GET
/
api
/
svc
/
v1
/
model-catalogues
/
deployment-specs
curl --request GET \
  --url https://{controlPlaneURL}/api/svc/v1/model-catalogues/deployment-specs \
  --header 'Authorization: Bearer <token>'
{
  "data": [
    {
      "name": "vLLM",
      "displayName": "<string>",
      "description": "<string>",
      "openAPIDescription": "<string>",
      "deployments": [
        {
          "name": "<string>",
          "spec": {},
          "isAvailableInWorkspace": true,
          "cost": {},
          "isTRTLLMEngineAvailable": true
        }
      ]
    }
  ],
  "pagination": {
    "total": 100,
    "offset": 0,
    "limit": 10
  }
}

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Query Parameters

limit
integer
default:100

Number of items per page

Required range: 1 <= x <= 1000
Example:

10

offset
integer
default:0

Number of items to skip

Required range: x >= 0
Example:

0

modelVersionFqn
string

FQN of the Model Version

huggingfaceHubUrl
string

huggingface hub url

workspaceId
string
required

workspace id

huggingfaceHubTokenSecretFqn
string

Huggingface hub token secret

pipelineTagOverride
string

The pipeline tag of the model for which deployment spec is being generated

Response

200
application/json
Returns deployment specifications for the model version or HuggingFace model URL And also the response includes paginated data.
data
object[]
required

Array of ModelDeploymentSpec

pagination
object
required

Pagination information