<p>Starts a transform job. A transform job uses a trained model to get inferences on a dataset and saves these results to an Amazon S3 location that you specify.</p> <p>To perform batch transformations, you create a transform job and use the data that you have readily available.</p> <p>In the request body, you provide the following:</p> <ul> <li> <p> <code>TransformJobName</code> - Identifies the transform job. The name must be unique within an Amazon Web Services Region in an Amazon Web Services account.</p> </li> <li> <p> <code>ModelName</code> - Identifies the model to use. <code>ModelName</code> must be the name of an existing Amazon SageMaker model in the same Amazon Web Services Region and Amazon Web Services account. For information on creating a model, see <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateModel.html">CreateModel</a>.</p> </li> <li> <p> <code>TransformInput</code> - Describes the dataset to be transformed and the Amazon S3 location where it is stored.</p> </li> <li> <p> <code>TransformOutput</code> - Identifies the Amazon S3 location where you want Amazon SageMaker to save the results from the transform job.</p> </li> <li> <p> <code>TransformResources</code> - Identifies the ML compute instances for the transform job.</p> </li> </ul> <p>For more information about how batch transformation works, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/batch-transform.html">Batch Transform</a>.</p>

{
  "success": true,
  "data": {
    "id": "abc123",
    "created_at": "2025-01-01T00:00:00Z"
  }
}

{
  "success": false,
  "error": {
    "code": "VALIDATION_ERROR",
    "message": "Invalid request parameters"
  }
}