Regional availability by models
Amazon Bedrock gives you three options so you can match the routing behavior of your inference calls to the scale, compliance, and cost requirements of your workload.
Process to enabling Bedrock models in GovCloud
Accessing Bedrock foundation models in AWS GovCloud (US) requires initiating the access request through the standard AWS account linked to your GovCloud account. You must first agree to the model's End User License Agreement (EULA) in a standard region (us-east-1 or us-west-2), then enable the model in your GovCloud account. You can do this in two ways:
-
Console: Sign in to your linked standard AWS account, open the Amazon Bedrock Chat/Text playground, choose the model, and run a prompt to establish the EULA.
-
AWS CLI: Run
aws bedrock list-foundation-modelsto get the model ID, thenaws bedrock list-foundation-model-agreement-offers --model-id <model-id>to get the offer token, and finallyaws bedrock create-foundation-model-agreement --model-id <model-id> --offer-token <offerToken>.
After completing either method, go to your GovCloud account and enable the model via the Model Access page. It may take a few minutes for entitlements to propagate. For the full walkthrough, see Process to enabling Bedrock models in GovCloud
-
In-Region: Your requests never leave the AWS Region you specify. Use this when regulations require strict single-Region data processing.
-
Geographic (Geo): Bedrock routes your request to a Region within a defined geography (US, EU, Japan, or Australia), keeping data within that geography. Use this when you have data residency requirements tied to a geography rather than a single Region.
-
Global: Bedrock routes your request to a supported commercial Region worldwide. For some models, global cross-Region inference is priced lower per token than geographic cross-Region inference. Use this when you have no data residency constraints.
Inference options at a glance
| In-Region | Geographic (Geo) Cross-Region | Global Cross-Region | |
|---|---|---|---|
| How it works | Request is processed entirely within the single AWS Region you specify | Bedrock routes the request to a Region within a defined geography (US, EU, APAC, JP, AU) | Bedrock routes the request to any supported commercial Region worldwide |
| Data residency | Strictly within one Region | Within geographic boundaries (e.g., all EU Regions); prompts and outputs may move within the geography but not outside it | No geographic restrictions; data may be processed in any commercial Region |
| Request routing | Processed in the Region you specify; subject to per-Region service quotas | Routed to a Region within the geography | Routed to a supported commercial Region worldwide |
| Pricing | Standard on-demand pricing for that Region | Priced at source Region rates; no surcharge for cross-Region routing | Priced at source Region rates; no surcharge for cross-Region routing. For some models, the per-token price is lower than geographic cross-Region inference |
| modelId format | Direct model ID: anthropic.claude-3-5-sonnet-20241022-v2:0 |
Geography prefix + model ID: us.anthropic.claude-3-5-sonnet-20241022-v2:0 |
Global prefix + model ID: global.anthropic.claude-3-5-sonnet-20241022-v2:0 |
| Best for | Strict single-Region compliance; Provisioned Throughput workloads | Data residency regulations scoped to a geography (e.g., GDPR in EU, data sovereignty requirements) | Cost efficiency with no data residency constraints |
Now, let us look at Regional availability across all the models supported by Amazon Bedrock.
AI21 Labs
| Region | In-Region | Geo | Global |
|---|---|---|---|
us-east-1 (N. Virginia) |
|
|
|
| Region | In-Region | Geo | Global |
|---|---|---|---|
us-east-1 (N. Virginia) |
|
|
|
Amazon
| Region | In-Region | Geo | Global |
|---|---|---|---|
us-east-1 (N. Virginia) |
|
|
|
us-west-2 (Oregon) |
|
|
|
eu-north-1 (Stockholm) |
|
|
|
ap-northeast-1 (Tokyo) |
|
|
|
| Region | In-Region | Geo | Global |
|---|---|---|---|
us-east-1 (N. Virginia) |
|
|
|
us-east-2 (Ohio) |
|
|
|
us-west-1 (N. California) |
|
|
|
us-west-2 (Oregon) |
|
|
|
ca-central-1 (Canada) |
|
|
|
ca-west-1 (Calgary) |
|
|
|
eu-central-1 (Frankfurt) |
|
|
|
eu-north-1 (Stockholm) |
|
|
|
eu-south-1 (Milan) |
|
|
|
eu-south-2 (Spain) |
|
|
|
eu-west-1 (Ireland) |
|
|
|
eu-west-2 (London) |
|
|
|
eu-west-3 (Paris) |
|
|
|
ap-east-2 (Taipei) |
|
|
|
ap-northeast-1 (Tokyo) |
|
|
|
ap-northeast-2 (Seoul) |
|
|
|
ap-south-1 (Mumbai) |
|
|
|
ap-southeast-1 (Singapore) |
|
|
|
ap-southeast-2 (Sydney) |
|
|
|
ap-southeast-3 (Jakarta) |
|
|
|
ap-southeast-4 (Melbourne) |
|
|
|
ap-southeast-5 (Malaysia) |
|
|
|
ap-southeast-6 (New Zealand) |
|
|
|
ap-southeast-7 (Thailand) |
|
|
|
il-central-1 (Tel Aviv) |
|
|
|
me-central-1 (UAE) |
|
|
|
| Region | In-Region | Geo | Global |
|---|---|---|---|
us-east-1 (N. Virginia) |
|
|
|
us-gov-west-1 (GovCloud) |
|
|
|
| Region | In-Region | Geo | Global |
|---|---|---|---|
us-east-1 (N. Virginia) |
|
|
|