NVIDIA Run:ai Nodes API

openapi: 3.0.3
info:
  version: latest
  description: '# Introduction


    The NVIDIA Run:ai Control-Plane API reference is a guide that provides an easy-to-use programming interface for adding various tasks to your application, including workload submission, resource management, and administrative operations.


    NVIDIA Run:ai APIs are accessed using *bearer tokens*. To obtain a token, you need to create a **Service account** through the NVIDIA Run:ai user interface.

    To create a service account, in your UI, go to Access → Service Accounts (for organization-level service accounts) or User settings → Access Keys (for user access keys), and create a new one.


    After you have created a new service account, you will need to assign it access rules.

    To assign access rules to the service account, see [Create access rules](https://run-ai-docs.nvidia.com/saas/infrastructure-setup/authentication/accessrules#create-or-delete-rules).

    Make sure you assign the correct rules to your service account. Use the [Roles](https://run-ai-docs.nvidia.com/saas/infrastructure-setup/authentication/roles) to assign the correct access rules.


    To get your access token, follow the instructions in [Request a token](https://run-ai-docs.nvidia.com/saas/reference/api/rest-auth/#request-an-api-token).

    '
  title: NVIDIA Run:ai Access Keys Nodes API
  x-logo:
    url: https://api.redocly.com/registry/raw/runai-xq8/saas/latest/public/runai-logo-api.png
    altText: NVIDIA Run:ai
    href: https://run.ai
  license:
    name: NVIDIA Run:ai
    url: https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-software-license-agreement/
servers:
- url: https://app.run.ai
security:
- bearerAuth: []
tags:
- name: Nodes
  description: "Nodes are worker machines in Kubernetes and may be either a virtual or a physical machine, depending on the cluster. \nEach Node is managed by the NVIDIA Run:ai control plane. For more information, see [Nodes](https://run-ai-docs.nvidia.com/saas/platform-management/aiinitiatives/resources/nodes).\n"
paths:
  /api/v1/clusters/{clusterUuid}/nodes:
    get:
      summary: Get a list of nodes.
      description: Retrieve a list of nodes from the Kubernetes cluster. Deprecated - use `/api/v1/nodes` instead.
      operationId: get_nodes
      deprecated: true
      tags:
      - Nodes
      parameters:
      - $ref: '#/components/parameters/ClusterUuid'
      - $ref: '#/components/parameters/QueryNodeName'
      - $ref: '#/components/parameters/NodesFilter'
      - $ref: '#/components/parameters/NodesSortBy'
      - $ref: '#/components/parameters/SortOrder'
      - $ref: '#/components/parameters/Offset'
      - $ref: '#/components/parameters/Limit'
      - $ref: '#/components/parameters/Search'
      responses:
        '200':
          description: Executed successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Nodes'
        '401':
          $ref: '#/components/responses/401Unauthorized'
        '403':
          $ref: '#/components/responses/403Forbidden'
        '404':
          $ref: '#/components/responses/404NotFound'
        '500':
          $ref: '#/components/responses/500InternalServerError'
        '503':
          $ref: '#/components/responses/503ServiceUnavailable'
  /api/v1/clusters/{clusterUuid}/nodes/count:
    get:
      summary: Count nodes
      operationId: count_nodes
      description: Count nodes
      tags:
      - Nodes
      parameters:
      - $ref: '#/components/parameters/ClusterUuid'
      - $ref: '#/components/parameters/NodesFilter'
      - $ref: '#/components/parameters/Search'
      responses:
        '200':
          description: ok
          content:
            application/json:
              schema:
                type: object
                properties:
                  count:
                    type: integer
                    format: int64
                required:
                - count
        '400':
          $ref: '#/components/responses/400BadRequest'
        '401':
          $ref: '#/components/responses/401Unauthorized'
        '403':
          $ref: '#/components/responses/403Forbidden'
        '500':
          $ref: '#/components/responses/500InternalServerError'
        '503':
          $ref: '#/components/responses/503ServiceUnavailable'
  /api/v1/nodes:
    get:
      summary: Get a list of nodes.
      description: Retrieve a list of nodes from all the Kubernetes clusters of the tenant.
      operationId: get_tenant_nodes
      tags:
      - Nodes
      parameters:
      - $ref: '#/components/parameters/NodesFilter'
      - $ref: '#/components/parameters/NodesSortBy'
      - $ref: '#/components/parameters/SortOrder'
      - $ref: '#/components/parameters/Offset'
      - $ref: '#/components/parameters/Limit'
      - $ref: '#/components/parameters/Search'
      responses:
        '200':
          description: Executed successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Nodes'
        '401':
          $ref: '#/components/responses/401Unauthorized'
        '403':
          $ref: '#/components/responses/403Forbidden'
        '404':
          $ref: '#/components/responses/404NotFound'
        '500':
          $ref: '#/components/responses/500InternalServerError'
        '503':
          $ref: '#/components/responses/503ServiceUnavailable'
  /api/v1/nodes/count:
    get:
      summary: Count tenant nodes
      operationId: count_tenant_nodes
      description: Count nodes from all the Kubernetes clusters of the tenant.
      tags:
      - Nodes
      parameters:
      - $ref: '#/components/parameters/NodesFilter'
      - $ref: '#/components/parameters/Search'
      responses:
        '200':
          description: ok
          content:
            application/json:
              schema:
                type: object
                properties:
                  count:
                    type: integer
                    format: int64
                required:
                - count
        '400':
          $ref: '#/components/responses/400BadRequest'
        '401':
          $ref: '#/components/responses/401Unauthorized'
        '403':
          $ref: '#/components/responses/403Forbidden'
        '500':
          $ref: '#/components/responses/500InternalServerError'
        '503':
          $ref: '#/components/responses/503ServiceUnavailable'
  /api/v1/nodes/telemetry:
    get:
      summary: Get node telemetry data.
      description: Retrieve node telemetry data for use in analysis applications.
      operationId: get_node_telemetry
      tags:
      - Nodes
      parameters:
      - $ref: '#/components/parameters/FilterByCluster'
      - $ref: '#/components/parameters/FilterByNodepoolName'
      - $ref: '#/components/parameters/TelemetryGroupBy'
      - $ref: '#/components/parameters/TelemetryType'
      responses:
        '200':
          description: Executed successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TelemetryResponse'
            text/csv: {}
        '400':
          $ref: '#/components/responses/400BadRequest'
        '401':
          $ref: '#/components/responses/401Unauthorized'
        '403':
          $ref: '#/components/responses/403Forbidden'
        '404':
          $ref: '#/components/responses/404NotFound'
        '500':
          $ref: '#/components/responses/500InternalServerError'
        '503':
          $ref: '#/components/responses/503ServiceUnavailable'
  /api/v1/nodes/{nodeId}/metrics:
    get:
      summary: Get the node metrics data.
      description: Retrieve the node metrics data by Universally Unique Identifier (UUID).
      operationId: get_node_metrics
      tags:
      - Nodes
      parameters:
      - $ref: '#/components/parameters/NodeId'
      - $ref: '#/components/parameters/NodeMetricTypes'
      - $ref: '#/components/parameters/StartRequired'
      - $ref: '#/components/parameters/EndRequired'
      - $ref: '#/components/parameters/NumberOfSamples'
      responses:
        '200':
          description: Executed successfully.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/MetricsResponse'
            text/csv: {}
        '207':
          description: Partial success.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/MetricsResponse'
        '400':
          $ref: '#/components/responses/400BadRequest'
        '401':
          $ref: '#/components/responses/401Unauthorized'
        '403':
          $ref: '#/components/responses/403Forbidden'
        '404':
          $ref: '#/components/responses/404NotFound'
        '500':
          $ref: '#/components/responses/500InternalServerError'
        '503':
          $ref: '#/components/responses/503ServiceUnavailable'
components:
  schemas:
    NodeTaint:
      type: object
      required:
      - key
      - effect
      properties:
        key:
          type: string
          description: The taint key to be applied to a node.
          example: foo
        value:
          type: string
          description: The taint value corresponding to the taint key.
          example: bar
        effect:
          type: string
          description: The effect of the taint on pods that do not tolerate the taint.
          enum:
          - NoSchedule
          - PreferNoSchedule
          - NoExecute
      x-schema-name: NodeTaint
    NodeAdditionalFields:
      type: object
      required:
      - name
      properties:
        name:
          type: string
          description: The name of the node
          example: worker-node-1
      x-schema-name: NodeAdditionalFields
    NodeAdditionalReadFields:
      type: object
      required:
      - clusterUuid
      - updatedAt
      properties:
        id:
          type: string
          format: uuid
          description: The unique identifier of the node.
        clusterUuid:
          $ref: '#/components/schemas/ClusterId'
        updatedAt:
          type: string
          format: date-time
      x-schema-name: NodeAdditionalReadFields
    NodeInfo:
      type: object
      required:
      - status
      - nodePool
      - createdAt
      properties:
        status:
          type: string
          enum:
          - Ready
          - NotReady
          - Unknown
          description: The calculated status of the node.
        conditions:
          type: array
          items:
            $ref: '#/components/schemas/NodeStatusConditionDetails'
        taints:
          type: array
          items:
            $ref: '#/components/schemas/NodeTaint'
        nodePool:
          type: string
          description: The node's NodePool.
          example: node-pool-1
        createdAt:
          type: string
          format: date-time
        gpuInfo:
          $ref: '#/components/schemas/GpuInfo'
        nvLinkDomainUid:
          type: string
          description: NV Link Domain Uid
          example: nvlink-domain-uid
          nullable: true
        nvLinkCliqueId:
          type: string
          description: NV Link Clique Id
          example: clique-id
          nullable: true
      x-schema-name: NodeInfo
    Error:
      required:
      - code
      - message
      properties:
        code:
          type: integer
          minimum: 100
          maximum: 599
        message:
          type: string
        details:
          type: string
      example:
        code: 400
        message: Bad request - Resource should have a name
    MetricsResponse:
      type: object
      required:
      - measurements
      properties:
        measurements:
          type: array
          items:
            $ref: '#/components/schemas/MeasurementResponse'
    GpuInfo:
      type: object
      nullable: true
      required:
      - gpuType
      - gpuCount
      properties:
        gpuType:
          type: string
          example: Tesla-V100
        gpuCount:
          type: integer
      x-schema-name: GpuInfo
    TelemetryResponse:
      type: object
      required:
      - type
      - timestamp
      - values
      properties:
        type:
          type: string
          description: specifies what data returned
          example: ALLOCATION_RATIO
        timestamp:
          type: string
          format: date-time
          example: '2023-06-06 12:09:18.211'
        values:
          type: array
          items:
            type: object
            required:
            - value
            properties:
              value:
                type: string
                example: '85'
              groups:
                type: array
                description: columns the data is grouped by
                maxItems: 2
                items:
                  type: object
                  required:
                  - key
                  - value
                  properties:
                    key:
                      type: string
                      example: department
                    value:
                      type: string
                      example: '1'
                    name:
                      type: string
                      example: department-A
    ClusterId:
      description: The id of the cluster.
      type: string
      format: uuid
      example: 71f69d83-ba66-4822-adf5-55ce55efd210
    NodeTelemetryType:
      type: string
      enum:
      - READY_GPU_NODES
      - READY_GPUS
      - TOTAL_GPU_NODES
      - TOTAL_GPUS
      - IDLE_ALLOCATED_GPUS
      - FREE_GPUS
      - ALLOCATED_GPUS
      - TOTAL_CPU_CORES
      - USED_CPU_CORES
      - ALLOCATED_CPU_CORES
      - TOTAL_GPU_MEMORY_BYTES
      - USED_GPU_MEMORY_BYTES
      - TOTAL_CPU_MEMORY_BYTES
      - USED_CPU_MEMORY_BYTES
      - ALLOCATED_CPU_MEMORY_BYTES
      - FULLY_FREE_GPU_NODES
    NodeStatusConditionDetails:
      type: object
      required:
      - type
      - reason
      properties:
        type:
          type: string
          description: Type of node condition.
        reason:
          type: string
          description: (brief) reason for the condition's last transition.
          example: KubeletNotReady
        message:
          type: string
          description: Human readable message indicating details about last transition.
          example: container runtime status check may not have completed yet
      x-schema-name: NodeStatusConditionDetails
    Nodes:
      type: object
      required:
      - nodes
      properties:
        nodes:
          type: array
          items:
            $ref: '#/components/schemas/Node'
      x-schema-name: Nodes
    MeasurementResponse:
      type: object
      required:
      - type
      - values
      properties:
        type:
          type: string
          description: specifies what data returned
          example: ALLOCATED_GPU
        labels:
          type: object
          nullable: true
          description: labels of the metric measurement
          example: '{''gpu'': ''3''}'
          additionalProperties:
            type: string
        values:
          type: array
          nullable: true
          items:
            type: object
            required:
            - value
            - timestamp
            properties:
              value:
                type: string
                example: '85'
              timestamp:
                type: string
                format: date-time
                nullable: true
                example: '2023-06-06 12:09:18.211'
    NodeFilterSortFields:
      type: string
      enum:
      - name
      - status
      - nodePool
      - gpuType
      - nvLinkDomainUid
      - nvLinkCliqueId
      - clusterUuid
    NodeMetricType:
      type: string
      description: Specify which metric data to request.
      enum:
      - GPU_UTILIZATION_PER_GPU
      - GPU_UTILIZATION
      - GPU_MEMORY_UTILIZATION_PER_GPU
      - GPU_MEMORY_UTILIZATION
      - GPU_MEMORY_USAGE_BYTES_PER_GPU
      - GPU_MEMORY_USAGE_BYTES
      - GPU_ALLOCATION_PER_GPU
      - GPU_MEMORY_ALLOCATION_BYTES_PER_GPU
      - GPU_IDLE_TIME_SECONDS_PER_GPU
      - CPU_USAGE_CORES
      - CPU_UTILIZATION
      - CPU_MEMORY_USAGE_BYTES
      - CPU_MEMORY_UTILIZATION
      - GPU_OOMKILL_BURST_COUNT_PER_GPU
      - GPU_OOMKILL_IDLE_COUNT_PER_GPU
      - GPU_OOMKILL_SWAP_OUT_OF_RAM_COUNT_PER_GPU
      - GPU_GRAPHICS_ENGINE_ACTIVITY_PER_GPU
      - GPU_SM_ACTIVITY_PER_GPU
      - GPU_SM_OCCUPANCY_PER_GPU
      - GPU_TENSOR_ACTIVITY_PER_GPU
      - GPU_FP64_ENGINE_ACTIVITY_PER_GPU
      - GPU_FP32_ENGINE_ACTIVITY_PER_GPU
      - GPU_FP16_ENGINE_ACTIVITY_PER_GPU
      - GPU_MEMORY_BANDWIDTH_UTILIZATION_PER_GPU
      - GPU_NVLINK_TRANSMITTED_BANDWIDTH_PER_GPU
      - GPU_NVLINK_RECEIVED_BANDWIDTH_PER_GPU
      - GPU_PCIE_TRANSMITTED_BANDWIDTH_PER_GPU
      - GPU_PCIE_RECEIVED_BANDWIDTH_PER_GPU
      - NVLINK_BANDWIDTH_TOTAL
      - NVLINK_BANDWIDTH_TOTAL_PER_GPU
    Node:
      allOf:
      - $ref: '#/components/schemas/NodeInfo'
      - $ref: '#/components/schemas/NodeAdditionalFields'
      - $ref: '#/components/schemas/NodeAdditionalReadFields'
      x-schema-name: Node
  parameters:
    FilterByNodepoolName:
      name: nodepoolName
      in: query
      description: Filter using the nodepool.
      required: false
      schema:
        type: string
        example: default
    StartRequired:
      name: start
      in: query
      description: Start date of time range to fetch data in ISO 8601 timestamp format.
      required: true
      schema:
        type: string
        format: date-time
        example: '2023-06-06T12:09:18.211Z'
    FilterByCluster:
      name: clusterId
      in: query
      description: Filter using the Universally Unique Identifier (UUID) of the cluster.
      required: false
      schema:
        type: string
        format: uuid
        example: d73a738f-fab3-430a-8fa3-5241493d7128
    EndRequired:
      name: end
      in: query
      description: End date of time range to fetch data in ISO 8601 timestamp format.
      required: true
      schema:
        type: string
        format: date-time
        example: '2023-06-07T12:09:18.211Z'
    TelemetryType:
      name: telemetryType
      in: query
      required: true
      description: specifies what data to request
      schema:
        $ref: '#/components/schemas/NodeTelemetryType'
    Search:
      name: search
      in: query
      required: false
      description: Filter results by a free text search.
      schema:
        type: string
        example: test project
    QueryNodeName:
      name: nodeName
      in: query
      description: Deprecated - use filterBy instead. The node name; Cannot be used together with filterBy, sort, offset, limit or search query params.
      schema:
        type: string
      required: false
    NodeId:
      name: nodeId
      in: path
      description: The node UUID.
      schema:
        type: string
        format: uuid
        minLength: 1
        example: 9f55255e-11ed-47c7-acef-fc4054768dbc
      required: true
    NodesFilter:
      name: filterBy
      in: query
      required: false
      description: Filter results by a parameter. Use the format field-name operator value. Operators are == Equals, != Not equals, <= Less than or equal, >= Greater than or equal, =@ contains, !@ Does not contains, =^ Starts with and =$ Ends with. Dates are in ISO 8601 timestamp format and available for operators ==, !=, <= and >=.
      schema:
        type: array
        items:
          type: string
          pattern: ^(name|status|nodePool|gpuType|nvLinkDomainUid|nvLinkCliqueId|clusterUuid)(==|!=|<=|>=|=@|!@|=\^|=\$).+$
        example:
        - name!=some-name
      explode: false
    NodeMetricTypes:
      name: metricType
      in: query
      required: true
      description: Specify which data to request.
      explode: false
      schema:
        type: array
        items:
          $ref: '#/components/schemas/NodeMetricType'
    SortOrder:
      name: sortOrder
      in: query
      required: false
      description: Sort results in descending or ascending order.
      schema:
        type: string
        enum:
        - asc
        - desc
        default: asc
    NumberOfSamples:
      name: numberOfSamples
      in: query
      description: The number of samples to take in the specified time range.
      required: false
      schema:
        type: integer
        example: 20
        maximum: 1000
        minimum: 0
        default: 20
    ClusterUuid:
      name: clusterUuid
      in: path
      required: true
      description: The Universally Unique Identifier (UUID) of the cluster.
      schema:
        type: string
        format: uuid
        minLength: 1
        example: 9f55255e-11ed-47c7-acef-fc4054768dbc
    TelemetryGroupBy:
      name: groupBy
      in: query
      description: workload fields to group the data by
      explode: false
      required: false
      schema:
        type: array
        maxItems: 2
        items:
          type: string
          enum:
          - ClusterId
          - Nodepool
          - Node
    NodesSortBy:
      name: sortBy
      in: query
      required: false
      description: Sort results by a parameters.
      schema:
        $ref: '#/components/schemas/NodeFilterSortFields'
    Limit:
      name: limit
      in: query
      required: false
      description: The maximum number of entries to return.
      schema:
        type: integer
        format: int32
        default: 50
        minimum: 1
        maximum: 500
    Offset:
      name: offset
      in: query
      required: false
      description: The offset of the first item returned in the collection.
      schema:
        type: integer
        format: int32
        example: 100
  responses:
    404NotFound:
      description: The specified resource was not found
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 404
            message: Resource id not found.
    500InternalServerError:
      description: unexpected error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 500
            message: Something went wrong.
    403Forbidden:
      description: Forbidden
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 403
            message: You do not have sufficient permissions.
    503ServiceUnavailable:
      description: unexpected error
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 503
            message: Please try again in few minutes.
    401Unauthorized:
      description: Unauthorized
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 401
            message: Issuer is not familiar.
    400BadRequest:
      description: Bad request.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/Error'
          example:
            code: 400
            message: Required parameter is missing
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: JWT
      description: Bearer authentication
x-tagGroups:
- name: Organizations
  tags:
  - Clusters
  - Departments
  - Reports
  - NodePools
  - Nodes
  - Projects
  - Tenant
  - Logo
  - Researcher Command Line Interface
  - Researcher Command Line Interface Deprecated
  - Administrator Command Line Interface
  - Network Topologies
- name: Authentication and Authorization
  tags:
  - Access Keys
  - Access rules
  - Permissions
  - Applications
  - Service Accounts
  - Roles
  - Tokens
  - Users
  - User Applications
  - Idps
  - Me
  - Settings
  - Org unit
- name: Audit
  tags:
  - AuditLogs
- name: Datavolumes
  tags:
  - Datavolumes
- name: Workloads
  tags:
  - Events
  - Pods
  - Workloads
  - Workloads V2
  - NVIDIA NIM
  - Workspaces
  - Trainings
  - Inferences
  - Revisions
  - Distributed
  - Workloads batch
  - Workload properties
  - Workload templates
  - Distributed Inferences
- name: Workload assets
  tags:
  - Compute
  - Credentials
  - Datasources
  - Environment
  - Storage Classes
  - Storage Class Configuration
  - Git
  - HostPath
  - NFS
  - PVC
  - Registry
  - S3
  - ConfigMap
  - Secret
  - Template
- name: Policies
  tags:
  - Policy
- name: Notifications
  tags:
  - Notification State
  - Notification Types
  - NotificationChannels
  - Subscriptions
- name: AI Applications
  tags:
  - AI Applications