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 NVIDIA NIM 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: NVIDIA NIM
description: 'The NVIDIA NIM API provides endpoints to create and manage workloads that deploy NVIDIA Inference Microservices (NIM) through the NIM Operator. These workloads package optimized NVIDIA model servers and run as managed services on the NVIDIA Run:ai platform.
Each request includes NVIDIA Run:ai scheduling metadata (for example, project, priority, and category) and a NIM service specification that defines the container image, compute resources, environment variables, storage, and networking configuration. Once submitted, NVIDIA Run:ai handles scheduling, orchestration, and lifecycle management of the NIM service to ensure reliable and efficient model serving.
'
paths:
/api/v2/workloads/nim-services:
post:
summary: Create a NVIDIA NIM service. [Experimental]
description: Create a NVIDIA NIM service
operationId: create_nim_service
tags:
- NVIDIA NIM
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/NimServiceCreateRequest'
responses:
'202':
description: Workload creation accepted
content:
application/json:
schema:
$ref: '#/components/schemas/NimServiceResponse'
'400':
$ref: '#/components/responses/400SubmissionErrorV2'
'401':
$ref: '#/components/responses/401Unauthorized'
'403':
$ref: '#/components/responses/403Forbidden'
'409':
$ref: '#/components/responses/409Conflict'
'500':
$ref: '#/components/responses/500InternalServerError'
'503':
$ref: '#/components/responses/503ServiceUnavailable'
/api/v2/workloads/nim-services/{WorkloadV2Id}:
get:
summary: Get a NVIDIA NIM service. [Experimental]
description: Retrieve details of a specific NVIDIA NIM service, by id
operationId: get_nim_service_by_id
tags:
- NVIDIA NIM
parameters:
- $ref: '#/components/parameters/WorkloadV2Id'
responses:
'200':
description: Successfully retrieved the workload
content:
application/json:
schema:
$ref: '#/components/schemas/NimServiceResponse'
'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'
patch:
summary: Update NVIDIA NIM service spec. [Experimental]
operationId: update_nim_service_spec
description: Update the specification of an existing NVIDIA NIM service.
tags:
- NVIDIA NIM
parameters:
- $ref: '#/components/parameters/WorkloadV2Id'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/NimServiceUpdateRequest'
responses:
'202':
description: Workload update request accepted
content:
application/json:
schema:
$ref: '#/components/schemas/NimServiceResponse'
'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:
Category:
description: Specify the workload category assigned to the workload. Categories are used to classify and monitor different types of workloads within the NVIDIA Run:ai platform.
type: string
nullable: true
pattern: .*
Probe:
type: object
properties:
initialDelaySeconds:
description: Number of seconds after the container has started before liveness or readiness probes are initiated.
type: integer
format: int32
minimum: 0
nullable: true
periodSeconds:
description: How often (in seconds) to perform the probe.
type: integer
format: int32
minimum: 1
nullable: true
timeoutSeconds:
description: Number of seconds after which the probe times out.
type: integer
format: int32
minimum: 1
nullable: true
successThreshold:
description: Minimum consecutive successes for the probe to be considered successful after having failed.
type: integer
format: int32
minimum: 1
nullable: true
failureThreshold:
description: When a probe fails, the number of times to try before giving up.
type: integer
format: int32
minimum: 1
nullable: true
handler:
$ref: '#/components/schemas/ProbeHandler'
nullable: true
Labels:
description: Set of labels to populate into the container running the workload.
type: array
items:
$ref: '#/components/schemas/Label'
nullable: true
Error:
required:
- code
- message
properties:
code:
type: integer
minimum: 100
maximum: 599
message:
type: string
details:
type: string
example:
code: 400
message: Bad request - Resource should have a name
DepartmentName1:
type: string
description: The name of the department
example: default
minLength: 1
pattern: ^[a-z0-9]([a-z0-9-]*[a-z0-9])?$
CpuMemoryLimit:
description: Limitations on the CPU memory to allocate for this workload (1G, 20M, .etc). The system guarantees that this workload will not be able to consume more than this amount of memory. The workload will receive an error when trying to allocate more memory than this limit.
type: string
pattern: ^([+]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$
example: 30M
nullable: true
PvcClaimSize:
description: 'Requested size for the PVC. Mandatory when existingPvc is false. Recommended sizes: TB/GB/MB/TIB/GIB/MIB'
type: string
pattern: ^([+]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$
example: 1G
nullable: true
PvcAddedAttrValues:
description: an optional array of key-values pairs that are written as annotations on the created PVC. the allowed attributes are determined according to the storage class configuration (see k8s-objects-tracker for further info).
type: array
items:
$ref: '#/components/schemas/PvcAddedAttrValue'
Toleration:
description: Toleration details.
properties:
name:
description: The name of the toleration.
type: string
minLength: 1
nullable: true
pattern: .*
operator:
$ref: '#/components/schemas/TolerationOperator'
key:
description: The taint key that the toleration applies to. (mandatory)
type: string
nullable: true
pattern: .*
value:
description: The taint value the toleration matches to. Mandatory if operator is Exists, forbidden otherwise.
type: string
nullable: true
pattern: .*
effect:
$ref: '#/components/schemas/TolerationEffect'
seconds:
description: The period of time the toleration tolerates the taint. Valid only if effect is NoExecute. taint.
type: integer
minimum: 1
nullable: true
exclude:
description: Use 'true' in case the label is defined in defaults of the policy, and you wish to exclude it from the workload.
type: boolean
example: false
nullable: true
nullable: true
type: object
ClusterId:
description: The id of the cluster.
type: string
format: uuid
example: 71f69d83-ba66-4822-adf5-55ce55efd210
GpuMemoryRequest:
description: Required if and only if gpuRequestType is memory. States the GPU memory to allocate for the created workload, per GPU device. Note that the workload will not be scheduled unless the system can guarantee this amount of GPU memory to the workload.
type: string
pattern: ^([+]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$
example: 10M
nullable: true
NimServiceUpdateRequest:
type: object
required:
- spec
properties:
spec:
$ref: '#/components/schemas/NimServiceSpec'
NimServicePvcFields:
properties:
existingPvc:
description: Verify existing PVC. PVC is assumed to exist when set to `true`. If set to `false`, the PVC will be created, if it does not exist.
type: boolean
default: false
nullable: true
claimName:
description: Name for the PVC. Allow referencing it across workloads. If not provided, a name based on the workload name and scope will be auto-generated.
type: string
minLength: 1
maxLength: 63
example: my-claim
nullable: true
pattern: .*
readOnly:
description: Permit only read access to PVC.
type: boolean
default: false
nullable: true
claimInfo:
$ref: '#/components/schemas/ClaimInfo'
nullable: true
type: object
ServingPortServiceType:
description: The type of Kubernetes service to create for the inference deployment. Options include 'ClusterIP' (default), 'NodePort', 'LoadBalancer', and 'ExternalName'.
type: string
default: ClusterIP
enum:
- ClusterIP
- NodePort
- LoadBalancer
- ExternalName
nullable: true
EnvironmentVariable:
description: Details of an environment variable which is populated into the container.
properties:
name:
description: The name of the environment variable. (mandatory)
type: string
minLength: 1
example: HOME
nullable: true
pattern: .*
value:
description: The value of the environment variable. (mutually exclusive with secret, userCredential, configMap and podFieldRef)
type: string
example: /home/my-folder
nullable: true
pattern: .*
secret:
$ref: '#/components/schemas/EnvironmentVariableSecret'
configMap:
$ref: '#/components/schemas/EnvironmentVariableConfigMap'
podFieldRef:
$ref: '#/components/schemas/EnvironmentVariablePodFieldReference'
userCredential:
$ref: '#/components/schemas/EnvironmentVariableUserCredential'
exclude:
description: Use 'true' in case the environment variable is defined in defaults of the policy, and you wish to exclude it from the workload.
type: boolean
example: false
nullable: true
description:
description: Description of the environment variable.
type: string
example: Home directory of the user.
nullable: true
pattern: .*
nullable: true
type: object
RunAsGid:
description: The group id to run the entrypoint of the container which executes the workspace. Default to the value specified in the environment asset `runAsGid` field (optional). Use only when the source uid/gid of the environment asset is not `fromTheImage`, and `overrideUidGidInWorkspace` is enabled.
type: integer
format: int64
example: 30
nullable: true
EnvironmentVariableSecret:
description: Details of the secret and key use to populate the environment variable
properties:
name:
description: The name of the secret resource. (mandatory)
type: string
minLength: 1
example: postgress_secret
nullable: true
pattern: ^[a-z0-9]([a-z0-9-]*[a-z0-9])?$
key:
description: The key in the secret resource. (mandatory)
type: string
minLength: 1
example: POSTGRES_PASSWORD
nullable: true
pattern: .*
nullable: true
type: object
WorkloadV2MetadataResponse:
type: object
required:
- name
- projectId
properties:
name:
$ref: '#/components/schemas/WorkloadName'
projectId:
$ref: '#/components/schemas/ProjectId'
priority:
$ref: '#/components/schemas/PriorityClass'
category:
$ref: '#/components/schemas/Category'
preemptibility:
$ref: '#/components/schemas/Preemptibility'
ServingPortExposeExternally:
description: Indicates whether the inference serving endpoint should be accessible outside the cluster. If set to true, the endpoint will be exposed externally. To enable external access, your administrator must configure the cluster as described in the [inference requirements](https://run-ai-docs.nvidia.com/saas/getting-started/installation/system-requirements#inference). section.
type: boolean
nullable: true
default: true
Annotations:
description: Set of annotations to populate into the container running the workload.
type: array
items:
$ref: '#/components/schemas/Annotation'
nullable: true
ProbeHandler:
description: The action taken to determine the health of the container. (mandatory)
type: object
properties:
httpGet:
description: An action based on HTTP Get requests.
type: object
properties:
path:
description: Path to access on the HTTP server, defaults to /.
type: string
pattern: ^(\x2F[a-zA-Z0-9\-_.\x2F]*)?$
example: /
nullable: true
port:
description: Number of the port to access on the container.
type: integer
format: int32
minimum: 1
maximum: 65535
nullable: true
host:
description: Host name to connect to, defaults to the pod IP.
type: string
format: hostname
example: example.com
nullable: true
pattern: .*
scheme:
$ref: '#/components/schemas/ProbeHandlerScheme'
nullable: true
WorkloadId3:
description: A unique ID of the workload.
type: string
format: uuid
TolerationEffect:
description: The taint effect to match. (mandatory)
type: string
enum:
- NoSchedule
- NoExecute
- PreferNoSchedule
- Any
nullable: true
ImagePullPolicy:
description: Image pull policy. Defaults to `Always` if `:latest` tag is specified, otherwise it is `IfNotPresent`.
type: string
minLength: 1
enum:
- Always
- Never
- IfNotPresent
nullable: true
WorkloadName:
description: The name of the workload.
type: string
minLength: 1
example: my-workload-name
pattern: .*
ClaimInfo:
description: Claim information for the newly created PVC. The information should not be provided when attempting to use existing PVC.
properties:
size:
$ref: '#/components/schemas/PvcClaimSize'
storageClass:
description: Storage class name to associate with the PVC. This parameter may be omitted if there is a single storage class in the system, or you are using the default storage class. For more information, see [Storage class](https://kubernetes.io/docs/concepts/storage/storage-classes).
type: string
minLength: 1
example: my-storage-class
nullable: true
pattern: ^[a-z0-9]([a-z0-9-]*[a-z0-9])?$
accessModes:
$ref: '#/components/schemas/PvcAccessModes'
volumeMode:
$ref: '#/components/schemas/PvcVolumeMode'
addedAttrValues:
$ref: '#/components/schemas/PvcAddedAttrValues'
nullable: true
type: object
AutoScalingMinReplicas:
description: The minimum number of replicas for autoscaling. Defaults to 1.
type: integer
format: int32
minimum: 1
nullable: true
AutoScalingMetricNim:
description: The metric to use for autoscaling (mandatory).
type: string
pattern: ^[a-zA-Z_:][a-zA-Z0-9_:]*$
example: http_requests_total
nullable: true
WorkloadV2Metadata:
allOf:
- $ref: '#/components/schemas/WorkloadV2MetadataResponse'
- $ref: '#/components/schemas/WorkloadV2MetadataAutoFill'
EnvironmentVariables:
description: Set of environment variables to populate into the container running the workload.
type: array
items:
$ref: '#/components/schemas/EnvironmentVariable'
nullable: true
CpuCoreRequest:
description: CPU units to allocate for the created workload (0.5, 1, .etc). The workload will receive at least this amount of CPU. Note that the workload will not be scheduled unless the system can guarantee this amount of CPUs to the workload.
format: double
type: number
example: 0.5
nullable: true
minimum: 0
Preemptibility:
description: Specifies whether the workload can be preempted by higher-priority workloads. Valid values are preemptible and non-preemptible. If explicitly set, this value takes precedence. If not set, the system derives the preemptibility from the priorityClassName field, ensuring backward compatibility. Each workload type has a default preemptibility. To view the default preemptibility for each workload type, use the GET /workload-types endpoint.
type: string
minLength: 1
enum:
- preemptible
- non-preemptible
nullable: true
TenantId:
description: The id of the tenant.
type: integer
format: int32
example: 1001
PolicyRuleEnum:
description: Indicates which validation rule (e.g., min, max, step, options, required, canEdit, canAdd) conflicted with policy restrictions, causing the asset or template to be rejected.
type: string
nullable: true
enum:
- min
- max
- step
- options
- required
- canEdit
- canAdd
- locked
ImagePullSecrets:
description: A list of references to Kubernetes secrets in the same namespace used for pulling container images.
type: array
items:
$ref: '#/components/schemas/ImagePullSecret'
nullable: true
Image:
description: Docker image name. For more information, see [Images](https://kubernetes.io/docs/concepts/containers/images). The image name is mandatory for creating a workload.
type: string
minLength: 1
example: python:3.8
nullable: true
pattern: .*
NimServiceResponse:
type: object
required:
- spec
- metadata
- desiredPhase
properties:
metadata:
$ref: '#/components/schemas/WorkloadV2Metadata'
desiredPhase:
$ref: '#/components/schemas/DesiredPhase'
spec:
$ref: '#/components/schemas/NimServiceSpec'
EnvironmentVariableUserCredential:
description: Defines a reference to a user-created credential and a specific key within that credential whose value will populate the environment variable. User credentials can only be accessed by the user who created them.
properties:
name:
description: The name of the user credential. (mandatory)
type: string
minLength: 1
example: my_postgres_user_and_password
nullable: true
key:
description: The key in the user credential resource. (mandatory)
type: string
minLength: 1
example: POSTGRES_PASSWORD
nullable: true
nullable: true
type: object
ServingPortGrpcPort:
description: The GRPC port that the container running the inference service exposes.
type: integer
format: int32
minimum: 1
maximum: 65535
example: 8001
nullable: true
NimServiceWorkers:
description: Specifies the number of worker nodes to use when running the NIM service in multi-node.
type: integer
format: int32
minimum: 1
maximum: 1000
example: 3
nullable: true
Annotation:
description: Annotation details to be populated into the container.
properties:
name:
description: The name of the annotation (mandatory)
type: string
minLength: 1
maxLength: 63
example: billing
nullable: true
pattern: .*
value:
description: The value of the annotation.
type: string
example: my-billing-unit
nullable: true
pattern: .*
exclude:
description: Use 'true' in case the annotation is defined in defaults of the policy, and you wish to exclude it from the workload.
type: boolean
default: false
example: false
nullable: true
nullable: true
type: object
WorkloadV2MetadataAutoFill:
type: object
required:
- id
- gvk
- projectName
- clusterId
- tenantId
- departmentId
- departmentName
- createdAt
- createdBy
- updatedAt
- updatedBy
properties:
id:
$ref: '#/components/schemas/WorkloadId3'
gvk:
$ref: '#/components/schemas/GVK'
projectName:
$ref: '#/components/schemas/ProjectName2'
clusterId:
$ref: '#/components/schemas/ClusterId'
tenantId:
$ref: '#/components/schemas/TenantId'
departmentId:
$ref: '#/components/schemas/DepartmentId3'
departmentName:
$ref: '#/components/schemas/DepartmentName1'
createdAt:
type: string
format: date-time
description: The timestamp for when the workload was created.
example: '2024-01-15T10:30:00Z'
createdBy:
type: string
description: Identifier of the user who created the workload.
format: .*
example: user@run.ai
updatedAt:
type: string
format: date-time
description: The timestamp for the last time the workload was updated.
example: '2024-01-15T10:35:00Z'
updatedBy:
type: string
description: Identifier of the user who last updated the workload.
format: .*
example: user@run.ai
deletedAt:
type: string
format: date-time
description: The timestamp indicating when the workload was deleted.
example: '2024-01-15T10:35:00Z'
nullable: true
deletedBy:
type: string
format: .*
description: Identifier of the user who deleted the workload.
example: user@run.ai
nullable: true
GpuMemoryLimit:
description: Limitation on the memory consumed by the workload, per GPU device. The system guarantees The gpuMemoryLimit must be no less than gpuMemoryRequest.
type: string
pattern: ^([+]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$
example: 10M
nullable: true
EnvironmentVariableConfigMap:
description: Details of the configMap and key use to populate the environment variable
properties:
name:
description: The name of the config-map resource. (mandatory)
type: string
minLength: 1
example: my-config-map
nullable: true
pattern: ^[a-z0-9]([a-z0-9-]*[a-z0-9])?$
key:
description: The key in the config-map resource. (mandatory)
type: string
minLength: 1
example: MY_POSTGRES_SCHEMA
nullable: true
pattern: .*
nullable: true
type: object
DesiredPhase:
description: The desired phase of the workload.
type: string
enum:
- Running
- Stopped
- Deleted
CpuCoreLimit:
description: Limitations on the number of CPUs consumed by the workload (0.5, 1, .etc). The system guarantees that this workload will not be able to consume more than this amount of CPUs.
format: double
type: number
example: 2
nullable: true
minimum: 0
GpuDevicesRequest:
description: Requested number of GPU devices. Currently if more than one device is requested, it is not possible to provide values for gpuMemory or gpuPortion.
type: integer
format: int32
example: 1
nullable: true
minimum: 0
NodePools:
description: A prioritized list of node pools for the scheduler to run the workload on. The scheduler will always try to use the first node pool before moving to the next one if the first is not available.
type: array
items:
type: string
pattern: .*
example:
- my-node-pool-a
- my-node-pool-b
nullable: true
ServingPortExposedUrl:
description: The custom URL to use for the serving port. If empty (default), an autogenerated URL will be used.
type: string
nullable: true
pattern: .*
PvcAddedAttrValue:
type: object
required:
- key
properties:
key:
type: string
minLength: 1
maxLength: 63
pattern: ^([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9]$
example: dnsname
value:
type: string
example: my.dns.com
pattern: .*
EnvironmentVariablePodFieldReference:
description: Details of the field-reference and key use to populate the environment variable
properties:
path:
description: The field path resource. (mandatory)
type: string
minLength: 1
example: metadata.name
nullable: true
pattern: .*
nullable: true
type: object
ProjectName2:
type: string
description: The name of the project
example: project-a
minLength: 1
pattern: ^[a-z0-9]([a-z0-9-]*[a-z0-9])?$
AutoScalingMaxReplicas:
description: The maximum number of replicas for autoscaling. Defaults to minReplicas. Must be no less than minReplicas.
type: integer
format: int32
minimum: 1
nullable: true
GpuRequestType:
description: Sets the unit type for GPU resources requests. Stated in terms of portion or memory. Sets the unit type for other GPU request fields. If `gpuDevicesRequest > 1`, only `portion` is supported. If `gpuDeviceRequest = 1`, the request type can be stated as `portion` or `memory`.
type: string
minLength: 1
enum:
- portion
- memory
nullable: true
NimServiceCreateRequest:
type: object
required:
- metadata
- spec
properties:
metadata:
$ref: '#/components/schemas/NIMServiceMetadataCreateParams'
spec:
$ref: '#/components/schemas/NimServiceSpec'
NimServiceMultiNode:
description: Defines whether the NIM service runs as a multi-node deployment. If workers is set to 1 or more, the service runs in multi-node.
properties:
workers:
$ref: '#/components/schemas/NimServiceWorkers'
nullable: true
type: object
ProbeHandlerScheme:
description: Scheme to use for connecting to the host, defaults to HTTP.
type: string
enum:
- HTTP
- HTTPS
nullable: true
NimServiceReplicas:
default: 1
description: The number of replicas to deploy.
type: integer
format: int32
minimum: 0
maximum: 1000
example: 2
nullable: true
ServingPortMetricsPort:
description: The port where metrics are exposed, required only if it's different than the main port.
type: integer
format: int32
minimum: 1
maximum: 65535
example: 8002
nullable: true
AutoScalingScaleWindowSeconds:
description: The time window for autoscaling decisions, in seconds. Defaults to 300 seconds.
type: integer
format: int32
minimum: 60
maximum: 3600
nullable: true
ComplianceIssuesV2:
properties:
complianceIssues:
type: array
items:
type: object
required:
- details
- field
properties:
field:
type: string
example: compute.gpuDevicesRequest
details:
type: string
example: value must be no less than 3
rule:
$ref: '#/components/schemas/PolicyRuleEnum'
nullable: true
type: object
PriorityClass:
description: 'Specifies the priority class for the workload, which determines its scheduling behavior. Valid values are: very-low, low, medium-low, medium, medium-high, high, and very-high. Each workload type has a default priority. To view the default priority for each workload type, use the GET /workload-types endpoint. Once you change the priority from the default value defined for that workload type, the preemptibility field is not automatically updated. Make sure to set the desired preemptibility value.'
type: string
nullable: true
pattern: .*
ServingPortExposedProtocol:
description: The protocol to use for the exposed URL. If grpcPort is set, this defaults to grpc. Otherwise, it defaults to http.
type: string
enum:
- http
- grpc
nullable: true
SubmissionErrorV2:
allOf:
- $ref: '#/components/schemas/Error'
- $ref: '#/components/schemas/ComplianceIssuesV2'
PvcVolumeMode:
description: Default volume mode for the PVC. Choose between Filesystem (default) or Block.
type: string
enum:
- Filesystem
- Block
nullable: true
Label:
description: Label details to be populated into the container.
properties:
name:
description: The name of the label (mandatory)
type: string
minLength: 1
maxLength: 63
example: stage
nullable: true
pattern: .*
value:
description: The value of the label.
type: string
example: initial-re
# --- truncated at 32 KB (46 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/runai/refs/heads/main/openapi/runai-nvidia-nim-api-openapi.yml