Get ModelProvider

GET

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

GET

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

$ curl https://host.com/apis/models/v2/workspaces/workspace/providers/name \
>      -H "Content-Type: application/json"

1 {
2   "name": "llama-3.1-8b",
3   "workspace": "research_team_alpha",
4   "created_at": "2024-01-15T09:30:00Z",
5   "updated_at": "2024-04-10T16:45:00Z",
6   "host_url": "https://models.research.example.com/api/v1/inference",
7   "id": "provider-12345",
8   "project": "proj-ml-models/v1",
9   "description": "LLaMA 3.1 8B model provider for research experiments",
10   "api_key_secret_name": "secret-nemo-llama-3-1-8b",
11   "served_models": [
12     {
13       "model_entity_id": "research_team_alpha/llama-3.1-8b",
14       "served_model_name": "llama-3.1-8b-v1"
15     }
16   ],
17   "enabled_models": [
18     "llama-3.1-8b-v1"
19   ],
20   "status": "READY",
21   "status_message": "Model provider is operational and ready to serve requests.",
22   "default_extra_body": {
23     "temperature": 0.7,
24     "max_tokens": 1024
25   },
26   "default_extra_headers": {
27     "X-Custom-Header": "nemo-client"
28   },
29   "required_extra_body": {
30     "client_id": "research_alpha_001"
31   },
32   "required_extra_headers": {
33     "Authorization": "Bearer <token>"
34   },
35   "model_deployment_id": "deployment-7890",
36   "auth_context": {
37     "principal_id": "user-98765",
38     "principal_email": "alice.research@example.com",
39     "principal_groups": [
40       "researchers",
41       "ml-team"
42     ],
43     "principal_on_behalf_of": "user-12345",
44     "principal_on_behalf_of_groups": [
45       "admin",
46       "devops"
47     ],
48     "principal_on_behalf_of_email": "bob.admin@example.com"
49   },
50   "auth_header_format": "Authorization: Bearer {{ auth_secret }}"
51 }

Get a model provider by workspace and name.

Path parameters

workspacestringRequired

namestringRequired

Response

Return model provider details

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

host_urlstring<=2048 characters

The network endpoint URL for the model provider

idstring

Unique identifier for the model provider

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

The URN of the project associated with this entity.

descriptionstring<=1000 characters

Optional description of the model provider

api_key_secret_namestring<=255 characters

Reference to the API key stored in Secrets service

served_modelslist of objects

List of models served by this provider with routing information for IGW

enabled_modelslist of strings

Optional list of specific models to enable from this provider. If not set, all discovered models are enabled.

statusenumDefaults to UNKNOWN

Current status of the model provider, populated by models service

status_messagestring<=1000 charactersDefaults to

Detailed status message, populated by models service

default_extra_bodymap from strings to any

Default body parameters for inference requests. Can be overridden by user requests.

default_extra_headersmap from strings to strings

Default headers for inference requests. Can be overridden by user requests.

required_extra_bodymap from strings to any

Required body parameters for inference requests. Cannot be overridden by user requests.

required_extra_headersmap from strings to strings

Required headers for inference requests. Cannot be overridden by user requests.

model_deployment_idstring<=255 characters

Optional reference to the ModelDeployment ID if this provider was auto-created for a deployment

auth_contextobject

Auth context captured at provider creation.

auth_header_formatstring<=1024 characters

Jinja2 template string controlling how the API key secret is sent to the upstream. Must contain exactly one variable named auth_secret, which is substituted with the resolved secret value at request time. Example: 'X-Api-Key: {{ auth_secret }}'. If not set, defaults to 'Authorization: Bearer {{ auth_secret }}'.

Errors

422

Unprocessable Entity Error