GCP-PMLE · Drill mode

You want to deploy a model behind a low-latency HTTPS endpoint that autoscales to zero when idle. Which Vertex AI option is best?

• AA. Vertex AI Online Prediction with the auto-scaling minimum set to zero (for supported regions/runtimes)
• BB. Vertex AI Batch Prediction
• CC. Compute Engine with manual scaling
• DD. BigQuery ML