Sign in

v32

latestOpenAPI 3.1.0raw.githubusercontent.com2026-05-151,1412,2144.5 MB
Everywhere Inference Apps

Update inference application deployment

Updates an existing application deployment. You can modify the target regions and update configurations for individual components. To disable a component, set its value to null. Only the provided fields will be updated; all others remain unchanged.

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

Path parameters

project_idinteger required

Project ID

Example:1

Project ID

deployment_namestring required

Name of deployment

Name of deployment

Request body

api_keysstring[]

List of API keys for the application

components_configurationobject

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

regionsinteger[]

Geographical regions to be updated for the deployment

Example request

{
  "api_keys": [
    "key1",
    "key2"
  ],
  "components_configuration": {
    "model": {
      "scale": {
        "max": 2
      }
    }
  },
  "regions": [
    1,
    2
  ]
}

Response

OK

tasksstring[] required

List of task IDs representing asynchronous operations. Use these IDs to monitor operation progress:

  • GET /v1/tasks/{task_id} - Check individual task status and details Poll task status until completion (FINISHED/ERROR) before proceeding with dependent operations.
idstring required

Example response

{
  "tasks": [
    "d478ae29-dedc-4869-82f0-96104425f565"
  ]
}