Get Deployment Status

Check the deployment status of an aligned model.

This endpoint retrieves the current deployment status of a model, including progress and completion information.

Path Parameters:

• model_id: Unique identifier of the model to check deployment status for

Returns:

• model_id: The model identifier
• status: Deployment status
  • pending: Deployment in progress
  • completed: Successfully deployed (provider confirms DEPLOYED/READY)
  • failed: Deployment failed
• result: Task result details (if completed)
• start_time: Timestamp when deployment started
• end_time: Timestamp when deployment completed (null if still pending)

Raises:

• 404: If model not found or doesn’t belong to user

Example Request:

GET /api/v3/models/deploy-model/alignment-xyz789/status
Headers: {"Authorization": "Bearer <api_key>"}

Example Response (Pending):

{
  "model_id": "alignment-xyz789",
  "status": "pending",
  "result": null,
  "start_time": "2024-02-24T10:00:00Z",
  "end_time": null
}

Example Response (Completed):

{
  "model_id": "alignment-xyz789",
  "status": "completed",
  "result": {
    "deployment_id": "deploy-abc123",
    "endpoint_url": "https://api.example.com/v1/models/alignment-xyz789"
  },
  "start_time": "2024-02-24T10:00:00Z",
  "end_time": "2024-02-24T10:05:00Z"
}

Example Response (Failed):

{
  "model_id": "alignment-xyz789",
  "status": "failed",
  "result": {
    "error": "Deployment failed due to insufficient resources"
  },
  "start_time": "2024-02-24T10:00:00Z",
  "end_time": "2024-02-24T10:02:30Z"
}

Notes:

• Poll this endpoint to track deployment progress
• Status completed means the model is ready for inference
• Once completed, use /models/aligned to get the inference endpoint URL