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 Distributed Inferences 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: Distributed Inferences
description: "Distributed inference enables running inference workloads across multiple pods, typically to scale model serving beyond a single container or node. This approach is useful when a single instance cannot meet resource requirements.NVIDIA Run:ai supports this model using Leader Worker Set (LWS). \nEach pod plays a specific role, either as a leader or worker, and together they form a coordinated service. NVIDIA Run:ai manages the orchestration and configuration of these pods to ensure efficient and scalable inference execution\n"
paths:
/api/v1/workloads/distributed-inferences:
post:
summary: Create a distributed inference. [Experimental]
operationId: create_distributed_inference
description: Create a distributed inference using container related fields.
tags:
- Distributed Inferences
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/DistributedInferenceCreationRequest'
responses:
'202':
description: Request completed successfully.
content:
application/json:
schema:
$ref: '#/components/schemas/DistributedInference'
'400':
$ref: '#/components/responses/400BadRequest'
'401':
$ref: '#/components/responses/401Unauthorized'
'403':
$ref: '#/components/responses/403Forbidden'
'503':
$ref: '#/components/responses/503ServiceUnavailable'
/api/v1/workloads/distributed-inferences/{workloadId}:
delete:
summary: Delete a distributed inference.
operationId: delete_distributed_inference
description: Delete a distributed inference using a workload id.
tags:
- Distributed Inferences
parameters:
- $ref: '#/components/parameters/WorkloadId'
responses:
'202':
$ref: '#/components/responses/202Accepted'
'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'
get:
summary: Get a distributed inference data.
operationId: get_distributed_inference
description: Retrieve a distributed inference details using a workload id.
tags:
- Distributed Inferences
parameters:
- $ref: '#/components/parameters/WorkloadId'
responses:
'200':
description: Executed successfully.
content:
application/json:
schema:
$ref: '#/components/schemas/DistributedInference'
'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 distributed inference spec.
operationId: update_distributed_inference_spec
description: Update the specification of an existing distributed inference workload.
tags:
- Distributed Inferences
parameters:
- $ref: '#/components/parameters/WorkloadId'
requestBody:
content:
application/json:
schema:
$ref: '#/components/schemas/UpdateRequest'
responses:
'202':
description: Executed successfully.
content:
application/json:
schema:
$ref: '#/components/schemas/DistributedInference'
'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: .*
PvcFieldsNonUpdatable:
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
ephemeral:
description: Use `true` to set PVC to ephemeral. If set to `true`, the PVC will be deleted when the workload is stopped. Not supported for inference workloads.
type: boolean
default: false
example: false
nullable: true
claimInfo:
$ref: '#/components/schemas/ClaimInfo'
dataSharing:
description: use `true` to share the PVC data to all projects under the selected scope.
type: boolean
default: false
example: false
nullable: true
nullable: true
type: object
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
WorkloadId2:
description: A unique ID of the workload.
type: string
format: uuid
DistributedInference:
allOf:
- $ref: '#/components/schemas/WorkloadMeta1'
- $ref: '#/components/schemas/DistributedInferenceSpec'
NodeAffinityRequired:
type: object
description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node.
properties:
nodeSelectorTerms:
description: A list of node selector terms. The terms are ORed.
type: array
items:
$ref: '#/components/schemas/NodeSelectorTerm'
nullable: true
UidGidSource:
description: Indicate the way to determine the user and group ids of the container. The options are a. `fromTheImage` - user and group ids are determined by the docker image that the container runs. this is the default option. b. `custom` - user and group ids can be specified in the environment asset and/or the workload creation request. c. `idpToken` - user and group IDs are automatically taken from the identity provider (IdP) token (available only in SSO-enabled installations). For more information, see [User Identity](https://docs.run.ai/latest/admin/runai-setup/config/non-root-containers/).
type: string
enum:
- fromTheImage
- fromIdpToken
- custom
nullable: true
SecretInstance2:
allOf:
- $ref: '#/components/schemas/StorageInstanceName'
- $ref: '#/components/schemas/Secret5'
- $ref: '#/components/schemas/ExcludeField'
nullable: true
type: object
Labels:
description: Set of labels to populate into the container running the workload.
type: array
items:
$ref: '#/components/schemas/Label'
nullable: true
Error:
required:
- code
- message
properties:
code:
type: integer
minimum: 100
maximum: 599
message:
type: string
details:
type: string
example:
code: 400
message: Bad request - Resource should have a name
ExcludeField:
properties:
exclude:
description: Use 'true' in case the item is defined in defaults of the policy, and you wish to exclude it from the workload.
type: boolean
default: false
example: false
nullable: true
type: object
nullable: true
CpuMemoryLimit:
description: Limitations on the CPU memory to allocate for this workload (1G, 20M, .etc). The system guarantees that this workload will not be able to consume more than this amount of memory. The workload will receive an error when trying to allocate more memory than this limit.
type: string
pattern: ^([+]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$
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'
DistributedInferenceSpec:
description: The specifications of the distributed inference to be created.
properties:
spec:
$ref: '#/components/schemas/DistributedInferenceSpecSpec'
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
SecretFieldsNonUpdatable:
properties:
secret:
description: The name of the Secret resource. (mandatory)
type: string
minLength: 1
nullable: true
nullable: true
type: object
Pvc:
allOf:
- $ref: '#/components/schemas/PvcFieldsUpdatable'
- $ref: '#/components/schemas/PvcFieldsNonUpdatable'
Capabilities:
description: Add POSIX capabilities to running containers. Defaults to the default set of capabilities granted by the container runtime.
type: array
items:
$ref: '#/components/schemas/Capability'
example:
- CHOWN
- KILL
nullable: true
GpuMemoryRequest:
description: Required if and only if gpuRequestType is memory. States the GPU memory to allocate for the created workload, per GPU device. Note that the workload will not be scheduled unless the system can guarantee this amount of GPU memory to the workload.
type: string
pattern: ^([+]?[0-9.]+)([eEinumkKMGTP]*[-+]?[0-9]*)$
example: 10M
nullable: true
DistributedInferenceCommonSpec:
allOf:
- nullable: true
properties:
category:
$ref: '#/components/schemas/Category'
nodePools:
$ref: '#/components/schemas/NodePools'
preemptibility:
$ref: '#/components/schemas/Preemptibility'
priorityClass:
$ref: '#/components/schemas/PriorityClass'
restartPolicy:
$ref: '#/components/schemas/DistributedInferenceRestartPolicy'
servingPort:
$ref: '#/components/schemas/DistributedInferenceServingPort'
type: object
- $ref: '#/components/schemas/DistributedInferenceStartupPolicyField'
- $ref: '#/components/schemas/DistributedInferenceWorkersField'
- $ref: '#/components/schemas/DistributedInferenceReplicasField'
nullable: true
type: object
SecretFieldsUpdatable:
properties:
mountPath:
description: Local path within the workload to which the Secret will be mapped to. (mandatory)
type: string
minLength: 1
nullable: true
defaultMode:
$ref: '#/components/schemas/DefaultMode'
nullable: true
type: object
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:
$ref: '#/components/schemas/EnvironmentVariableUserCredential'
exclude:
description: Use 'true' in case the environment variable is defined in defaults of the policy, and you wish to exclude it from the workload.
type: boolean
example: false
nullable: true
description:
description: Description of the environment variable.
type: string
example: Home directory of the user.
nullable: true
pattern: .*
nullable: true
type: object
LargeShmRequest:
description: A large /dev/shm device to mount into a container running the created workload. An shm is a shared file system mounted on RAM.
type: boolean
example: false
nullable: true
DistributedInferenceWorkersField:
properties:
workers:
default: 0
description: Specifies the number of worker nodes to run. If set to 0, only the leader node will run, and no worker pods will be created. In this case, worker spec is not required.
type: integer
format: int32
minimum: 0
maximum: 1000
example: 4
nullable: true
RunAsGid:
description: The group id to run the entrypoint of the container which executes the workspace. Default to the value specified in the environment asset `runAsGid` field (optional). Use only when the source uid/gid of the environment asset is not `fromTheImage`, and `overrideUidGidInWorkspace` is enabled.
type: integer
format: int64
example: 30
nullable: true
EnvironmentVariableSecret:
description: Details of the secret and key use to populate the environment variable
properties:
name:
description: The name of the secret resource. (mandatory)
type: string
minLength: 1
example: postgress_secret
nullable: true
pattern: ^[a-z0-9]([a-z0-9-]*[a-z0-9])?$
key:
description: The key in the secret resource. (mandatory)
type: string
minLength: 1
example: POSTGRES_PASSWORD
nullable: true
pattern: .*
nullable: true
type: object
Annotations:
description: Set of annotations to populate into the container running the workload.
type: array
items:
$ref: '#/components/schemas/Annotation'
nullable: true
WorkloadDesiredPhase:
description: The desired phase of the workload.
type: string
enum:
- Running
- Stopped
- Deleted
ProbeHandler:
description: The action taken to determine the health of the container. (mandatory)
type: object
properties:
httpGet:
description: An action based on HTTP Get requests.
type: object
properties:
path:
description: Path to access on the HTTP server, defaults to /.
type: string
pattern: ^(\x2F[a-zA-Z0-9\-_.\x2F]*)?$
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
DistributedInferenceLeaderWorkerSpec1:
properties:
annotations:
$ref: '#/components/schemas/Annotations'
args:
$ref: '#/components/schemas/Args'
command:
$ref: '#/components/schemas/Command'
compute:
nullable: true
properties:
cpuCoreLimit:
$ref: '#/components/schemas/CpuCoreLimit'
cpuCoreRequest:
$ref: '#/components/schemas/CpuCoreRequest'
cpuMemoryLimit:
$ref: '#/components/schemas/CpuMemoryLimit'
cpuMemoryRequest:
$ref: '#/components/schemas/CpuMemoryRequest'
extendedResources:
$ref: '#/components/schemas/ExtendedResources'
gpuDevicesRequest:
$ref: '#/components/schemas/GpuDevicesRequest'
gpuMemoryLimit:
$ref: '#/components/schemas/GpuMemoryLimit'
gpuMemoryRequest:
$ref: '#/components/schemas/GpuMemoryRequest'
gpuPortionLimit:
$ref: '#/components/schemas/GpuPortionLimit'
gpuPortionRequest:
$ref: '#/components/schemas/GpuPortionRequest'
gpuRequestType:
$ref: '#/components/schemas/GpuRequestType'
largeShmRequest:
$ref: '#/components/schemas/LargeShmRequest'
type: object
createHomeDir:
$ref: '#/components/schemas/CreateHomeDir'
environmentVariables:
$ref: '#/components/schemas/EnvironmentVariables'
image:
$ref: '#/components/schemas/Image'
imagePullPolicy:
$ref: '#/components/schemas/ImagePullPolicy'
imagePullSecrets:
$ref: '#/components/schemas/ImagePullSecrets'
labels:
$ref: '#/components/schemas/Labels'
nodeAffinityRequired:
$ref: '#/components/schemas/NodeAffinityRequired'
nodeType:
$ref: '#/components/schemas/NodeType3'
podAffinity:
$ref: '#/components/schemas/PodAffinity'
probes:
$ref: '#/components/schemas/Probes'
security:
nullable: true
properties:
capabilities:
$ref: '#/components/schemas/Capabilities'
readOnlyRootFilesystem:
$ref: '#/components/schemas/ReadOnlyRootFileSystem'
runAsGid:
$ref: '#/components/schemas/RunAsGid'
runAsNonRoot:
$ref: '#/components/schemas/RunAsNonRoot'
runAsUid:
$ref: '#/components/schemas/RunAsUid'
seccompProfileType:
$ref: '#/components/schemas/SeccompProfileType'
supplementalGroups:
$ref: '#/components/schemas/SupplementalGroups'
uidGidSource:
$ref: '#/components/schemas/UidGidSource'
type: object
storage:
nullable: true
properties:
configMapVolume:
$ref: '#/components/schemas/ConfigMapItems'
emptyDirVolume:
$ref: '#/components/schemas/EmptyDirItems'
pvc:
$ref: '#/components/schemas/PvcItems'
secretVolume:
$ref: '#/components/schemas/SecretItems1'
type: object
tolerations:
$ref: '#/components/schemas/Tolerations'
workingDir:
$ref: '#/components/schemas/WorkingDir'
type: object
TolerationEffect:
description: The taint effect to match. (mandatory)
type: string
enum:
- NoSchedule
- NoExecute
- PreferNoSchedule
- Any
nullable: true
MatchExpressionOperator:
description: Represents a key's relationship to a set of values (mandatory).
type: string
enum:
- In
- NotIn
- Exists
- DoesNotExist
- Gt
- Lt
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
UpdateSpec:
description: The specifications of the inference to be updated.
properties:
spec:
allOf:
- type: object
properties:
replicas:
description: Specifies the number of leader-worker sets to deploy. Each replica represents a group consisting of one leader pod and multiple worker pods. For example, setting replicas to 3 will create 3 independent groups, each with its own leader and corresponding set of workers.
type: integer
format: int32
minimum: 0
maximum: 1000
example: 2
nullable: true
nullable: true
DistributedInferenceServingPort:
description: Defines the configuration for the inference serving endpoint. This determines how applications or services can send inference requests to the workload.
allOf:
- $ref: '#/components/schemas/DistributedInferenceServingPortContainerAndProtocol'
- $ref: '#/components/schemas/DistributedInferenceServingPortAccess'
nullable: true
type: object
DepartmentId2:
description: The id of the department.
type: string
minLength: 1
example: 2
pattern: .*
DistributedInferenceRestartPolicy:
description: 'Determines the behavior when a pod fails.
- `RecreateGroupOnPodRestart`: Restarts all pods in the group if any pod fails.
- `None`: No automatic restart behavior is applied.
'
type: string
enum:
- RecreateGroupOnPodRestart
- None
nullable: true
default: RecreateGroupOnPodRestart
StorageInstanceName:
properties:
name:
description: unique name to identify the instance. primarily used for policy locked rules.
type: string
minLength: 1
example: storage-instance-a
nullable: true
nullable: true
type: object
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
DistributedInferenceWorkerSpecFields:
properties:
worker:
description: Defines the pod specification for the workers. Required only if the number of workers is greater than 0.
allOf:
- $ref: '#/components/schemas/DistributedInferenceLeaderWorkerSpec1'
nullable: true
type: object
SupplementalGroups:
description: Comma separated list of groups that the user running the container belongs to, in addition to the group indicated by runAsGid. Use only when the source uid/gid of the environment asset is not `fromTheImage`, and `overrideUidGidInWorkspace` is enabled. Using an empty string implies reverting the supplementary groups of the image.
type: string
example: 2,3,5,8
nullable: true
pattern: .*
DistributedInferenceSpecSpec:
allOf:
- $ref: '#/components/schemas/DistributedInferenceCommonSpec'
- $ref: '#/components/schemas/DistributedInferenceLeaderSpecFields'
- $ref: '#/components/schemas/DistributedInferenceWorkerSpecFields'
ConfigMapItems:
description: Set of config map volumes to use in the workload
type: array
items:
$ref: '#/components/schemas/ConfigMapInstance'
nullable: true
DistributedInferenceServingPortAccess:
properties:
authorizationType:
$ref: '#/components/schemas/DistributedInferenceServingPortAccessAuthorizationTypeEnum'
authorizedUsers:
description: A list of users and service accounts allowed to send inference requests to the serving endpoint. `Note:` Cannot be used together with authorizedGroups.
type: array
items:
type: string
pattern: .*
example:
- user.a@example.com
- user.b@example.com
nullable: true
authorizedGroups:
description: A list of user groups allowed to send inference requests to the serving endpoint. `Note:` Cannot be used together with authorizedUsers.
type: array
items:
type: string
pattern: .*
example:
- group-a
- group-b
nullable: true
exposeExternally:
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
exposedUrl:
description: The custom URL to use for the serving port. If empty (default), an autogenerated URL will be used.
type: string
nullable: true
pattern: .*
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. F
# --- truncated at 32 KB (60 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/runai/refs/heads/main/openapi/runai-distributed-inferences-api-openapi.yml