Vertex AI pricing

When you train a model using a Tabular Workflow, you are charged based on the cost of the infrastructure and the dependent services. When you make inferences with this model, you are charged based on the cost of the infrastructure.

The cost of the infrastructure depends on the following factors:

• The number of machines you use. You can set associated parameters during model training, batch inference, or online inference.
• The type of machines you use. You can set this parameter during model training, batch inference, or online inference.
• The length of time the machines are in use.
  • If you train a model or make batch inferences, this is a measure of the total processing time of the operation.
  • If you make online inferences, this is a measure of the time that your model is deployed to an endpoint.

Tabular Workflows runs multiple dependent services in your project on your behalf: Dataflow, BigQuery, Cloud Storage, Vertex AI Pipelines, Vertex AI Training. These services charge you directly.

Examples of training cost calculation

Example 1: 110MB dataset in CSV format, trained for one hour with default hardware configuration.

The cost breakdown for the default workflow with Architecture Search and Training is as follows:

Service	Cost
Dataflow example and stats generation	$2 (Dataflow ran 7 min)
Dataflow data and feature transformations	$3 (Dataflow ran 10 min)
Vertex AI Training	0.8hr x $20 + 0.2hr x $20 + $3.3 SSD cost + pipeline container cost = $24 (48min tuning, 12min training)
Vertex AI Pipelines	1 run x $0.03 = $0.03
Total excluding model distillation	$27.03

Optionally, you can enable model distillation to reduce the resulting model size. The cost breakdown is as follows:

Service	Cost
Total excluding model distillation	$27.03
Vertex AI Training for model distillation	$1
Dataflow data, feature transformations for model distillation	$3 (Dataflow ran 10 min)
Batch inference for model distillation	$7
Total including model distillation	$38.03

Example 2: 1.84TB dataset in BigQuery, trained for 20 hours with hardware override.

The hardware configuration for this example is as follows:

Hardware Configuration Name	Value
stats_and_example_gen_dataflow_machine_type	n1-standard-16
stats_and_example_gen_dataflow_max_num_workers	100
stats_and_example_gen_dataflow_disk_size_gb	40
transform_dataflow_machine_type	n1-standard-16
transform_dataflow_max_num_workers	100
transform_dataflow_disk_size_gb	200
distill_batch_predict_machine_type	n1-standard-2
distill_batch_predict_starting_replica_count	200
distill_batch_predict_max_replica_count	200

The cost breakdown for the default workflow with Architecture Search and Training is as follows:

Service	Cost
Dataflow example and stats generation	$518 (Dataflow ran 6 hours)
Dataflow data, feature transformations	$471 (Dataflow ran 6 hours)
Vertex AI Training	17hr x $20 + 3hr x $20 + $41.5 SSD cost + pipeline container cost = $555 (17 hours tuning, 3 hours training)
Vertex AI Pipelines	1 run x $0.03 = $0.03
Total	$1544.03