ModelResponse
Data returned for Model. Required fields are id, name, category, type, protocol, item.
Server-assigned unique identifier
Resource name
alias object
URL-safe short handle
- string
- null
Resource type tag
Model placement: internal is hosted in D.Hub; external uses a registered endpoint.
Possible values: [internal, external]
collection_id object
Parent collection ID
- string
- null
folder_id object
Identifier of the containing folder.
- string
- null
tags object
Classification labels
- string[]
- null
description object
Resource description
- string
- null
Mandatory marking ids this resource requires; read-only — set via the marking guard endpoints, not Create/PATCH.
[]created_at object
Creation timestamp (Unix ms)
- integer
- null
updated_at object
Last update timestamp (Unix ms)
- integer
- null
owners object[]
Users and groups that own the resource.
"user.
Possible values: [user, group, public]
avatar_url object
- string
- null
avatar_config object
- object
- null
email object
- string<email>
- null
my_share_scope object
How the current caller received access to the resource.
- string
- null
Possible values: [owner, grant, admin]
REST contract identifier ('openai-embeddings' | 'custom').
Possible values: [openai-embeddings, custom]
deployment object
- ModelDeployment
- null
Fully qualified container image reference. Custom images must be digest-pinned and cannot use the latest tag.
artifact_version object
Artifact version identifier to deploy. Omit it to resolve the latest version when deployment starts.
- string
- null
command object
Optional container entrypoint override.
- string[]
- null
args object
Optional arguments that override the image command.
- string[]
- null
8080cpu object
Requested CPU amount, such as 500m.
- string
- null
memory object
Requested memory amount, such as 2Gi.
- string
- null
gpu object
GPU count request
- integer
- null
Number of model instances to run. Higher values increase resource usage.
1HTTP path used to check whether the model is ready and healthy.
/healthzenv object
Non-secret environment variables passed to the model container. Store secrets separately.
node_selector object
Node labels that every selected execution node must match.
tolerations object[]
Node taints that the model deployment is allowed to tolerate.
key object
Taint key matched by this toleration, or null to match every key when operator is Exists.
- string
- null
'Equal' requires value; 'Exists' ignores it.
Possible values: [Exists, Equal]
Equalvalue object
- string
- null
effect object
Taint effect matched by this toleration, or null to match every effect.
- string
- null
Possible values: [NoSchedule, PreferNoSchedule, NoExecute]
toleration_seconds object
For effect='NoExecute', evict after this many seconds.
- integer
- null
url object
- string
- null
auth object
- ModelExternalAuth
- null
Possible values: [bearer, none]
nonesecret_ref object
Opaque reference to a stored secret. Required when kind is bearer; raw tokens are never returned.
- string
- null
AuthorizationBearer model object
- string
- null
false{
"id": "string",
"name": "string",
"alias": "string",
"category": "string",
"type": "internal",
"collection_id": "string",
"folder_id": "string",
"tags": [
"string"
],
"description": "string",
"markings": [
"string"
],
"created_at": 0,
"updated_at": 0,
"owners": [
{
"id": "string",
"type": "user",
"display_name": "string",
"avatar_url": "string",
"avatar_config": {},
"email": "user@example.com"
}
],
"my_share_scope": "owner",
"protocol": "openai-embeddings",
"deployment": {
"image": "string",
"artifact_version": "string",
"command": [
"string"
],
"args": [
"string"
],
"port": 8080,
"cpu": "string",
"memory": "string",
"gpu": 0,
"replicas": 1,
"health_path": "/healthz",
"env": {},
"node_selector": {},
"tolerations": [
{
"key": "string",
"operator": "Equal",
"value": "string",
"effect": "NoSchedule",
"toleration_seconds": 0
}
]
},
"url": "string",
"auth": {
"kind": "none",
"secret_ref": "string",
"header": "Authorization",
"prefix": "Bearer "
},
"model": "string",
"ready": false
}