Google Cloud uses regions, subdivided into zones, to define the geographic location of physical computing resources. Google stores and processes your data only in the region you specify for all features of Vertex AI except for data labeling tasks and any feature in experimental or preview launch status.
Choosing your location
You can choose any supported location when you create a dataset, train a custom-trained model that doesn't use a managed dataset, or when you import an existing model. You should typically use the region closest to your physical location or the physical location of your intended users, but check that the Vertex AI feature you want to use is supported in your region. There is no global location.
For operations other than creating a dataset or importing a model, you must use the location of the resources you are operating on. For example, when you create a training pipeline that uses a managed dataset, you must use the region where the dataset is located.
Specifying the location using Google Cloud console
When you use Google Cloud console, you specify the location by using the location drop-down menu:
Specifying the location using the Vertex AI API
You specify the location for a Vertex AI API request by using the appropriate regional endpoint.
For example, to make a request in the europe-west4
region, use
the following endpoint:
https://europe-west4-aiplatform.googleapis.com
To make a request in the us-central1
region, use the following
endpoint:
https://us-central1-aiplatform.googleapis.com
When you specify a resource, you use the name of the resource's region as the
location. For example, a dataset in the us-central1
region would be specified
using the following path:
projects/PROJECT/locations/us-central1/datasets/DATASET_ID
See the list of supported service endpoints.
Available locations
Vertex AI is available in the following regions:
United States
- Columbus, Ohio (
us-east5
) - Dallas, Texas (
us-south1
) - Iowa (
us-central1
) - Las Vegas, Nevada (
us-west4
) - Los Angeles, California (
us-west2
) - Moncks Corner, South Carolina (
us-east1
) - Northern Virginia (
us-east4
) - Oregon (
us-west1
) - Salt Lake City, Utah (
us-west3
)
Canada
- Montréal (
northamerica-northeast1
) - Toronto (
northamerica-northeast2
)
South America
- Santiago, Chile (
southamerica-west1
) - São Paulo, Brazil (
southamerica-east1
)
Africa
- Johannesburg, South Africa (
africa-south1
)
Europe
- Belgium (
europe-west1
) - Finland (
europe-north1
) - Frankfurt, Germany (
europe-west3
) - London, United Kingdom (
europe-west2
) - Madrid, Spain (
europe-southwest1
) - Milan, Italy (
europe-west8
) - Netherlands (
europe-west4
) - Paris, France (
europe-west9
) - Turin, Italy (
europe-west12
) - Warsaw, Poland (
europe-central2
) - Zürich, Switzerland (
europe-west6
)
Asia Pacific
- Hong Kong, China (
asia-east2
) - Jakarta, Indonesia (
asia-southeast2
) - Melbourne, Australia (
australia-southeast2
) - Mumbai, India (
asia-south1
) - Osaka, Japan (
asia-northeast2
) - Seoul, Korea (
asia-northeast3
) - Singapore (
asia-southeast1
) - Sydney, Australia (
australia-southeast1
) - Taiwan (
asia-east1
) - Tokyo, Japan (
asia-northeast1
)
Middle East
- Dammam, Saudi Arabia (
me-central2
) - Doha, Qatar (
me-central1
) - Tel Aviv (
me-west1
)
For Generative AI locations, see Generative AI on Vertex AI locations.
Google Cloud also provides additional regions for products other than Vertex AI.
Feature availability
Some Vertex AI features are not available in all regions. The following table lists the features that are available in each region.
The following sortable table lets you select different options to see where Vertex AI features are available. For example, to see a list of regions where Vertex AI Feature Store is available in Europe, you can select Europe from the Select a location drop-down menu, and Vertex AI Feature Store from the Select a feature drop-down menu.
Region | Location | Features |
---|---|---|
asia-east1 | Changhua County, Taiwan, Asia Pacific |
|
africa-south1 | Johannesburg, South Africa, Africa |
|
asia-east2 | Hong Kong, Asia Pacific |
|
asia-northeast1 | Tokyo, Japan, Asia Pacific |
|
asia-northeast2 | Osaka, Japan, Asia Pacific |
|
asia-northeast3 | Seoul, South Korea, Asia Pacific |
|
asia-south1 | Mumbai, India, Asia Pacific |
|
asia-southeast1 | Jurong West, Singapore, Asia Pacific |
|
asia-southeast2 | Jakarta, Indonesia, Asia Pacific |
|
australia-southeast1 | Sydney, Australia, Asia Pacific |
|
australia-southeast2 | Melbourne, Australia, Asia Pacific |
|
europe-central2 | Warsaw, Poland, Europe |
|
europe-north1 | Hamina, Finland, Europe |
|
europe-southwest1 | Madrid, Spain, Europe |
|
europe-west1 | St. Ghislain, Belgium, Europe |
|
europe-west2 | London, England, Europe |
|
europe-west3 | Frankfurt, Germany, Europe |
|
europe-west4 | Eemshaven, Netherlands, Europe |
|
europe-west6 | Zürich, Switzerland, Europe |
|
europe-west8 | Milan, Italy, Europe |
|
europe-west9 | Paris, France, Europe |
|
europe-west12 | Turin, Italy, Europe |
|
me-central1 | Doha, Qatar, Middle East |
|
me-central2 | Damman, Saudi Arabia, Middle East |
|
me-west1 | Tel Aviv, Israel, Middle East |
|
northamerica-northeast1 | Montréal, Québec, North America |
|
northamerica-northeast2 | Toronto, Ontario, North America |
|
southamerica-east1 | Osasco, São Paulo, Brazil, South America |
|
southamerica-west1 | Santiago, Chile, South America |
|
us-central1 | Council Bluffs, Iowa, North America |
|
us-east1 | Moncks Corner, South Carolina, North America |
|
us-east4 | Ashburn, Virginia, North America |
|
us-east5 | Columbus, Ohio, North America |
|
us-south1 | Dallas, Texas, North America |
|
us-west1 | The Dalles, Oregon, North America |
|
us-west2 | Los Angeles, California, North America |
|
us-west3 | Salt Lake City, Utah, North America |
|
us-west4 | Las Vegas, Nevada, North America |
|
* Cells marked with asterisks represent regions where the service is available through the Vertex AI API but not in the Google Cloud console.
Vertex AI Workbench locations
See the following locations tables for Vertex AI Workbench:
Vertex AI Workbench instances locations
Vertex AI Workbench instances are available in the following zones.
Region | Location | Zones |
---|---|---|
asia-east1 * |
Changhua County, Taiwan, Asia Pacific |
asia-east1-a asia-east1-b asia-east1-c
|
asia-east2 |
Hong Kong, Asia Pacific |
asia-east2-a asia-east2-b asia-east2-c
|
asia-northeast1 |
Tokyo, Japan, Asia Pacific |
asia-northeast1-a asia-northeast1-b asia-northeast1-c
|
asia-northeast3 |
Seoul, South Korea, Asia Pacific |
asia-northeast3-a asia-northeast3-b asia-northeast3-c
|
asia-south1 |
Mumbai, India, Asia Pacific |
asia-south1-a asia-south1-b asia-south1-c
|
asia-southeast1 |
Jurong West, Singapore, Asia Pacific |
asia-southeast1-a asia-southeast1-b asia-southeast1-c
|
asia-southeast2 * |
Jakarta, Indonesia, Asia Pacific |
asia-southeast2-a asia-southeast2-b asia-southeast2-c
|
australia-southeast1 |
Sydney, Australia, Asia Pacific |
australia-southeast1-a australia-southeast1-b australia-southeast1-c
|
europe-central2 * |
Warsaw, Poland, Europe |
europe-central2-a europe-central2-b europe-central2-c
|
europe-west1 |
St. Ghislain, Belgium, Europe |
europe-west1-b europe-west1-c europe-west1-d
|
europe-west2 * |
London, England, Europe |
europe-west2-a europe-west2-b europe-west2-c
|
europe-west3 * |
Frankfurt, Germany, Europe |
europe-west3-a europe-west3-b europe-west3-c
|
europe-west4 † |
Eemshaven, Netherlands, Europe |
europe-west4-a europe-west4-b europe-west4-c
|
europe-west6 * |
Zürich, Switzerland, Europe |
europe-west6-a europe-west6-b europe-west6-c
|
me-west1 * |
Tel Aviv, Israel, Middle East |
me-west1-a me-west1-b me-west1-c
|
northamerica-northeast1 |
Montréal, Québec, North America |
northamerica-northeast1-a northamerica-northeast1-b northamerica-northeast1-c
|
northamerica-northeast2 * |
Toronto, Ontario, North America |
northamerica-northeast2-a northamerica-northeast2-b northamerica-northeast2-c
|
southamerica-east1 |
Osasco, São Paulo, Brazil, South America |
southamerica-east1-a southamerica-east1-b southamerica-east1-c
|
us-central1 |
Council Bluffs, Iowa, North America |
us-central1-a us-central1-b us-central1-c
|
us-east1 * |
Moncks Corner, South Carolina, North America |
us-east1-b us-east1-c us-east1-d
|
us-east4 * |
Ashburn, Virginia, North America |
us-east4-a us-east4-b us-east4-c
|
us-south1 * |
Dallas, Texas, North America |
us-south1-a us-south1-b us-south1-c
|
us-west1 |
The Dalles, Oregon, North America |
us-west1-a us-west1-b us-west1-c
|
us-west2 * |
Los Angeles, California, North America |
us-west2-a us-west2-b us-west2-c
|
us-west3 * |
Salt Lake City, Utah, North America |
us-west3-a us-west3-b us-west3-c
|
us-west4 |
Las Vegas, Nevada, North America |
us-west4-a us-west4-b us-west4-c
|
* Regions marked with asterisks don't support running or scheduling notebooks by using the Vertex AI Workbench executor.
† Regions marked with daggers don't support the ability to schedule a notebook run, but all other abilities of the Vertex AI Workbench executor are supported.
Managed notebooks regions
Managed notebooks are available in the following regions.
Region | Location |
---|---|
asia-east2 |
Hong Kong, Asia Pacific |
asia-northeast1 |
Tokyo, Japan, Asia Pacific |
asia-northeast3 |
Seoul, South Korea, Asia Pacific |
asia-south1 |
Mumbai, India, Asia Pacific |
asia-southeast1 |
Jurong West, Singapore, Asia Pacific |
australia-southeast1 |
Sydney, Australia, Asia Pacific |
europe-west1 |
St. Ghislain, Belgium, Europe |
europe-west4 † |
Eemshaven, Netherlands, Europe |
northamerica-northeast1 |
Montréal, Québec, North America |
southamerica-east1 |
Osasco, São Paulo, Brazil, South America |
us-central1 |
Council Bluffs, Iowa, North America |
us-east4 |
Ashburn, Virginia, North America |
us-west1 |
The Dalles, Oregon, North America |
us-west4 |
Las Vegas, Nevada, North America |
† Regions marked with daggers don't support the ability to schedule a notebook run, but all other abilities of the Vertex AI Workbench executor are supported.
User-managed notebooks locations
User-managed notebooks are available in the following zones.
Region | Location | Zones |
---|---|---|
asia-east1 |
Changhua County, Taiwan, Asia Pacific |
asia-east1-a asia-east1-b asia-east1-c
|
asia-east2 |
Hong Kong, Asia Pacific |
asia-east2-a asia-east2-b asia-east2-c
|
asia-northeast1 |
Tokyo, Japan, Asia Pacific |
asia-northeast1-a asia-northeast1-b asia-northeast1-c
|
asia-northeast3 |
Seoul, South Korea, Asia Pacific |
asia-northeast3-a asia-northeast3-b asia-northeast3-c
|
asia-south1 |
Mumbai, India, Asia Pacific |
asia-south1-a asia-south1-b asia-south1-c
|
asia-southeast1 |
Jurong West, Singapore, Asia Pacific |
asia-southeast1-a asia-southeast1-b asia-southeast1-c
|
asia-southeast2 |
Jakarta, Indonesia, Asia Pacific |
asia-southeast2-a asia-southeast2-b asia-southeast2-c
|
australia-southeast1 |
Sydney, Australia, Asia Pacific |
australia-southeast1-a australia-southeast1-b australia-southeast1-c
|
europe-central2 |
Warsaw, Poland, Europe |
europe-central2-a europe-central2-b europe-central2-c
|
europe-west1 |
St. Ghislain, Belgium, Europe |
europe-west1-b europe-west1-c europe-west1-d
|
europe-west2 |
London, England, Europe |
europe-west2-a europe-west2-b europe-west2-c
|
europe-west3 |
Frankfurt, Germany, Europe |
europe-west3-a europe-west3-b europe-west3-c
|
europe-west4 |
Eemshaven, Netherlands, Europe |
europe-west4-a europe-west4-b europe-west4-c
|
europe-west6 |
Zürich, Switzerland, Europe |
europe-west6-a europe-west6-b europe-west6-c
|
me-west1 |
Tel Aviv, Israel, Middle East |
me-west1-a me-west1-b me-west1-c
|
northamerica-northeast1 |
Montréal, Québec, North America |
northamerica-northeast1-a northamerica-northeast1-b northamerica-northeast1-c
|
northamerica-northeast2 |
Toronto, Ontario, North America |
northamerica-northeast2-a northamerica-northeast2-b northamerica-northeast2-c
|
southamerica-east1 |
Osasco, São Paulo, Brazil, South America |
southamerica-east1-a southamerica-east1-b southamerica-east1-c
|
us-central1 |
Council Bluffs, Iowa, North America |
us-central1-a us-central1-b us-central1-c
|
us-east1 |
Moncks Corner, South Carolina, North America |
us-east1-b us-east1-c us-east1-d
|
us-east4 |
Ashburn, Virginia, North America |
us-east4-a us-east4-b us-east4-c
|
us-south1 |
Dallas, Texas, North America |
us-south1-a us-south1-b us-south1-c
|
us-west1 |
The Dalles, Oregon, North America |
us-west1-a us-west1-b us-west1-c
|
us-west2 |
Los Angeles, California, North America |
us-west2-a us-west2-b us-west2-c
|
us-west3 |
Salt Lake City, Utah, North America |
us-west3-a us-west3-b us-west3-c
|
us-west4 |
Las Vegas, Nevada, North America |
us-west4-a us-west4-b us-west4-c
|
Region considerations
Using accelerators
Accelerators are available on a region basis. The following table lists all the available accelerators for each region.
You can search either by location or GPU model, or a combination of both.
Region | Location | Accelerators |
---|---|---|
asia-east1 |
Changhua County, Taiwan, Asia Pacific | L4†, P100, T4, TPU V2*, V100 |
asia-east2 |
Hong Kong, Asia Pacific | T4 |
asia-northeast1 |
Tokyo, Japan, Asia Pacific | A100 40GB†, L4†, T4, V100* |
asia-northeast3 |
Seoul, South Korea, Asia Pacific | A100 40GB, L4, T4, V100* |
asia-south1 |
Mumbai, India, Asia Pacific | L4, T4, V100* |
asia-southeast1 |
Jurong West, Singapore, Asia Pacific | A100 40GB, A100 80GB, H100†, L4, P4, T4 |
asia-southeast2 |
Jakarta, Indonesia, Asia Pacific | T4 |
australia-southeast1 |
Sydney, Australia, Asia Pacific | P4, P100, T4 |
europe-west1 |
St. Ghislain, Belgium, Europe | L4†, P100, T4 |
europe-west2 |
London, England, Europe | L4, T4 |
europe-west3 |
Frankfurt, Germany, Europe | T4* |
europe-west4 |
Eemshaven, Netherlands, Europe | A100 40GB, A100 80GB, H100, L4, P4, P100, T4, TPU V2*, TPU V2 Pod*, TPU V3*, TPU V3 Pod*, V100 |
northamerica-northeast1 |
Montréal, Québec, North America | P4, T4 |
southamerica-east1 |
Osasco, São Paulo, Brazil, South America | T4 |
us-central1 |
Council Bluffs, Iowa, North America | A100 40GB, A100 80GB, H100, L4, P4, P100, T4, TPU V2*, TPU V2 Pod*, TPU V3*, TPU v5e*, V100 |
us-east1 |
Moncks Corner, South Carolina, North America | A100 40GB*, L4, P100, T4, TPU V3*, V100* |
us-east4 |
Ashburn, Virginia, North America | A100 80GB, H100, L4, P4, T4 |
us-west1 |
The Dalles, Oregon, North America | L4, P100, T4, H100, TPU v5e, V100 |
us-west2 |
Los Angeles, California, North America | P4, T4 |
us-west4 |
Las Vegas, Nevada, North America | L4†, T4, TPU v5e* |
* Cells marked with asterisks represent regions where the specified accelerator is available for training but not for serving batch or online predictions.
† Cells marked with daggers represent regions where the specified accelerator is available for serving batch or online predictions but not for training.
If your job uses multiple types of GPUs, they must all be available in a single
zone in your region. For example, you can't run a job in
australia-southeast1
using NVIDIA Tesla P4 GPUs, NVIDIA Tesla T4 GPUs,
and NVIDIA Tesla P100 GPUs. While all of these GPUs are available for
jobs in australia-southeast1
, no single zone in that region provides all
three types of GPU. To learn more about the zone
availability of GPUs, see GPU availability by regions and
zones.
BigQuery location requirements
When you use a BigQuery table as a source for a managed tabular dataset or tabular prediction data, it must conform to the following location requirements:
Americas
BigQuery tables can be either multi-regional (
US
) or regional (us-central1
).BigQuery views must be regional (
us-central1
).If the table or view is not in the same project that the Vertex AI job is running in, make sure that Vertex AI has the correct roles.
Europe
BigQuery tables and views must be regional (
europe-west4
).Location: The region that your Vertex AI job runs in, such as
us-central1
,europe-west4
, orasia-east1
.If the table or view is not in the same project that the Vertex AI job is running in, make sure that Vertex AI has the correct roles.
Cloud Storage bucket requirements
Some Vertex AI tasks, such as importing data, use a Cloud Storage bucket.
We recommend that you use the following settings when creating a Cloud Storage bucket to use with Vertex AI:
- Location type:
Region
. - Location: The region where you are using Vertex AI; for
example,
us-central1
,europe-west4
, orasia-east1
. - Storage class:
Standard
.
These settings are not strict requirements, but using these settings often improves performance. For example, it's possible to use a bucket in a multi-region with Vertex AI, but loading data from a bucket in the same region as your Vertex AI resource might reduce latency.
- Location type:
If the bucket is not in the same project that the Vertex AI job is running in, make sure Vertex AI has the correct roles.
Restricting resource locations
Organization policy administrators can restrict the regions available where you can use Vertex AI by creating a resource locations constraint. Read about how a resource locations constraint applies to Vertex AI
Resource locations constraints don't apply to
DataLabelingJob
resources.
What's next
- Learn about Generative AI on Vertex AI locations.