Update ModelDeployment

POST

https://host.com/apis/models/v2/workspaces/:workspace/deployments/:name

POST

/apis/models/v2/workspaces/:workspace/deployments/:name

$ curl -X POST https://host.com/apis/models/v2/workspaces/workspace/deployments/name \
>      -H "Content-Type: application/json" \
>      -d '{
>   "config": "llama-config-v2"
> }'

1 {
2   "name": "llama-3.1-8b",
3   "workspace": "research-team-alpha",
4   "created_at": "2024-01-15T09:30:00Z",
5   "updated_at": "2024-04-20T14:45:00Z",
6   "entity_version": 3,
7   "config": "llama-config-v2",
8   "config_version": 2,
9   "id": "d4f1a2b3-c567-4e89-9f12-3456789abcde",
10   "project": "proj-llama-2024",
11   "status": "READY",
12   "status_message": "Deployment is active and serving requests.",
13   "status_history": [
14     {
15       "timestamp": "2024-01-15T09:30:00Z",
16       "status": "CREATED",
17       "status_message": "Deployment created."
18     },
19     {
20       "timestamp": "2024-01-20T10:00:00Z",
21       "status": "PENDING",
22       "status_message": "Deployment is pending initialization."
23     },
24     {
25       "timestamp": "2024-04-20T14:45:00Z",
26       "status": "READY",
27       "status_message": "Deployment is active and serving requests."
28     }
29   ],
30   "model_provider_id": "provider-workspace/llama-provider",
31   "auth_context": {
32     "principal_id": "user-12345",
33     "principal_email": "alice@example.com",
34     "principal_groups": [
35       "ml-engineers",
36       "research-team-alpha"
37     ],
38     "principal_on_behalf_of": "user-67890",
39     "principal_on_behalf_of_groups": [
40       "project-managers"
41     ],
42     "principal_on_behalf_of_email": "bob@example.com"
43   }
44 }

Update a ModelDeployment (creates a new immutable version).

Path parameters

workspacestringRequired

namestringRequired

Request

This endpoint expects an object.

configstringRequired<=255 characters

Reference to the ModelDeploymentConfig name

config_versionintegerOptional

Reference to a specific ModelDeploymentConfig version. If not specified, uses latest.

Response

Update a model deployment (creates new version)

namestringformat: "^[\w\-.]+$"<=255 characters

Name of the entity. Name/workspace combo must be unique across all entities. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.

workspacestringformat: "^[\w\-.]+$"<=255 characters

The workspace of the entity. Allowed characters: letters (a-z, A-Z), digits (0-9), underscores, hyphens, and dots.

created_atdatetime

The timestamp of model entity creation

updated_atdatetime

The timestamp of the last model entity update

entity_versioninteger

Version of this deployment. Automatically managed.

configstring<=255 characters

Reference to the ModelDeploymentConfig name

config_versioninteger

Reference to the specific ModelDeploymentConfig version

idstring

Unique identifier for the deployment

projectstringformat: "^[\w\-./]+$"<=255 characters

The URN of the project associated with this entity.

statusenumDefaults to UNKNOWN

Current status of the deployment, populated by models controller

status_messagestring<=1000 charactersDefaults to

Detailed status message, populated by models controller

status_historylist of objects

History of status changes, ordered chronologically (oldest first)

model_provider_idstring<=255 characters

Optional reference to the auto-created ModelProvider workspace/name (format: workspace/name)

auth_contextobject

Auth context captured at deployment creation.

Errors

422

Unprocessable Entity Error