.
paths:
  /reporting/v1beta/organizations/{organizationId}/clusters:runOptimizationsReport:
    post:
      tags:
      - OptimizationAPI
      summary: Returns cluster optimizations report
      description: Returns optimization reports for clusters including utilization metrics and autoscaler suggestions.
      operationId: OptimizationAPI_RunClusterOptimizationsReport
      parameters:
      - name: organizationId
        in: path
        description: ID of the organization.
        required: true
        schema:
          type: string
      - name: page.limit
        in: query
        description: Defines the number of items that should be returned
        schema:
          type: string
      - name: page.cursor
        in: query
        description: "Cursor that defines token indicating where to start the next page.\n Empty value indicates to start from beginning of the dataset."
        schema:
          type: string
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/RunClusterOptimizationsReportRequest_Filter'
        required: true
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/RunClusterOptimizationsReportResponse'
        default:
          description: Default error response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Status'
components:
  schemas:
    Status:
      type: object
      properties:
        code:
          type: integer
          description: The status code, which should be an enum value of [google.rpc.Code][google.rpc.Code].
          format: int32
        message:
          type: string
          description: A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the [google.rpc.Status.details][google.rpc.Status.details] field, or localized by the client.
        details:
          type: array
          items:
            $ref: '#/components/schemas/GoogleProtobufAny'
          description: A list of messages that carry the error details.  There is a common set of message types for APIs to use.
      description: 'The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors).'
    RunClusterOptimizationsReportResponse_ClusterOptimization:
      type: object
      properties:
        clusterId:
          type: string
          description: ID of the cluster.
        efficiency:
          allOf:
          - $ref: '#/components/schemas/RunClusterOptimizationsReportResponse_EfficiencyMetrics'
          description: Cluster current efficiency and utilization metrics.
        cost:
          allOf:
          - $ref: '#/components/schemas/RunClusterOptimizationsReportResponse_CostMetrics'
          description: Cluster current cost metrics.
        infrastructureAutoscaler:
          allOf:
          - $ref: '#/components/schemas/RunClusterOptimizationsReportResponse_OptimizationSuggestions'
          description: Infrastructure autoscaler optimization suggestions.
        workloadAutoscaler:
          allOf:
          - $ref: '#/components/schemas/RunClusterOptimizationsReportResponse_OptimizationSuggestions'
          description: Workload autoscaler optimization suggestions.
      description: Represents optimization report for a single cluster.
    RunClusterOptimizationsReportResponse_CostMetrics:
      type: object
      properties:
        costPerCpuCoreHourly:
          type: number
          description: Hourly cost per 1 CPU core.
          format: double
        costPerMemoryGibHourly:
          type: number
          description: Hourly cost per 1 GiB of memory.
          format: double
        costPerGpuHourly:
          type: number
          description: Hourly cost per 1 GPU.
          format: double
        costPerStorageGibHourly:
          type: number
          description: Hourly cost per 1 GiB of storage.
          format: double
        totalCostMonthly:
          type: number
          description: "Projected monthly total cost. Calculated based on the current state of the cluster\n taking into account the current cluster hourly cost multiplied by amount of hours in month."
          format: double
        cpuCostMonthly:
          type: number
          description: "Projected CPU monthly cost. Calculated based on the current state of the cluster\n taking into account the current cluster hourly cost multiplied by amount of hours in month."
          format: double
        memoryCostMonthly:
          type: number
          description: "Projected memory monthly cost. Calculated based on the current state of the cluster\n taking into account the current cluster hourly cost multiplied by amount of hours in month."
          format: double
        gpuCostMonthly:
          type: number
          description: "Projected GPU monthly cost. Calculated based on the current state of the cluster\n taking into account the current cluster hourly cost multiplied by amount of hours in month."
          format: double
        storageCostMonthly:
          type: number
          description: "Projected storage monthly cost. Calculated based on the current state of the cluster\n taking into account the current cluster hourly cost multiplied by amount of hours in month."
          format: double
      description: Cost-related metrics.
    RunClusterOptimizationsReportResponse_OptimizationSuggestions:
      type: object
      properties:
        enabled:
          type: boolean
          description: Indicates if the autoscaler is enabled.
        cpuSavingsMonthly:
          type: number
          description: Potential monthly savings from CPU optimization.
          format: double
        memorySavingsMonthly:
          type: number
          description: Potential monthly savings from memory optimization.
          format: double
        downscaleCpuCores:
          type: number
          description: Suggested CPU cores to downscale.
          format: double
        downscaleMemoryBytes:
          type: number
          description: Suggested memory bytes to downscale.
          format: double
        optimalCostPerCpuCoreHourly:
          type: number
          description: Optimal hourly cost per 1 CPU core.
          format: double
        optimalCostPerMemoryGibHourly:
          type: number
          description: Optimal hourly cost per 1 GiB of memory.
          format: double
        issueCount:
          type: integer
          description: Number of detected issues.
          format: int32
      description: Optimization suggestions from autoscalers.
    RunClusterOptimizationsReportResponse_EfficiencyMetrics:
      type: object
      properties:
        provisionedCpuCores:
          type: number
          description: CPU provisioned cores.
          format: double
        requestedCpuCores:
          type: number
          description: CPU requested cores.
          format: double
        usedCpuCores:
          type: number
          description: CPU used cores.
          format: double
        provisionedMemoryBytes:
          type: number
          description: Memory provisioned bytes.
          format: double
        requestedMemoryBytes:
          type: number
          description: Memory requested bytes.
          format: double
        usedMemoryBytes:
          type: number
          description: Memory used bytes.
          format: double
        provisionedGpu:
          type: number
          description: GPU provisioned.
          format: double
        requestedGpu:
          type: number
          description: GPU requested.
          format: double
        provisionedStorageBytes:
          type: number
          description: Storage provisioned bytes.
          format: double
        requestedStorageBytes:
          type: number
          description: Storage requested bytes.
          format: double
        cpuOverprovisionPercent:
          type: number
          description: CPU overprovisioning percentage. Represents the proportion of CPU requested to actually provisioned, expressed as a percentage (0–100).
          format: double
        memoryOverprovisionPercent:
          type: number
          description: Memory overprovisioning percentage. Represents the proportion of Memory requested to actually provisioned, expressed as a percentage (0–100).
          format: double
        gpuOverprovisionPercent:
          type: number
          description: GPU overprovisioning percentage. Represents the proportion of GPU requested to actually provisioned, expressed as a percentage (0–100).
          format: double
        storageOverprovisionPercent:
          type: number
          description: Storage overprovisioning percentage. Represents the proportion of Storage requested to actually provisioned, expressed as a percentage (0–100).
          format: double
        score:
          type: number
          description: Efficiency score. The higher the score, the more efficient the cluster is.
          format: double
      description: Efficiency and utilization metrics.
    RunClusterOptimizationsReportResponse:
      type: object
      properties:
        items:
          type: array
          items:
            $ref: '#/components/schemas/RunClusterOptimizationsReportResponse_ClusterOptimization'
          description: List of cluster optimization reports.
        nextPageCursor:
          type: string
          description: The pagination cursor to retrieve the next page of items.
      description: Response containing cluster optimization reports.
    RunClusterOptimizationsReportRequest_Filter:
      type: object
      properties:
        clusterIds:
          type: array
          items:
            type: string
          description: "Optional list of cluster IDs.\n If specified, only data for selected clusters will be displayed."
      description: Request filter.
    GoogleProtobufAny:
      type: object
      properties:
        '@type':
          type: string
          description: The type of the serialized message.
      additionalProperties: true
      description: Contains an arbitrary serialized message along with a @type that describes the type of the serialized message.
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-Key
x-provenance:
  method: searched
  source: https://docs.cast.ai/reference
  harvested: '2026-10-20'
  tool: harvest-readme-openapi.py
  note: Assembled verbatim from the OpenAPI definition ReadMe embeds in each operation page of the provider's developer portal; paths and components merged by API title, nothing authored.
  assembled_from:
  - https://docs.cast.ai/reference/budgetsapi_createbudget.md
  - https://docs.cast.ai/reference/budgetsapi_deletebudget.md
  - https://docs.cast.ai/reference/budgetsapi_getbudget.md
  - https://docs.cast.ai/reference/budgetsapi_listbudgets.md
  - https://docs.cast.ai/reference/budgetsapi_previewbudgetcost.md
  - https://docs.cast.ai/reference/budgetsapi_updatebudget.md
  - https://docs.cast.ai/reference/clusterscoreapi_getclusterrestrictiondetails.md
  - https://docs.cast.ai/reference/clusterscoreapi_listclusterrestrictions.md
  - https://docs.cast.ai/reference/containerlivemigrationapi_getcontainerlivemigrationdetail.md
  - https://docs.cast.ai/reference/containerlivemigrationapi_getcontainerlivemigrationsummary.md
  - https://docs.cast.ai/reference/containerlivemigrationapi_listcontainerlivemigrationevents.md
  - https://docs.cast.ai/reference/containerlivemigrationapi_listcontainerlivemigrationfiltervalues.md
  - https://docs.cast.ai/reference/containerlivemigrationapi_listcontainerlivemigrationincompatibleworkloads.md
  - https://docs.cast.ai/reference/containerlivemigrationapi_listcontainerlivemigrations.md
  - https://docs.cast.ai/reference/containerlivemigrationapi_listcontainerlivemigrationworkloads.md
  - https://docs.cast.ai/reference/instanceapi_getinstancessummary.md
  - https://docs.cast.ai/reference/instanceapi_listinstances.md
  - https://docs.cast.ai/reference/nodeconditioneventsapi_listnodeconditionevents.md
  - https://docs.cast.ai/reference/nodetemplateapi_getspotinterruptionpredictionperformancesummary.md
  - https://docs.cast.ai/reference/nodetemplateapi_listnodetemplatesmetrics.md
  - https://docs.cast.ai/reference/nodetemplateapi_listnodetemplatesmetricsfiltered.md
  - https://docs.cast.ai/reference/nodetemplateapi_listspotinterruptionpredictionperformancemetrics.md
  - https://docs.cast.ai/reference/optimizationapi_runclusteroptimizationsreport.md
  - https://docs.cast.ai/reference/reliabilitymetricsapi_getclusterreliabilitymetrics.md
  - https://docs.cast.ai/reference/reliabilitymetricsapi_getorganizationclustersreliabilitymetrics.md
  - https://docs.cast.ai/reference/valuerealizationapi_getbaselineparams.md
  - https://docs.cast.ai/reference/valuerealizationapi_recalculatebaselineparams.md
  - https://docs.cast.ai/reference/valuerealizationapi_runclustersvaluerealizationreport.md
  - https://docs.cast.ai/reference/valuerealizationapi_runvaluerealizationtimelinereport.md
  - https://docs.cast.ai/reference/valuerealizationapi_runworkloadsvaluerealizationreport.md
  - https://docs.cast.ai/reference/valuerealizationapi_updatebaselineparams.md
  merge:
    pages: 31
    deduped: 179
    conflicts_kept_first: 0