Get inference application deployment

Retrieves detailed information about a specific application deployment. The response includes the catalog application it was created from, deployment name, active regions, configuration of each component, and the current status of the deployment.

GET /cloud/v3/inference/applications/{project_id}/deployments/{deployment_name}

Python

Python

import os
from gcore import Gcore

client = Gcore(
    api_key=os.environ.get("GCORE_API_KEY"),  # This is the default and can be omitted
)
inference_application_deployment = client.cloud.inference.applications.deployments.get(
    deployment_name="deployment_name",
    project_id=1,
)
print(inference_application_deployment.api_keys)

200

{
  "api_keys": [
    "key1",
    "key2"
  ],
  "application_name": "<string>",
  "components_configuration": {},
  "name": "<string>",
  "regions": [
    1,
    2
  ],
  "status": {
    "component_inferences": {},
    "expose_addresses": {},
    "regions": [
      {
        "components": {
          "model": {
            "error": "",
            "status": "Active"
          }
        },
        "region_id": 1,
        "status": "<string>"
      }
    ]
  }
}

Authorizations

Authorization · string · header · required

API key for authentication. Make sure to include the word apikey, followed by a single space and then your token. Example: apikey 1234$abcdef

Path Parameters

project_id · integer · required

Project ID

Example:

1

deployment_name · string · required

Name of deployment

Response

200 - application/json

OK

api_keys · string[] · required

List of API keys for the application

Example:

["key1", "key2"]

application_name · string · required

Identifier of the application template from the catalog

components_configuration · Components Configuration · object · required

Mapping of component names to their configuration (e.g., "model": {...})

Show child attributes

name · string · required

Unique identifier of the deployment

regions · integer[] · required

Geographical regions where the deployment is active

Example:

[1, 2]

status · Status · object · required

Current state of the deployment across regions

Show child attributes