Cast AI Hosted Models API

openapi: 3.2.0
info:
  title: AI Enabler Hosted Models API
  version: 0.0.1
  description: Provides the API for managing hosted model deployment on CAST AI managed clusters.
servers:
- url: https://api.cast.ai/
  description: US endpoint
- url: https://api.eu.cast.ai/
  description: EU endpoint
security:
- BearerAuth: []
- ApiKeyAuth: []
tags:
- name: HostedModelsAPI
  description: Provides the API for managing hosted model deployment on CAST AI managed clusters.
paths:
  /ai-optimizer/v1beta/organizations/{organizationId}/clusters/{clusterId}/hosted-models:
    get:
      tags:
      - HostedModelsAPI
      summary: List hosted models
      description: 'Gets the list of hosted models for given organization.

        Supported sort fields are: model, createTime.

        Max page limit is 1000.'
      operationId: HostedModelsAPI_ListHostedModels
      parameters:
      - name: organizationId
        in: path
        description: The ID of the organization.
        required: true
        schema:
          type: string
      - name: clusterId
        in: path
        description: The ID of the cluster the model is deployed on. Use "-" placeholder to list all models across all clusters.
        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
      - name: sort.field
        in: query
        description: The field name to order by. Nested fields can be specified by using a dot (e.g. user.name).
        schema:
          type: string
      - name: sort.order
        in: query
        description: The order of returned items. Default is ASC.
        schema:
          enum:
          - ASC
          - asc
          - DESC
          - desc
          type: string
          format: enum
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListHostedModelsResponse'
        default:
          description: Default error response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Status'
  /ai-optimizer/v1beta/organizations/{organizationId}/clusters/{clusterId}/hosted-models/{hostedModelId}/pods:
    get:
      tags:
      - HostedModelsAPI
      summary: Get hosted model pod statuses and events
      description: Gets hosted model pod events.
      operationId: HostedModelsAPI_GetHostedModelPods
      parameters:
      - name: organizationId
        in: path
        description: The ID of the Organization.
        required: true
        schema:
          type: string
      - name: clusterId
        in: path
        description: The ID of the Cluster.
        required: true
        schema:
          type: string
      - name: hostedModelId
        in: path
        description: The ID of the hosted model deployment.
        required: true
        schema:
          type: string
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HostedModelPods'
        default:
          description: Default error response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Status'
  /ai-optimizer/v1beta/organizations/{organizationId}/clusters/{clusterId}/hosted-models/{id}:
    delete:
      tags:
      - HostedModelsAPI
      summary: Delete hosted model deployment
      description: Deletes a hosted model deployment.
      operationId: HostedModelsAPI_DeleteHostedModel
      parameters:
      - name: organizationId
        in: path
        description: The ID of the Organization.
        required: true
        schema:
          type: string
      - name: clusterId
        in: path
        description: The ID of the Cluster.
        required: true
        schema:
          type: string
      - name: id
        in: path
        description: The ID of the hosted model deployment.
        required: true
        schema:
          type: string
      responses:
        '200':
          description: OK
          content: {}
        default:
          description: Default error response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Status'
    patch:
      tags:
      - HostedModelsAPI
      summary: Update hosted model
      description: Updates hosted model configuration
      operationId: HostedModelsAPI_UpdateHostedModel
      parameters:
      - name: organizationId
        in: path
        description: The ID of the Organization.
        required: true
        schema:
          type: string
      - name: clusterId
        in: path
        description: The ID of the cluster that hosted model is deployed in
        required: true
        schema:
          type: string
      - name: id
        in: path
        description: The ID of hosted model to be updated.
        required: true
        schema:
          type: string
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/HostedModelUpdate'
        required: true
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HostedModel'
        default:
          description: Default error response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Status'
  /ai-optimizer/v1beta/organizations/{organizationId}/clusters/{clusterId}/hosted-models/{id}:scale:
    post:
      tags:
      - HostedModelsAPI
      summary: Scale the hosted model deployment
      description: Scales the hosted model deployment.
      operationId: HostedModelsAPI_ScaleHostedModel
      parameters:
      - name: organizationId
        in: path
        description: The ID of the Organization.
        required: true
        schema:
          type: string
      - name: clusterId
        in: path
        description: The ID of the Cluster.
        required: true
        schema:
          type: string
      - name: id
        in: path
        description: The ID of the hosted model deployment.
        required: true
        schema:
          type: string
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ScaleHostedModelRequest'
        required: true
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ScaleHostedModelResponse'
        default:
          description: Default error response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Status'
  /ai-optimizer/v1beta/organizations/{organizationId}/clusters/{hosted_model.cluster_id}/hosted-models:
    post:
      tags:
      - HostedModelsAPI
      summary: Create hosted model
      description: Deploys a model on a CAST AI managed cluster.
      operationId: HostedModelsAPI_CreateHostedModel
      parameters:
      - name: organizationId
        in: path
        description: The ID of the Organization.
        required: true
        schema:
          type: string
      - name: hosted_model.cluster_id
        in: path
        required: true
        schema:
          type: string
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/HostedModel'
        required: true
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HostedModel'
        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).'
    Hibernation:
      required:
      - resumeCondition
      - hibernateCondition
      type: object
      properties:
        enabled:
          type: boolean
          description: Whether the automatic hibernation and resumption feature is enabled for the hosted model.
        resumeCondition:
          allOf:
          - $ref: '#/components/schemas/Hibernation_Condition'
          description: The condition that will trigger the resumption of the hosted model.
        hibernateCondition:
          allOf:
          - $ref: '#/components/schemas/Hibernation_Condition'
          description: The condition that will trigger the hibernation of the hosted model.
      description: The settings for automatic hibernation and resumption of the hosted model.
    EdgeLocations:
      type: object
      properties:
        ids:
          type: array
          items:
            type: string
          description: IDs of edge locations.
      description: Edge locations where the model can be deployed
    ScaleHostedModelResponse:
      type: object
      properties:
        replicas:
          readOnly: true
          type: integer
          description: The number of replicas the hosted model deployment was scaled to.
          format: uint32
      description: Response message for scaling the hosted model deployment.
    HostedModel:
      required:
      - clusterId
      - service
      - port
      - modelSpecsId
      type: object
      properties:
        id:
          readOnly: true
          type: string
          description: The ID of the hosted model.
        clusterId:
          type: string
          description: The ID of the Cluster.
        provider:
          readOnly: true
          type: string
          description: Provider of the model (e.g. hugging_face).
        model:
          readOnly: true
          type: string
          description: The name of the model that will be deployed.
        service:
          type: string
          description: Kubernetes service name for the deployed hosted model.
        port:
          type: integer
          description: Port on which the model will be exposed.
          format: int32
        nodeTemplateName:
          type: string
          description: The name of the node template that will be used to deploy the model. If not provided, a new node template will be created.
        status:
          readOnly: true
          enum:
          - STATUS_UNSPECIFIED
          - RUNNING
          - DEPLOYING
          - FAILED
          - STOPPED
          - DELETING
          - SCALING
          - HIBERNATING
          - RESUMING
          - HIBERNATED
          - RESTARTING
          - WARNING
          type: string
          description: Status of the hosted model.
          format: enum
        statusReason:
          readOnly: true
          type: string
          description: A message explaining the reason for the current status.
        createTime:
          readOnly: true
          type: string
          description: The time when the hosted model was created.
          format: date-time
        updateTime:
          readOnly: true
          type: string
          description: The time when the hosted model was last updated.
          format: date-time
        vllmConfig:
          allOf:
          - $ref: '#/components/schemas/VLLMConfig'
          description: Configuration for the vLLM provider.
        region:
          type: string
          description: The region the model is deployed in.
        horizontalAutoscaling:
          allOf:
          - $ref: '#/components/schemas/HorizontalAutoscaling'
          description: The settings for horizontal autoscaling
        fallback:
          allOf:
          - $ref: '#/components/schemas/Fallback'
          description: The fallback model to use when the primary model is not available.
        hibernation:
          allOf:
          - $ref: '#/components/schemas/Hibernation'
          description: The settings for hibernation
        currentReplicas:
          readOnly: true
          type: integer
          description: The current number of replicas in the hosted model deployment
          format: int32
        type:
          readOnly: true
          type: string
          description: The type of the hosted model. Can be "chat", "embeddings", "completion", "audio_transcription", etc.
        helmChartVersion:
          readOnly: true
          type: string
          description: The version of the Helm chart used to deploy the hosted model.
        modelSpecsId:
          type: string
          description: Model specs ID
        organizationId:
          readOnly: true
          type: string
          description: The ID of the organization the hosted model belongs to.
        providerId:
          readOnly: true
          type: string
          description: The ID of the provider of the model.
        cloudProvider:
          readOnly: true
          type: string
          description: Cloud provider on which the model is deployed.
        deployedModel:
          readOnly: true
          type: string
          description: The name of the deployed model.
        namespace:
          readOnly: true
          type: string
          description: Kubernetes namespace where the model is deployed.
        requiredGpuMemoryMib:
          readOnly: true
          type: string
          description: The amount of GPU memory (in MiB) required by the hosted model.
        edgeLocations:
          allOf:
          - $ref: '#/components/schemas/EdgeLocations'
          description: List of edge locations where the model can be deployed.
        includeInCli:
          type: boolean
          description: Whether the auto-created provider for this hosted model should appear in the CLI provider list.
      description: A model that is deployed on a CAST AI managed cluster.
    HorizontalAutoscaling:
      required:
      - minReplicas
      - maxReplicas
      - targetMetric
      - targetValue
      type: object
      properties:
        enabled:
          type: boolean
          description: Whether horizontal autoscaling is enabled for the model.
        minReplicas:
          type: integer
          description: The minimum number of running replicas
          format: int32
        maxReplicas:
          type: integer
          description: The maximum number of running replicas.
          format: int32
        targetMetric:
          enum:
          - AUTOSCALING_METRIC_UNSPECIFIED
          - NUMBER_OF_REQUESTS_WAITING
          - GPU_CACHE_USAGE_PERCENTAGE
          type: string
          description: The metric to observe for scaling decisions.
          format: enum
        targetValue:
          type: number
          description: The target value of observed metric to trigger scale up/down decisions.
          format: float
      description: The settings for horizontal autoscaling.
    PodEvent:
      type: object
      properties:
        message:
          type: string
          description: The message of the event.
        action:
          type: string
          description: The action of the event.
        reason:
          type: string
          description: The reason of the event.
        reportingController:
          type: string
          description: The reporting controller of the event.
        firstTime:
          type: string
          description: The first time the event was seen.
          format: date-time
        lastTime:
          type: string
          description: The last time the event was seen.
          format: date-time
      description: Pod event.
    HostedModelUpdate:
      type: object
      properties:
        nodeTemplateName:
          type: string
          description: The name of the node template that will be used to deploy the model. If not provided, a Cast AI managed node template will be used.
        vllmConfig:
          allOf:
          - $ref: '#/components/schemas/VLLMConfig'
          description: Configuration for the vLLM provider.
        horizontalAutoscaling:
          allOf:
          - $ref: '#/components/schemas/HorizontalAutoscaling'
          description: The settings for horizontal autoscaling
        hibernation:
          allOf:
          - $ref: '#/components/schemas/Hibernation'
          description: The settings for hibernation
        fallback:
          allOf:
          - $ref: '#/components/schemas/Fallback'
          description: The fallback model to use when the primary model is not available.
        edgeLocations:
          allOf:
          - $ref: '#/components/schemas/EdgeLocations'
          description: Edge locations where the model can be deployed.
      description: A request message for updates hosted model fields
    Fallback:
      type: object
      properties:
        providerId:
          type: string
          description: The ID of the provider of the fallback model.
        model:
          type: string
          description: The fallback model to use when the primary model is not available.
        enabled:
          type: boolean
          description: Indicates if the fallback is enabled or not.
      description: The fallback to use when the primary model is not available.
    HostedModelPods:
      required:
      - pods
      type: object
      properties:
        pods:
          type: array
          items:
            $ref: '#/components/schemas/Pod'
          description: The list of pods.
      description: Hosted model pods.
    PodStatus:
      type: object
      properties:
        phase:
          type: string
          description: The phase of the pod.
        reason:
          type: string
          description: The reason of the pod status.
        message:
          type: string
          description: The message of the pod status.
      description: Pod status.
    ListHostedModelsResponse:
      required:
      - items
      - totalCount
      type: object
      properties:
        items:
          type: array
          items:
            $ref: '#/components/schemas/HostedModel'
          description: The list of hosted models.
        nextPageCursor:
          type: string
          description: The pagination cursor to retrieve the next page of hosted models.
        totalCount:
          type: integer
          description: The total number of items.
          format: int32
      description: Response message for listing hosted models.
    VLLMConfig:
      type: object
      properties:
        secretName:
          type: string
          description: The secret name that contains the HuggingFace token.
        huggingFaceToken:
          type: string
          description: The HuggingFace token. If the secret name is provided, this field is ignored.
      description: Configuration specific to the vLLM provider.
    Hibernation_Condition:
      required:
      - duration
      type: object
      properties:
        requestCount:
          type: integer
          description: "Request count that will trigger the automatic hibernation or resumption of the hosted model.\n For resume operation, the number of requests need to exceed this value to resume the model.\n For hibernate operation, the number of requests need to drop below this value to hibernate the model."
          format: uint32
        duration:
          pattern: ^-?(?:0|[1-9][0-9]{0,11})(?:\.[0-9]{1,9})?s$
          type: string
          description: The time period that the request count should be reached in.
      description: The condition that will trigger automatic hosted model status change.
    ScaleHostedModelRequest:
      required:
      - organizationId
      - clusterId
      - id
      - replicas
      type: object
      properties:
        organizationId:
          type: string
          description: The ID of the Organization.
        clusterId:
          type: string
          description: The ID of the Cluster.
        id:
          type: string
          description: The ID of the hosted model deployment.
        replicas:
          type: integer
          description: The number of replicas to scale the hosted model deployment to.
          format: uint32
      description: Request message for scaling the hosted model deployment.
    Pod:
      required:
      - name
      - status
      - events
      type: object
      properties:
        name:
          type: string
          description: The name of the pod.
        status:
          allOf:
          - $ref: '#/components/schemas/PodStatus'
          description: Status of the pod.
        events:
          type: array
          items:
            $ref: '#/components/schemas/PodEvent'
          description: The events of the pod.
      description: Pod.
    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/analyticsapi_generateanalytics.md
  - https://docs.cast.ai/reference/analyticsapi_generatebillingmodelusagereport.md
  - https://docs.cast.ai/reference/analyticsapi_generatebreakdown.md
  - https://docs.cast.ai/reference/analyticsapi_generatelatestchatcompletionsummary.md
  - https://docs.cast.ai/reference/analyticsapi_generatelatestevaluationsummary.md
  - https://docs.cast.ai/reference/analyticsapi_generatelatestinferencesummaries.md
  - https://docs.cast.ai/reference/analyticsapi_generaterouterreport.md
  - https://docs.cast.ai/reference/analyticsapi_queryanalytics.md
  - https://docs.cast.ai/reference/apikeysapi_createapikey.md
  - https://docs.cast.ai/reference/apikeysapi_deleteapikeybudget.md
  - https://docs.cast.ai/reference/apikeysapi_deleteorganizationbudget.md
  - https://docs.cast.ai/reference/apikeysapi_deleteteambudget.md
  - https://docs.cast.ai/reference/apikeysapi_deleteuserbudget.md
  - https://docs.cast.ai/reference/apikeysapi_getapikeybudget.md
  - https://docs.cast.ai/reference/apikeysapi_getbudgetoverview.md
  - https://docs.cast.ai/reference/apikeysapi_getorganizationbudget.md
  - https://docs.cast.ai/reference/apikeysapi_getteambudget.md
  - https://docs.cast.ai/reference/apikeysapi_getuserbudget.md
  - https://docs.cast.ai/reference/apikeysapi_getuserbudgetstatus.md
  - https://docs.cast.ai/reference/apikeysapi_listapikeybudgets.md
  - https://docs.cast.ai/reference/apikeysapi_listorganizationbudgets.md
  - https://docs.cast.ai/reference/apikeysapi_listteambudgets.md
  - https://docs.cast.ai/reference/apikeysapi_listuserbudgets.md
  - https://docs.cast.ai/reference/apikeysapi_updateapikeybudget.md
  - https://docs.cast.ai/reference/apikeysapi_updateorganizationbudget.md
  - https://docs.cast.ai/reference/apikeysapi_updateteambudget.md
  - https://docs.cast.ai/reference/apikeysapi_updateuserbudget.md
  - https://docs.cast.ai/reference/apikeysapi_verifyapikey.md
  - https://docs.cast.ai/reference/apikeysapi_verifyinference.md
  - https://docs.cast.ai/reference/authorizeapi_authorizeaction.md
  - https://docs.cast.ai/reference/batchapi_cancelbatch.md
  - https://docs.cast.ai/reference/batchapi_createbatch.md
  - https://docs.cast.ai/reference/batchapi_getbatch.md
  - https://docs.cast.ai/reference/batchapi_listbatches.md
  - https://docs.cast.ai/reference/batchapi_reportbatcherror.md
  - https://docs.cast.ai/reference/batchapi_updatebatch.md
  - https://docs.cast.ai/reference/componentsapi_listcomponents.md
  - https://docs.cast.ai/reference/couponsapi_listredeemedcoupons.md
  - https://docs.cast.ai/reference/couponsapi_redeemcoupon.md
  - https://docs.cast.ai/reference/couponsapi_validatecoupon.md
  - https://docs.cast.ai/reference/embeddingsapi_createclusterembedding.md
  - https://docs.cast.ai/reference/embeddingsapi_createembedding.md
  - https://docs.cast.ai/reference/evaluationsapi_createclusterevaluation.md
  - https://docs.cast.ai/reference/evaluationsapi_createevaluation.md
  - https://docs.cast.ai/reference/hostedmodeleventsapi_listhostedmodelevents.md
  - https://docs.cast.ai/reference/hostedmodelsapi_createhostedmodel.md
  - https://docs.cast.ai/reference/hostedmodelsapi_deletehostedmodel.md
  - https://docs.cast.ai/reference/hostedmodelsapi_gethostedmodelpods.md
  - https://docs.cast.ai/reference/hostedmodelsapi_listhostedmodels.md
  - https://docs.cast.ai/reference/hostedmodelsapi_scalehostedmodel.md
  - https://docs.cast.ai/reference/hostedmodelsapi_updatehostedmodel.md
  - https://docs.cast.ai/reference/llmrequestsapi_listllmrequests.md
  - https://docs.cast.ai/reference/marketingapi_handlehubspotwebhook.md
  - https://docs.cast.ai/reference/mcpgatewayadminapi_createmcpconnection.md
  - https://docs.cast.ai/reference/mcpgatewayadminapi_deletemcpconnection.md
  - https://docs.cast.ai/reference/mcpgatewayadminapi_getmcpconnection.md
  - https://docs.cast.ai/reference/mcpgatewayadminapi_listmcpconnections.md
  - https://docs.cast.ai/reference/mcpgatewayadminapi_updatemcpconnection.md
  - https://docs.cast.ai/reference/modelaccessapi_getmodelaccesscatalog.md
  - https://docs.cast.ai/reference/modelaccessapi_getorganizationmodelaccess.md
  - https://docs.cast.ai/reference/modelaccessapi_getteammodelaccess.md
  - https://docs.cast.ai/reference/modelaccessapi_listteammodelaccess.md
  - https://docs.cast.ai/reference/modelaccessapi_updateorganizationmodelaccess.md
  - https://docs.cast.ai/reference/modelaccessapi_updateteammodelaccess.md
  - https://docs.cast.ai/reference/modelregistriesapi_createmodelregistry.md
  - https://docs.cast.ai/reference/modelregistriesapi_deletemodelregistry.md
  - https://docs.cast.ai/reference/modelregistriesapi_getmodelregistry.md
  - https://docs.cast.ai/reference/modelregistriesapi_getonboardingcommand.md
  - https://docs.cast.ai/reference/modelregistriesapi_getonboardingscript.md
  - https://docs.cast.ai/reference/modelregistriesapi_listmodelregistries.md
  - https://docs.cast.ai/reference/modelregistriesapi_listmodelregistrydirectories.md
  - https://docs.cast.ai/reference/modelspecsapi_createmodelspecs.md
  - https://docs.cast.ai/reference/modelspecsapi_deletemodelspecs.md
  - https://docs.cast.ai/reference/modelspecsapi_getmodelspecs.md
  - https://docs.cast.ai/reference/modelspecsapi_listmodelspecs.md
  - https://docs.cast.ai/reference/oauthappsapi_completeoauthlogin.md
  - https://docs.cast.ai/reference/oauthappsapi_createoauthapp.md
  - https://docs.cast.ai/reference/oauthappsapi_deleteoauthapp.md
  - https://docs.cast.ai/reference/oauthappsapi_disconnectoauthapp.md
  - https://docs.cast.ai/reference/oauthappsapi_getoauthapp.md
  - https://docs.cast.ai/reference/oauthappsapi_listoauthapps.md
  - https://docs.cast.ai/reference/oauthappsapi_registerdiscoveredoauthapp.md
  - https://docs.cast.ai/reference/oauthappsapi_startoauthlogin.md
  - https://docs.cast.ai/reference/oauthappsapi_updateoauthapp.md
  - https://docs.cast.ai/reference/onboardingapi_checkmodelscache.md
  - https://docs.cast.ai/reference/onboardingapi_getmodelscachescript.md
  - https://docs.cast.ai/reference/onboardingapi_getonboardingcommand.md
  - https://docs.cast.ai/reference/onboardingapi_getonboardingscript.md
  - https://docs.cast.ai/reference/onboardingapi_getonboardingstatus.md
  - https://docs.cast.ai/reference/onboardingapi_getsetupscript.md
  - https://docs.cast.ai/reference/onboardingapi_registermodelscache.md
  - https://docs.cast.ai/reference/otelapi_generateproductivitymetricstimeseries.md
  - https://docs.cast.ai/reference/otelapi_getproductivitymetrics.md
  - https://docs.cast.ai/reference/otelapi_ingestlogs.md
  - https://docs.cast.ai/reference/otelapi_ingestmetrics.md
  - https://docs.cast.ai/reference/playgroundchatcompletionsapi_streamplaygroundchatcompletion.md
  - https://docs.cast.ai/reference/policiesapi_createpolicy.md
  - https://docs.cast.ai/reference/policiesapi_deletepolicy.md
  - https://docs.cast.ai/reference/policiesapi_getpolicy.md
  - https://docs.cast.ai/reference/policiesapi_listpolicies.md
  - https://docs.cast.ai/reference/policiesapi_listpolicyversions.md
  - https://docs.cast.ai/reference/policiesapi_rollbackpolicy.md
  - https://docs.cast.ai/reference/policiesapi_syncpolicies.md
  - https://docs.cast.ai/reference/policiesapi_updatepolicy.md
  - https://docs.cast.ai/reference/prcostsapi_queryprcosts.md
  - https://docs.cast.ai/reference/prcostsapi_reportprcosts.md
  - https://docs.cast.ai/reference/quotaapi_deleteuserquotapolicy.md
  - https://docs.cast.ai/reference/quotaapi_getorgquotapolicy.md
  - https://docs.cast.ai/reference/quotaapi_getquotadefaults.md
  - https://docs.cast.ai/reference/quotaapi_getquotalimits.md
  - https://docs.cast.ai/reference/quotaapi_getquotausage.md
  - https://docs.cast.ai/reference/quotaapi_getuserquotapolicy.md
  - https://docs.cast.ai/reference/quotaapi_updateorgquotapolicy.md
  - https://docs.cast.ai/reference/quotaapi_updateuserquotapolicy.md
  - https://docs.cast.ai/reference/rerankingsapi_createclusterreranking.md
  - https://docs.cast.ai/reference/rerankingsapi_createreranking.md
  - https://docs.cast.ai/reference/secretsapi_createsecret.md
  - https://docs.cast.ai/reference/secretsapi_deletesecret.md
  - https://docs.cast.ai/reference/secretsapi_getsecret.md
  - https://docs.cast.ai/reference/secretsapi_listsecrets.md
  - https://docs.cast.ai/reference/secretsapi_setsecretmappings.md
  - https://docs.cast.ai/reference/secretsapi_updatesecret.md
  - https://docs.cast.ai/reference/sessionsapi_deletesession.md
  - https://docs.cast.ai/reference/sessionsapi_getsession.md
  - https://docs.cast.ai/reference/sessionsapi_listsessions.md
  - https://docs.cast.ai/reference/sessionsapi_resumesession.md
  - https://docs.cast.ai/reference/sessionsapi_suspendsession.md
  - https://docs.cast.ai/reference/sessionsapi_upsertsession.md
  - https://docs.cast.ai/reference/settingsapi_deleteapikeysettings.md
  - https://docs.cast.ai/reference/settingsapi_deleteteamsettings.md
  - https://docs.cast.ai/reference/settingsapi_getapikeysettings.md
  - https://docs.cast.ai/reference/settingsapi_getsettings.md
  - https://docs.cast.ai/reference/settingsapi_getteamsettings.md
  - https://docs.cast.ai/reference/settingsapi_listapikeysettings.md
  - https://docs.cast.ai/reference/settingsapi_listteamsettings.md
  - https://docs.cast.ai/reference/settingsapi_resolvesettings.md
  - https://docs.cast.ai/reference/settingsapi_updatesettings.md
  - https://docs.cast.ai/reference/settingsapi_updateteamsettings.md


# --- truncated at 32 KB (34 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/kimchi/refs/heads/main/openapi/kimchi-hostedmodelsapi-api-openapi.yml