Vertex AI quotas and limits

Google Cloud uses quotas to help ensure fairness and reduce spikes in resource use and availability. A quota restricts how much of a Google Cloud resource your Google Cloud project can use. Quotas apply to a range of resource types, including hardware, software, and network components. For example, quotas can restrict the number of API calls to a service, the number of load balancers used concurrently by your project, or the number of projects that you can create. Quotas protect the community of Google Cloud users by preventing the overloading of services. Quotas also help you to manage your own Google Cloud resources.

The Cloud Quotas system does the following:

• Monitors your consumption of Google Cloud products and services
• Restricts your consumption of those resources
• Provides a way to request changes to the quota value and automate quota adjustments

In most cases, when you attempt to consume more of a resource than its quota allows, the system blocks access to the resource, and the task that you're trying to perform fails.

Quotas generally apply at the Google Cloud project level. Your use of a resource in one project doesn't affect your available quota in another project. Within a Google Cloud project, quotas are shared across all applications and IP addresses.

There are also limits on Vertex AI resources. These limits are unrelated to the quota system. Limits can't be changed.

Request quotas

The following quotas apply to Vertex AI requests for a given project and supported region. For example, in a single project, you can have up to 30,000 online inference requests per minute in one region and another 30,000 online inference requests per minute in another supported region.

Request type	Requests per minute
Resource management (CRUD) requests^1	600
Job or long-running operation (LRO) submission requests	60
Online inference requests^2	30,000
Online inference request throughput	1.5 GB
Online explain requests	600
Vertex AI TensorBoard Time Series read requests	60,000
ML Metadata (CRUD) requests	12,000
generative AI Caching (CRUD) requests	200
Vertex AI Vizier (CRUD) requests	6,000
Vertex AI Feature Store online serving requests	300,000
Vertex ML Metadata requests	12,000
Number of count tokens or compute tokens requests	3,000

¹Resource management requests include any request that isn't a job, an LRO, an online inference request, a Vertex AI Vizier request, an ML metadata request, a Vertex AI TensorBoard Timeseries Insights API read request, a Vertex AI Feature Store request, a Vertex AI Feature Store streaming request, or a Vector Search request.

² This quota applies for public endpoints only.

Jobs or LROs include the following requests:

• Create or delete a dataset.
• Import or export data to or from a dataset.
• Create an endpoint.
• Create or delete a custom job.
• Create or delete a data-labeling job.
• Create or delete a hyper-parameter tuning job.
• Create or delete a batch-inference job.
• Create or delete a model.
• Upload, delete, or export a model.
• Create or delete a notebook-runtime template.
• Assign, delete, start, or upgrade a notebook runtime.
• Create, delete, or update a model monitor.
• Create or delete a model monitoring job.

For quota information for Generative AI models, see Generative AI on Vertex AI quotas and limits.

AutoML model quotas

The following quotas apply to each data type and objective for a given project and region. For example, in a particular project and region, you can deploy 10 AutoML image classification models and 10 AutoML image object detection models for a total of 20 deployed models.

Image

Classification

Quota	Value
Concurrent training jobs	5
Concurrent training jobs with explainable AI	2
Concurrent batch inference jobs	5
Concurrent model deployment jobs	5
Concurrent model undeployment jobs	5
Number of deployed models	10

Object detection

Quota	Value
Concurrent training jobs	5
Concurrent batch inference jobs	5
Number of deployed models	10

Tabular

Quota	Value
Concurrent training jobs	5
Concurrent batch inference jobs	5
Number of deployed models	30

Text

Starting on September 15, 2024, you can only customize classification, entity extraction, and sentiment analysis objectives by moving to Vertex AI Gemini prompts and tuning. Training or updating models for Vertex AI AutoML for Text classification, entity extraction, and sentiment analysis objectives will no longer be available. You can continue using existing Vertex AI AutoML Text models until June 15, 2025. For a comparison of AutoML text and Gemini, see Gemini for AutoML text users. For more information about how Gemini offers enhanced user experience through improved prompting capabilities, see Introduction to tuning. To get started with tuning, see Model tuning for Gemini text models

Classification

Quota	Value
Concurrent training jobs	5
Concurrent batch inference jobs	5
Number of deployed models	10

Entity extraction

Quota	Value
Concurrent training jobs	5
Concurrent batch inference jobs	5
Number of deployed models	10

Sentiment analysis

Quota	Value
Concurrent training jobs	5
Concurrent batch inference jobs	5
Number of deployed models	10

Video

Action Recognition

Quota	Value
Concurrent training jobs	5
Concurrent batch inference jobs	5

Classification

Quota	Value
Concurrent training jobs	5
Concurrent batch inference jobs	5

Object tracking

Quota	Value
Concurrent training jobs	5
Concurrent batch inference jobs	5

Vertex AI Model Registry

The maximum model size supported by Vertex AI Model Registry is 1 TB.

AutoML model limits

The following limits apply to each data type for a given project and region. For example, in a particular project and region, you can include a maximum of 1,000,000 images in a batch request input.

Image

Type of limit	Value
Image file size	Maximum: 30MB
Images per dataset	Maximum: 1,000,000
Labels per dataset	Minimum: 2 Maximum: 5000
Images per label	Minimum: 10 Recommended: 1000
Batch input CSV file size	Maximum: 100MB
Number of images in batch input	Maximum: 1,000,000

Tabular

Type of limit	Value
Maximum size	100GB
Number of rows	Between 1,000 and 200,000,000 rows
Number of columns	Between 2 and 1,000 columns
Number of concurrently running dataset imports	5 imports
CSV file size	Maximum: 10GB per file, up to maximum total amount of 100GB

Text

Starting on September 15, 2024, you can only customize classification, entity extraction, and sentiment analysis objectives by moving to Vertex AI Gemini prompts and tuning. Training or updating models for Vertex AI AutoML for Text classification, entity extraction, and sentiment analysis objectives will no longer be available. You can continue using existing Vertex AI AutoML Text models until June 15, 2025. For a comparison of AutoML text and Gemini, see Gemini for AutoML text users. For more information about how Gemini offers enhanced user experience through improved prompting capabilities, see Introduction to tuning. To get started with tuning, see Model tuning for Gemini text models

Character counts assume UTF-8 characters.

Type of limit	Classification	Entity extraction	Sentiment analysis
Training items	10 to 1,000,000	50 to 100,000	10 to 100,000
Labels per dataset	2 to 5,000	1 to 100	2 to 11
Length of label name	1 to 32	1 to 32	Integer from 0 to 10
Length of annotated span	N/A	1 to 100 characters	N/A
Training items per label	10 to 1,000,000	100 to 100,000	10 to 100,000
Training item size	10MB 5,000,000 characters	128 KB (text); 20MB (PDF) 10 to 300,000 characters (text)	128 KB (text); 2MB (PDF) 60,000 characters
Item sent for inference	128 KB (text); 2MB (PDF) 60,000 characters	20MB	128 KB (text); 2MB (PDF) 60,000 characters
Items per batch request	10,000	10,000	10,000

Video

Type of limit	Value
Maximum video length	3 hours
Maximum video file size	50GB
Minimum labels per dataset	2
Minimum videos per label	10 (1000 is recommended)
Batch input CSV file size	Maximum: 100MB
Number of video segments in batch input	Maximum: 1,000

Custom-trained model quotas

The following quotas apply to Vertex AI custom-trained models for a given project and region.

Note: The number of CPUs or GPUs are not counted against Compute Engine quotas. They are counted separately and can't be used together.

Training

Quota	Value
Concurrent custom training pipelines	2,000

Number of N1 and E2 CPUs for training, per region
Region	Value
us-west1	2,200
us-west2	20
us-west3	2,200
us-west4	20
us-central1	2,200
us-east1	2,200
us-east4	20
us-east5	450
us-south1	450
northamerica-northeast1	2,200
northamerica-northeast2	20
southamerica-east1	20
southamerica-west1	20
europe-west2	2,200
europe-west1	2,200
europe-west4	2,200
europe-west6	20
europe-west3	2,200
europe-north1	20
europe-central2	450
europe-west8	20
europe-west9	450
europe-southwest1	20
asia-south1	2,200
asia-southeast1	2,200
asia-southeast2	2,200
asia-east2	2,200
asia-east1	2,200
asia-northeast1	2,200
asia-northeast2	20
australia-southeast1	2,200
australia-southeast2	20
asia-northeast3	2,200
me-west1	450
me-central1	450
me-central2	450
europe-west12	450
africa-south1	450

Number of N2 CPUs for training, per region
Region	Value
us-west1	20
us-west2	20
us-west3	20
us-west4	20
us-central1	450
us-east1	20
us-east4	20
us-east5	450
us-south1	20
northamerica-northeast1	20
northamerica-northeast2	20
southamerica-east1	20
southamerica-west1	20
europe-west2	20
europe-west1	20
europe-west4	450
europe-west6	20
europe-west3	20
europe-north1	20
europe-central2	20
europe-west8	20
europe-west9	450
europe-southwest1	20
asia-south1	20
asia-southeast1	20
asia-southeast2	20
asia-east2	20
asia-east1	450
asia-northeast1	20
asia-northeast2	20
australia-southeast1	20
australia-southeast2	20
asia-northeast3	20
me-west1	20
me-central1	450
me-central2	450
europe-west12	450
africa-south1	450

Number of M1 CPUs for training, per region
Region	Value
us-west1	0
us-west2	0
us-west3	0
us-west4	0
us-central1	0
us-east1	0
us-east4	0
us-east5	0
us-south1	0
northamerica-northeast1	0
northamerica-northeast2	0
southamerica-east1	0
southamerica-west1	0
europe-west2	0
europe-west1	0
europe-west4	0
europe-west6	0
europe-west3	0
europe-north1	0
europe-central2	0
europe-west8	0
europe-west9	0
europe-southwest1	0
asia-south1	0
asia-southeast1	0
asia-southeast2	0
asia-east2	0
asia-east1	0
asia-northeast1	0
asia-northeast2	0
australia-southeast1	0
australia-southeast2	0
asia-northeast3	0
me-west1	0
me-central1	0
me-central2	0
europe-west12	0
africa-south1	0

Number of C2 CPUs for training, per region
Region	Value
us-west1	20
us-west2	20
us-west3	20
us-west4	20
us-central1	450
us-east1	20
us-east4	20
us-east5	450
us-south1	20
northamerica-northeast1	20
northamerica-northeast2	20
southamerica-east1	20
southamerica-west1	20
europe-west2	20
europe-west1	20
europe-west4	450
europe-west6	20
europe-west3	20
europe-north1	20
europe-central2	20
europe-west8	20
europe-west9	450
europe-southwest1	20
asia-south1	20
asia-southeast1	20
asia-southeast2	20
asia-east2	20
asia-east1	450
asia-northeast1	20
asia-northeast2	20
australia-southeast1	20
australia-southeast2	20
asia-northeast3	20
me-west1	20
me-central1	20
me-central2	20
europe-west12	20
africa-south1	20

Number of A2 CPUs for training, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	Unlimited
us-east1	Unlimited
us-east4	Unlimited
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	Unlimited
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Unlimited
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Unlimited
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of concurrent A3 CPUs for training, per region
Region	Value
us-west1	Unlimited
us-west2	Unlimited
us-west3	Unlimited
us-west4	Unlimited
us-central1	Unlimited
us-east1	Unlimited
us-east4	Unlimited
us-east5	Unlimited
us-south1	Unlimited
northamerica-northeast1	Unlimited
northamerica-northeast2	Unlimited
southamerica-east1	Unlimited
southamerica-west1	Unlimited
europe-west2	Unlimited
europe-west1	Unlimited
europe-west4	Unlimited
europe-west6	Unlimited
europe-west3	Unlimited
europe-north1	Unlimited
europe-central2	Unlimited
europe-west8	Unlimited
europe-west9	Unlimited
europe-southwest1	Unlimited
asia-south1	Unlimited
asia-southeast1	Unlimited
asia-southeast2	Unlimited
asia-east2	Unlimited
asia-east1	Unlimited
asia-northeast1	Unlimited
asia-northeast2	Unlimited
australia-southeast1	Unlimited
australia-southeast2	Unlimited
asia-northeast3	Unlimited
me-west1	Unlimited
me-central1	Unlimited
me-central2	Unlimited
europe-west12	Unlimited
africa-south1	Unlimited

Number of concurrent H200 GPUs for training, per region
Region	Value
us-west1	0
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	0
us-east1	Not available
us-east4	8
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	0
europe-west4	Not available
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of P4 GPUs for training, per region
Region	Value
us-west1	Not available
us-west2	6
us-west3	Not available
us-west4	Not available
us-central1	6
us-east1	Not available
us-east4	1
us-east5	Not available
us-south1	Not available
northamerica-northeast1	6
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	6
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	6
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	6
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of T4 GPUs for training, per region
Region	Value
us-west1	2
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	12
us-east1	2
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	6
europe-west1	Not available
europe-west4	2
europe-west6	Not available
europe-west3	0
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	6
asia-southeast1	1
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	6
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	1
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of L4 GPUs for training, per region
Region	Value
us-west1	0
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	0
us-east1	0
us-east4	0
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	0
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	0
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	0
asia-southeast1	0
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	0
me-west1	Not available
me-central1	Not available
me-central2	0
europe-west12	Not available
africa-south1	Not available

Number of P100 GPUs for training, per region
Region	Value
us-west1	30
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	56
us-east1	30
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	30
europe-west4	Not available
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	30
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	6
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of V100 GPUs for training, per region
Region	Value
us-west1	6
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	6
us-east1	Not available
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	6
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	6
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of A100 GPUs for training, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	8
us-east1	Not available
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	8
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	8
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of concurrent A100 80GB GPUs for training, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	0
us-east1	Not available
us-east4	0
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	0
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	0
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

For more information, see View and manage quotas.

Number of concurrent H100 GPUs for training, per region
Region	Value
us-west1	0
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	0
us-east1	Not available
us-east4	0
us-east5	0
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	0
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	0
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	0
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of concurrent B200 GPUs for training, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	0
us-east1	Not available
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	Not available
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of concurrent H100 Mega GPUs for training, per region
Region	Value
us-west1	0
us-west2	Not available
us-west3	Not available
us-west4	0
us-central1	0
us-east1	Not available
us-east4	0
us-east5	0
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	0
europe-west4	0
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	0
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	0
asia-northeast2	Not available
australia-southeast1	0
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

For more information, see View and manage quotas.

Number of TPU V2 cores for training, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	8
us-east1	Not available
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	8
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	8
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of TPU V2 pod cores for training, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	Not available
us-east1	Not available
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	Not available
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of TPU V3 cores for training, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	8
us-east1	Not available
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	8
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	8
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of TPU V3 pod cores for training, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	Not available
us-east1	Not available
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	Not available
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

HDD usage (GB) during training, per region
Region	Value
us-west1	180,000
us-west2	3,600
us-west3	180,000
us-west4	3,600
us-central1	180,000
us-east1	180,000
us-east4	3,600
us-east5	3,600
us-south1	180,000
northamerica-northeast1	180,000
northamerica-northeast2	3,600
southamerica-east1	3,600
southamerica-west1	3,600
europe-west2	180,000
europe-west1	180,000
europe-west4	180,000
europe-west6	3,600
europe-west3	180,000
europe-north1	3,600
europe-central2	180,000
europe-west8	3,600
europe-west9	180,000
europe-southwest1	3,600
asia-south1	180,000
asia-southeast1	180,000
asia-southeast2	180,000
asia-east2	180,000
asia-east1	180,000
asia-northeast1	180,000
asia-northeast2	3,600
australia-southeast1	180,000
australia-southeast2	3,600
asia-northeast3	180,000
me-west1	180,000
me-central1	3,600
me-central2	3,600
europe-west12	3,600
africa-south1	3,600

SSD usage (GB) during training, per region
Region	Value
us-west1	75,000
us-west2	450
us-west3	75,000
us-west4	450
us-central1	75,000
us-east1	75,000
us-east4	450
us-east5	450
us-south1	75,000
northamerica-northeast1	75,000
northamerica-northeast2	450
southamerica-east1	450
southamerica-west1	450
europe-west2	75,000
europe-west1	75,000
europe-west4	75,000
europe-west6	450
europe-west3	75,000
europe-north1	450
europe-central2	75,000
europe-west8	450
europe-west9	75,000
europe-southwest1	450
asia-south1	75,000
asia-southeast1	75,000
asia-southeast2	75,000
asia-east2	75,000
asia-east1	75,000
asia-northeast1	75,000
asia-northeast2	450
australia-southeast1	75,000
australia-southeast2	450
asia-northeast3	75,000
me-west1	75,000
me-central1	450
me-central2	450
europe-west12	450
africa-south1	450

Hyperdisk Balanced usage (GB) during training, per region
Region	Value
us-west1	75,000
us-west2	450
us-west3	450
us-west4	450
us-central1	75,000
us-east1	450
us-east4	75,000
us-east5	450
us-south1	75,000
northamerica-northeast1	450
northamerica-northeast2	450
southamerica-east1	450
southamerica-west1	450
europe-west2	450
europe-west1	75,000
europe-west4	75,000
europe-west6	450
europe-west3	450
europe-north1	450
europe-central2	450
europe-west8	450
europe-west9	450
europe-southwest1	450
asia-south1	75,000
asia-southeast1	450
asia-southeast2	450
asia-east2	450
asia-east1	450
asia-northeast1	450
asia-northeast2	450
australia-southeast1	450
australia-southeast2	450
asia-northeast3	450
me-west1	450
me-central1	450
me-central2	450
europe-west12	450
africa-south1	450

Serving

Quota	Value
Number of deployed custom model replicas	100

Number of CPUs for serving, per region
Region	Value
us-west1	2,200
us-west2	2,200
us-west3	2,200
us-west4	16
us-central1	2,200
us-east1	2,200
us-east4	2,200
us-east5	16
us-south1	450
northamerica-northeast1	2,200
northamerica-northeast2	450
southamerica-east1	2,200
southamerica-west1	450
europe-west2	2,200
europe-west1	2,200
europe-west4	2,200
europe-west6	2,200
europe-west3	2,200
europe-north1	16
europe-central2	450
europe-west8	16
europe-west9	16
europe-southwest1	16
asia-south1	2,200
asia-southeast1	2,200
asia-southeast2	2,200
asia-east2	2,200
asia-east1	2,200
asia-northeast1	2,200
asia-northeast2	16
australia-southeast1	2,200
australia-southeast2	16
asia-northeast3	2,200
me-west1	450
me-central1	16
me-central2	16
europe-west12	16
africa-south1	16

Number of concurrent H200 GPUs for serving, per region
Region	Value
us-west1	0
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	0
us-east1	Not available
us-east4	0
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	0
europe-west4	Not available
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of P100 GPUs for serving, per region
Region	Value
us-west1	30
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	56
us-east1	30
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	30
europe-west4	Not available
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	30
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of P4 GPUs for serving, per region
Region	Value
us-west1	Not available
us-west2	6
us-west3	Not available
us-west4	Not available
us-central1	6
us-east1	Not available
us-east4	6
us-east5	Not available
us-south1	Not available
northamerica-northeast1	6
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	6
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	6
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	6
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of T4 GPUs for serving, per region
Region	Value
us-west1	12
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	12
us-east1	12
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	12
europe-west1	Not available
europe-west4	12
europe-west6	Not available
europe-west3	0
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	6
asia-southeast1	6
asia-southeast2	Not available
asia-east2	12
asia-east1	6
asia-northeast1	6
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	6
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of L4 GPUs for serving, per region
Region	Value
us-west1	28
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	28
us-east1	28
us-east4	28
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	28
europe-west1	28
europe-west4	28
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	28
asia-southeast2	Not available
asia-east2	Not available
asia-east1	28
asia-northeast1	28
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of V100 GPUs for serving, per region
Region	Value
us-west1	6
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	6
us-east1	Not available
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	6
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of A100 GPUs for serving, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	14
us-east1	Not available
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	14
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	14
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	14
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	14
me-west1	1
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of A100 80GB GPUs for serving, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	1
us-east1	Not available
us-east4	1
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	1
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	1
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of concurrent B200 GPUs for serving, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	0
us-east1	Not available
us-east4	Not available
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	Not available
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of H100 GPUs for serving, per region
Region	Value
us-west1	8
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	8
us-east1	Not available
us-east4	0
us-east5	Not available
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	8
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	8
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of H100 Mega GPUs for serving, per region
Region	Value
us-west1	0
us-west2	Not available
us-west3	Not available
us-west4	0
us-central1	0
us-east1	Not available
us-east4	0
us-east5	0
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	0
europe-west4	0
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	0
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	0
asia-northeast2	Not available
australia-southeast1	0
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of v5e TPU Chips for serving, per region
Region	Value
us-west1	4
us-west2	Not available
us-west3	Not available
us-west4	0
us-central1	16
us-east1	Not available
us-east4	Not available
us-east5	Not available
us-south1	0
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	0
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	Not available
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Number of v6e TPU Chips for serving, per region
Region	Value
us-west1	Not available
us-west2	Not available
us-west3	Not available
us-west4	Not available
us-central1	Not available
us-east1	0
us-east4	Not available
us-east5	0
us-south1	Not available
northamerica-northeast1	Not available
northamerica-northeast2	Not available
southamerica-east1	Not available
southamerica-west1	Not available
europe-west2	Not available
europe-west1	Not available
europe-west4	0
europe-west6	Not available
europe-west3	Not available
europe-north1	Not available
europe-central2	Not available
europe-west8	Not available
europe-west9	Not available
europe-southwest1	Not available
asia-south1	Not available
asia-southeast1	Not available
asia-southeast2	Not available
asia-east2	Not available
asia-east1	Not available
asia-northeast1	0
asia-northeast2	Not available
australia-southeast1	Not available
australia-southeast2	Not available
asia-northeast3	Not available
me-west1	Not available
me-central1	Not available
me-central2	Not available
europe-west12	Not available
africa-south1	Not available

Custom-trained model limits

The following limits apply to Vertex AI custom-trained models for a given project and region.

Serving

Limit	Value
Number of replicas per project	200
Number of containers per cluster	25,000

Vertex AI Feature Store

This section lists the quotas and limits for the following:

• Vertex AI Feature Store

• Vertex AI Feature Store (Legacy)

Vertex AI Feature Store

The following quotas apply to a given project and region. For example, in a single project, you can have 200 online serving nodes in us-central1 and another 50 nodes in us-east4.

Quota	Value
Online serving requests per minute	300,000
Maximum number of FeatureOnlineStore instances	10
Maximum number of search requests per minute	6,000,000
Maximum number of online serving nodes across all Optimized FeatureOnlineStore instances in the project	80
Maximum number of FeatureView instances across all FeatureOnlineStore instances	30

Vertex AI Feature Store also has the following limits. You can't request an increase to any of the limits in the following table:

Limit	Value
Maximum number of FeatureGroup resources in a project and location	250
Maximum number of Feature resources within a FeatureGroup	10,000
Maximum size of feature data per entity	5 MB
Number of entity IDs per online serving request (FetchFeatureValues)	1
Maximum length of an entity ID	4076 characters
Storage limit for an Optimized online serving node	200 GB

Vertex AI Feature Store (Legacy)

The following quotas apply to a given project and region. For example, in a single project, you can have 75 concurrent batch jobs in us-central1 and another 75 jobs in europe-west4.

Quota	Value
Online serving requests per minute	300,000
Streaming ingestion requests per minute	60,000
Streaming ingestion write throughput per minute	1.2 GB
Feature creation requests per minute	100
Online serving nodes across all featurestores	30
Concurrent batch jobs (ingestion, serving, and delete feature values combined)	75
Concurrent requests to delete feature values	1
Entity types across all featurestores	75

Vertex AI Feature Store (Legacy) also has the following limits. You can't request an increase to any of the limits in the following table:

Limit	Value
Storage limit for an online serving node	5 TB
Total data in the offline store	Unlimited
Features per entity type	5,000
Number of create, update, and delete featurestore requests per day per project per region	500
For streaming ingestion, the size per request	1 MB
For streaming read, the number of entities that can be included per request	100
For batch import, the number of files that can be included per request	5,000 for Avro or 500 for CSV
For batch serving and exports, the number of features you can request	5,000
For batch ingestion and streaming ingestion, the oldest timestamp for which feature data can be ingested	4,000 days from current date

The data retention limit in Vertex AI Feature Store (Legacy) has the following default value, which you can override:

Data retention defaults	Default value
Data retention in offline store (oldest feature value timestamp after which the values are deleted)	4,000 days from the current date
Data retention in online store (oldest feature value timestamp after which the values are deleted)	4,000 days from the current date

You can override the data retention limit in the following ways:

• To override the data retention limit for the online store, set the online_storage_ttl_days parameter while creating or updating a featurestore.

• To override the data retention limit for the offline store, set the offline_storage_ttl_days parameter while creating or updating an entity type.

Note: Vertex AI Feature Store (Legacy) uses column-partitioned tables from BigQuery. Your project can make up to 30,000 partition modifications per day for a column-partitioned table in BigQuery. If you exceed this limit, Vertex AI returns an error. For more information about this error, see Number of partition modifications for column-partitioned tables quota errors.
Learn more about limits for BigQuery partitioned tables.

Vector Search

The following quotas apply to Vector Search for a given project in each region.

Quota	Value
Concurrent index creation operations	5
Concurrent index update operations	5
Number of deployed index nodes	50
Number of deployed index N2D nodes	5
Number of Index	100
Streaming Update requests per minute	6,000
Streaming Update throughput(in KB) per minute	120,000

Vertex ML Metadata

The following limits apply to Vertex ML Metadata for a given project in each region.

Limit	Value
Maximum serialized size of the metadata field within a resource	204,800 bytes
Maximum serialized size of metadata schemas	204,800 bytes

Vertex AI Pipelines

The following quotas and limits apply to Vertex AI Pipelines for a given project in each region.

Quota	Value
Running pipeline tasks in parallel^*	600
Concurrent pipeline runs^*	300

^* Pipeline run and task requests beyond this limit are queued until resources are available.

Vertex AI Pipelines have the following limits. Note that, unlike quotas, you can't request an increase to a limit.

Limit	Value
Number of pipeline tasks per job	10,000
Input and output artifacts per pipeline task	100
Input and output artifacts per pipeline job	10,000
Maximum size of JSON payload containing output parameters and artifacts per pipeline task	131,072 bytes
Maximum running time for a pipeline task^**	7 days

^* Pipeline tasks running beyond this limit are cancelled.

Colab Enterprise quotas and limits

Colab Enterprise quotas and limits are listed separately. See Colab Enterprise quotas and limits.

Quota increases

If you want to increase any of your quotas for Vertex AI, you can use the Google Cloud console to request a quota increase.

Note: refer to Available locations and Region considerations and only apply for quota increase in the supported locations.

For more information about submitting a quota increase request, see the following sections of View and manage quotas:

• Request a quota adjustment

Quotas by region and model

View and edit the quotas in the Google Cloud console

To view and edit the quotas in the Google Cloud console, do the following:

1. Go to the Quotas and System Limits page.

Go to Quotas and System Limits

2. To adjust the quota, copy and paste the property aiplatform.googleapis.com/generate_content_requests_per_minute_per_project_per_base_model in the Filter. Press Enter.
3. Click the three dots at the end of the row, and select Edit quota.
4. Enter a new quota value in the pane, and click Submit request.

View the requests per minute (RPM) quotas by region and by model

By default, models 2.0 and later use Dynamic shared quota (DSQ).

Choose a region to view the quotas for each available model:

Increase the quotas

If you want to increase any of your quotas for Generative AI on Vertex AI, you can use the Google Cloud console to request a quota increase.

RAG Engine quotas

Preview

Some of the RAG features are Preview offerings, subject to the "Pre-GA Offerings Terms" of the Google Cloud Service Specific Terms. Pre-GA products and features may have limited support, and changes to Pre-GA products and features may not be compatible with other Pre-GA versions. For more information, see the launch stage descriptions. Further, by using the Gemini API on Vertex AI, you agree to the Generative AI Preview terms and conditions (Preview Terms).

For each service to perform retrieval-augmented generation (RAG) using RAG Engine, the following quotas apply, with the quota measured as requests per minute (RPM).

Service	Quota	Metric
RAG Engine data management APIs	60 RPM	VertexRagDataService requests per minute per region
RetrievalContexts API	1,500 RPM	VertexRagService retrieve requests per minute per region
base_model: textembedding-gecko	1,500 RPM	Online prediction requests per base model per minute per region per base_model An additional filter for you to specify is base_model: textembedding-gecko

The following limits apply:

Service	Limit	Metric
Concurrent ImportRagFiles requests	3 RPM	VertexRagService concurrent import requests per region
Maximum number of files per ImportRagFiles request	10,000	VertexRagService import rag files requests per region

For more rate limits and quotas, see Generative AI on Vertex AI rate limits.

Batch requests

The quotas and limits for batch inference jobs are the same across all regions.

Concurrent batch inference job limits for Gemini models

There are no predefined quota limits on batch inference for Gemini models. Instead, the batch service provides access to a large, shared pool of resources, dynamically allocated based on the model's real-time availability and demand across all customers for that model. When more customers are active and saturated the model's capacity, your batch requests might be queued for capacity.

Concurrent batch inference job quotas

The following table lists the quotas for the number of concurrent batch inference jobs, which don't apply to Gemini models:

Quota	Value
aiplatform.googleapis.com/textembedding_gecko_concurrent_batch_prediction_jobs	4

If the number of tasks submitted exceeds the allocated quota, the tasks are placed in a queue and processed when the quota capacity becomes available.

Custom-trained model quotas

The following quotas apply to Generative AI on Vertex AI tuned models for a given project and region:

Quota	Value
Restricted image training TPU V3 pod cores per region * supported Region - europe-west4	64
Restricted image training Nvidia A100 80GB GPUs per region * supported Region - us-central1 * supported Region - us-east4	8 2

* Tuning scenarios have accelerator reservations in specific regions. Quotas for tuning are supported and must be requested in specific regions.

Text embedding limits

Each text embedding model request can have up to 250 input texts (generating 1 embedding per input text) and 20,000 tokens per request. Only the first 2,048 tokens in each input text are used to compute the embeddings. For gemini-embedding-001, each request can only include a single input text. The quota for this model is listed under the name gemini-embedding.

Embed content input tokens per minute per base model

Unlike previous embedding models which were primarily limited by RPM quotas, the quota for the Gemini Embedding model limits the number of tokens that can be sent per minute per project.

Quota	Value
Embed content input tokens per minute	200000

Gen AI evaluation service service quotas

The Gen AI evaluation service uses gemini-2.0-flash as a default judge model for model-based metrics. A single evaluation request for a model-based metric might result in multiple underlying requests to the Gen AI evaluation service. Each model's quota is calculated on a per-project basis, which means that any requests directed to gemini-2.0-flash for model inference and model-based evaluation contribute to the quota. Quotas for the Gen AI evaluation service and the underlying judge model are shown in the following table:

Request quota	Default quota
Gen AI evaluation service requests per minute	1,000 requests per project per region
Online prediction requests per minute for base_model: gemini-2.0-flash	See Quotas by region and model.

If you receive an error related to quotas while using the Gen AI evaluation service, you might need to file a quota increase request. See View and manage quotas for more information.

Limit	Value
Gen AI evaluation service request timeout	60 seconds

When you use the Gen AI evaluation service for the first time in a new project, you might experience an initial setup delay up to two minutes. If your first request fails, wait a few minutes and then retry. Subsequent evaluation requests typically complete within 60 seconds.

The maximum input and output tokens for model-based metrics depend on the model used as the judge model. See Google models for a list of models.

Pipeline evaluation quotas

If you receive an error related to quotas while using the evaluation pipelines service, you might need to file a quota increase request. See View and manage quotas for more information. The evaluation pipelines service uses Vertex AI Pipelines to run PipelineJobs. See relevant quotas for Vertex AI Pipelines. The following are general quota recommendations:

Service	Quota	Recommendation
Vertex AI API	Concurrent LLM batch prediction jobs per region	Pointwise: 1 * num_concurrent_pipelines Pairwise: 2 * num_concurrent_pipelines
Vertex AI API	Evaluation requests per minute per region	1000 * num_concurrent_pipelines

Additionally, the relevant quota for model-based metrics depends on which judge model you use:

Tasks	Quota	Base model	Recommendation
summarization question_answering	Online prediction requests per base model per minute per region per base_model	text-bison	60 * num_concurrent_pipelines

Vertex AI Agent Engine

The following limits apply to Vertex AI Agent Engine for a given project in each region:

Description	Limit
Create, delete, or update Vertex AI Agent Engine per minute	10
Create, delete, or update Vertex AI Agent Engine sessions per minute	100
Create, delete, or update Vertex AI Agent Engine sessions per minute	100
Query or StreamQuery Vertex AI Agent Engine per minute	60
Append event to Vertex AI Agent Engine sessions per minute	100
Maximum number of Vertex AI Agent Engine resources	100
Create, delete, or update Vertex AI Agent Engine memory resources per minute	100
Get, list, or retrieve from Vertex AI Agent Engine Memory Bank per minute	300

Troubleshoot error code 429

To troubleshoot the 429 error, see Error code 429.

What's next

• Learn more about Generative AI on Vertex AI quotas and limits.

Send feedback