Kia ora!<\/em><\/p>\n

Clients in New Zealand have been asking for entry to basis fashions (FMs) on Amazon Bedrock<\/a> from their native AWS Area.<\/p>\n

Right this moment, we\u2019re excited to announce that Amazon Bedrock is now accessible within the Asia Pacific (New Zealand) Area (ap-southeast-6). Clients in New Zealand can now entry Anthropic Claude<\/a> fashions (Claude Opus 4.5, Opus 4.6, Sonnet 4.5, Sonnet 4.6, and Haiku 4.5) and Amazon (Nova 2 Lite) fashions straight within the Auckland Area with cross area inference.<\/p>\n

On this publish, we discover how cross-Area inference works from the New Zealand Area, the fashions accessible by way of geographic and international routing, and the way to get began along with your first API name. We cowl three key areas:<\/p>\n

\n
How Amazon Bedrock in ap-southeast-6 makes use of cross-Area inference to provide you entry to FMs, with the ANZ geographic routing configuration throughout Auckland, Sydney, and Melbourne<\/li>\n
Supported fashions, IAM permissions, and making your first inference name from the Auckland Area<\/li>\n
Quota administration, safety issues, and selecting between geographic and international cross-Area inference to your workloads<\/li>\n<\/ul>\n
Understanding cross-Area inference<\/h2>\n
Cross-Area inference is an Amazon Bedrock functionality that distributes inference processing throughout a number of AWS Areas that will help you obtain greater throughput at scale.<\/p>\n
Whenever you invoke a cross-Area inference profile<\/a>, Amazon Bedrock routes your request from the supply Area<\/strong> (the place you provoke the API name) to a vacation spot Area<\/strong> (the place inference processing happens). All knowledge transmitted throughout cross-Area operations stays on the AWS community and doesn\u2019t traverse the general public web, and knowledge is encrypted in transit between AWS Areas. All cross-Area inference requests are logged in AWS CloudTrail<\/a> in your supply Area. For those who configure mannequin invocation logging<\/a>, logs are revealed to Amazon CloudWatch Logs<\/a> or Amazon Easy Storage Service (Amazon S3)<\/a> ~~<\/s>in the identical Area.<\/p>\n~~
~~Amazon Bedrock gives two kinds of cross-Area inference profiles:<\/p>\n~~
\n
Geographic cross-Area inference<\/strong> \u2013 Routes requests inside a selected geographic boundary. For instance, with AU profile, and Auckland as your supply Area, requests path to Auckland, Sydney, and Melbourne. Designed for organizations with knowledge residency necessities that want inference processing to remain inside Australia and New Zealand.<\/li>\n
World cross-Area inference<\/strong> \u2013 Routes requests to supported business AWS Areas worldwide, offering the very best accessible throughput. Designed for organizations with out strict knowledge residency necessities.<\/li>\n<\/ul>\n
What\u2019s new: New Zealand as a supply Area for cross-Area inference<\/h2>\n
With this launch, Auckland (ap-southeast-6<\/code>) turns into a brand new supply Area for each AU geographic and international cross-Area inference on Amazon Bedrock. This implies which you could now make Amazon Bedrock API calls from the New Zealand Area, and cross-Area inference routes your requests to vacation spot Areas the place the FMs course of inference.<\/p>\n
AU geographic cross-Area inference configuration<\/h3>\nThe AU cross-Area profile now spans three Areas throughout Australia and New Zealand. The next desk particulars the supply and vacation spot Area routing.<\/p>\n\n\n\n\n\n\nSupply Area<\/strong><\/td>\n Vacation spot Areas<\/strong><\/td>\n Description<\/strong><\/td>\n<\/tr>\n Auckland (ap-southeast-6<\/code>)<\/strong><\/td>\n ap-southeast-6<\/code>, ap-southeast-2<\/code>, ap-southeast-4<\/code><\/td>\n New \u2013 Requests from Auckland may be routed to Sydney, Melbourne, or Auckland<\/td>\n<\/tr>\n Sydney (ap-southeast-2<\/code>)<\/strong><\/td>\n ap-southeast-2<\/code>, ap-southeast-4<\/code><\/td>\n Requests from Sydney may be routed to Sydney or Melbourne<\/td>\n<\/tr>\n Melbourne (ap-southeast-4<\/code>)<\/strong><\/td>\n ap-southeast-2<\/code>, ap-southeast-4<\/code><\/td>\n Requests from Melbourne may be routed to Sydney or Melbourne<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\nThere are two essential particulars to notice:<\/p>\n \nThe AU cross-Area inference profiles for Sydney and Melbourne proceed to route between Sydney and Melbourne solely. The addition of Auckland doesn\u2019t change the vacation spot Areas for present Australian supply Area configurations.<\/li>\n Requests originating from Auckland may be served regionally or routed to both Australian Area, offering three vacation spot Areas for capability distribution.<\/li>\n<\/ul>\nWorld cross-Area inference from New Zealand<\/h3>\nFor organizations with out strict knowledge residency necessities, international cross-Area inference from the Auckland Area gives entry to inference capability throughout all supported AWS business Areas worldwide. World cross-Area inference delivers two key benefits:<\/p>\n \nIncreased throughput<\/strong> \u2014 Clever routing distributes site visitors dynamically throughout all supported business Areas, decreasing the chance of throttling throughout site visitors spikes<\/li>\n Constructed-in resilience<\/strong> \u2014 Requests are routinely routed to Areas with accessible capability, serving to your purposes preserve operational continuity as demand patterns shift<\/li>\n<\/ul>\nGetting began<\/h2>\n Supported fashions and inference profile IDs<\/h3>\nCross-Area inference from the New Zealand Area helps basis fashions from a number of suppliers throughout each AU geographic and international cross-Area inference profiles. The next desk reveals examples of the most recent fashions accessible at launch.<\/p>\n\n\n\n\n\nCross-Area inference sort<\/strong><\/td>\n Instance fashions<\/strong><\/td>\n<\/tr>\n AU geographic cross-Area inference<\/strong><\/td>\n Anthropic Claude Opus 4.6, Claude Sonnet 4.6, Claude Sonnet 4.5, Claude Haiku 4.5<\/td>\n<\/tr>\n World cross-Area inference<\/strong><\/td>\n Anthropic Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\nAU geographic cross-Area inference at present helps Anthropic Claude fashions, protecting inference processing throughout the ANZ geography. World cross-Area inference gives entry to a broader set of basis fashions from a number of suppliers. To make use of a cross-Area inference profile, substitute the foundational mannequin ID with the geographic (au.) or international (international.) prefix \u2014 for instance, anthropic.claude-sonnet-4-6<\/em><\/code> turns into au<\/em><\/strong>.anthropic.claude-sonnet-4-6<\/em><\/code> or international<\/em><\/strong>.anthropic.claude-sonnet-4-6<\/em><\/code>.<\/p>\n For the entire and up-to-date checklist of supported fashions and inference profile IDs, seek advice from Supported Areas and fashions for inference profiles<\/a>.<\/p>\n Cross-Area inference profiles work with the InvokeModel<\/code>, InvokeModelWithResponseStream<\/code>, Converse<\/code>, and ConverseStream<\/code> APIs. The Converse<\/code> API gives a constant request and response format throughout completely different basis fashions, making it easy to change between fashions with out rewriting integration code.<\/p>\n Configure IAM permissions<\/h3>\nTo invoke basis fashions by way of AU geographic cross-Area inference from the Auckland Area, your AWS Id and Entry Administration (IAM)<\/a> coverage wants two statements:<\/p>\n \nGranting entry to the inference profile within the supply Area<\/li>\nGranting entry to the inspiration mannequin in all vacation spot Areas listed within the AU cross-Area inference profile.<\/li>\n<\/ul>\nThe next IAM coverage instance grants entry to invoke Anthropic Claude Sonnet 4.6 by way of AU geographic cross-Area inference from Auckland. Substitute <\/code> along with your AWS account ID.<\/p>\n\n{ \n \"Model\": \"2012-10-17\", \n \"Assertion\": [ \n { \n \"Sid\": \"AllowAuCrisInferenceProfile\", \n \"Effect\": \"Allow\", \n \"Action\": [ \n \"bedrock:InvokeModel\", \n \"bedrock:InvokeModelWithResponseStream\" \n ], \n \"Useful resource\": \"arn:aws:bedrock:ap-southeast-6::inference-profile\/au.anthropic.claude-sonnet-4-6\" \n }, \n { \n \"Sid\": \"AllowFoundationModelViaAuCris\", \n \"Impact\": \"Enable\", \n \"Motion\": [ \n \"bedrock:InvokeModel\", \n \"bedrock:InvokeModelWithResponseStream\" \n ], \n \"Useful resource\": [ \n \"arn:aws:bedrock:ap-southeast-2::foundation-model\/anthropic.claude-sonnet-4-6\", \n \"arn:aws:bedrock:ap-southeast-4::foundation-model\/anthropic.claude-sonnet-4-6\", \n \"arn:aws:bedrock:ap-southeast-6::foundation-model\/anthropic.claude-sonnet-4-6\" \n ], \n \"Situation\": { \n \"StringLike\": { \n \"bedrock:InferenceProfileArn\": \"arn:aws:bedrock:ap-southeast-6::inference-profile\/au.anthropic.claude-sonnet-4-6\" \n } \n } \n } \n ] \n} <\/account_id><\/account_id><\/code><\/pre>\n<\/p><\/div>\nThe primary assertion permits invoking the AU inference profile from the Auckland supply Area. The second assertion permits the FM to be invoked within the three vacation spot Areas, however solely when the request is routed by way of the AU inference profile. This follows the precept of least privilege by stopping direct mannequin invocation in these Areas.<\/p>\nThe identical two-statement sample applies to any mannequin within the AU cross-Area inference profile\u2014substitute the mannequin ID within the useful resource ARNs. For international cross-Area inference IAM insurance policies, service management insurance policies (SCP)<\/a> configurations, and superior safety patterns, seek advice from Securing Amazon Bedrock cross-Area inference: Geographic and international<\/a>.<\/p>\n Safety and compliance issues<\/h2>\nCross-Area inference is designed with safety at its core. All requests journey solely over the AWS World Community with end-to-end encryption, and your knowledge at relaxation stays within the supply Area.<\/p>\n For organizations utilizing SCPs to limit entry to particular AWS Areas, word the next when calling from the Auckland supply Area (ap-southeast-6<\/code>):<\/p>\n\nAU geographic cross-Area inference<\/strong> requires permitting ap-southeast-2<\/code>, ap-southeast-4<\/code>, and ap-southeast-6<\/code> for Amazon Bedrock actions in your SCPs, as a result of Auckland\u2019s AU profile routes to all three ANZ Areas.<\/li>\nWorld cross-Area inference<\/strong> moreover requires permitting unspecified<\/em> as a Area worth for Amazon Bedrock actions, as a result of vacation spot Areas are decided dynamically.<\/li>\n<\/ul>\nThe next instance SCP restricts providers to the Auckland Area, with exceptions for Amazon Bedrock and international providers like IAM. It limits Amazon Bedrock to the three ANZ Areas, and requires that Amazon Bedrock entry in Sydney and Melbourne undergo cross-Area inference profiles somewhat than direct mannequin invocation:<\/p>\n\n{ \n \"Model\": \"2012-10-17\", \n \"Assertion\": [ \n { \n \"Sid\": \"DenyNonBedrockServicesOutsideAuckland\", \n \"Effect\": \"Deny\", \n \"NotAction\": [ \n \"bedrock:*\", \n \"iam:*\", \n \"organizations:*\", \n \"support:*\" \n ], \n \"Useful resource\": \"*\", \n \"Situation\": { \n \"StringNotEquals\": { \n \"aws:RequestedRegion\": [\"ap-southeast-6\"] \n } \n } \n }, \n { \n \"Sid\": \"DenyBedrockOutsideANZRegions\", \n \"Impact\": \"Deny\", \n \"Motion\": \"bedrock:*\", \n \"Useful resource\": \"*\", \n \"Situation\": { \n \"StringNotEquals\": { \n \"aws:RequestedRegion\": [ \n \"ap-southeast-2\", \n \"ap-southeast-4\", \n \"ap-southeast-6\" \n ] \n } \n } \n }, \n { \n \"Sid\": \"DenyDirectBedrockInDestinationRegions\", \n \"Impact\": \"Deny\", \n \"Motion\": \"bedrock:*\", \n \"Useful resource\": \"*\", \n \"Situation\": { \n \"StringEquals\": { \n \"aws:RequestedRegion\": [ \n \"ap-southeast-2\", \n \"ap-southeast-4\" \n ] \n }, \n \"Null\": { \n \"bedrock:InferenceProfileArn\": \"true\" \n } \n } \n } \n ] \n} <\/code><\/pre>\n<\/p><\/div>\nWithin the earlier coverage:<\/p>\n\nThe primary assertion restricts all providers to the Auckland Area, aside from Amazon Bedrock and international providers resembling IAM, AWS Organizations, and AWS Assist that function independently of Area restrictions.<\/li>\n The second assertion restricts Amazon Bedrock to the three ANZ Areas, which is important for AU cross-Area inference to route requests from Auckland to Sydney and Melbourne.<\/li>\nThe third assertion makes use of the Null situation on bedrock:InferenceProfileArn<\/strong> to disclaim any Amazon Bedrock request in Sydney or Melbourne that\u2019s not routed by way of a cross-Area inference profile. This prevents direct mannequin invocation in vacation spot Areas whereas permitting cross-Area inference to perform usually.<\/li>\n<\/ul>\nFor detailed SCP configuration examples, international cross-Area inference IAM insurance policies, disabling particular cross-Area inference sorts, and AWS Management Tower<\/a> integration steering, seek advice from Securing Amazon Bedrock cross-Area inference: Geographic and international<\/a>.<\/p>\n Auditing and monitoring<\/h2>\nAWS CloudTrail<\/a> logs all cross-Area inference calls within the supply Area. The additionalEventData.inferenceRegion<\/em> subject information the place every request was processed, so you may audit precisely the place inference occurred:<\/p>\n \n{ \n \"eventSource\": \"bedrock.amazonaws.com\", \n \"eventName\": \"InvokeModel\", \n \"awsRegion\": \"ap-southeast-6\", \n \"requestParameters\": { \n \"modelId\": \"au.anthropic.claude-sonnet-4-6\" \n }, \n \"additionalEventData\": { \n \"inferenceRegion\": \"ap-southeast-2\" \n } \n} <\/code><\/pre>\n<\/p><\/div>\nFor real-time operational monitoring, Amazon CloudWatch<\/a> gives metrics for cross-Area inference requests in your supply Area. Key metrics embrace:<\/p>\n \nInvocationCount<\/strong> \u2014 Whole variety of inference requests<\/li>\n InvocationLatency<\/strong> \u2014 Finish-to-end response time together with cross-Area routing<\/li>\n InvocationClientErrors<\/strong> \u2014 Failed requests, together with throttling (spikes point out that you just\u2019re approaching quota limits)<\/li>\nInputTokenCount<\/strong> and OutputTokenCount<\/strong> \u2014 Token consumption for quota monitoring<\/li>\n<\/ul>\nQuota administration<\/h2>\nAmazon Bedrock service quotas<\/a> are managed on the supply Area degree. Quota will increase requested from the Auckland Area (ap-southeast-6) apply solely to requests originating from Auckland.<\/p>\n Quotas are measured in two dimensions:<\/p>\n \nTokens per minute (TPM)<\/strong> \u2014 The utmost variety of tokens (enter + output) processed per minute<\/li>\nRequests per minute (RPM)<\/strong> \u2014 The utmost variety of inference requests per minute<\/li>\n<\/ul>\nWhen calculating your required quota, account for the token burndown price<\/strong>. For Anthropic Claude Opus 4.6, Sonnet 4.6, and Sonnet 4.5, output tokens eat 5 instances extra quota than enter tokens (5:1 burndown price). For Claude Haiku 4.5 and Amazon Nova fashions, the burndown price is 1:1.<\/p>\n Quota consumption formulation:<\/strong><\/p>\n Quota consumption = Enter tokens + Cache write tokens + (Output tokens x Burndown price)<\/em><\/p>\nTo request quota will increase, navigate to the AWS Service Quotas console<\/a> in your supply Area, choose Amazon Bedrock, and seek for the related cross-Area inference quota to your mannequin.<\/p>\n Conclusion<\/h2>\nOn this publish, we launched cross-Area inference assist from the New Zealand Area on Amazon Bedrock. Clients in New Zealand can now make API calls from Auckland and entry basis fashions by way of geographic and international cross-Area inference profiles.Key takeaways:<\/p>\n\nAuckland is now a supply Area for cross-Area inference<\/strong> \u2014 New Zealand prospects could make Amazon Bedrock API calls from their native Area, with logs and configurations staying in Auckland.<\/li>\n AU geographic cross-Area inference retains knowledge inside ANZ<\/strong> \u2014 Inference requests from Auckland route to a few locations (Auckland, Sydney, and Melbourne), offering Anthropic Claude fashions throughout the ANZ geographic boundary.<\/li>\n World cross-Area inference expands mannequin entry<\/strong> \u2014 offering the very best accessible throughput by routing requests to supported business AWS Areas worldwide.<\/li>\nPresent Australian routing is unchanged<\/strong> \u2014 Sydney and Melbourne supply Areas proceed to route between one another solely.<\/li>\n<\/ul>\nYou may get began with cross-Area inference from the New Zealand Area with the next steps:<\/p>\n\nCheck in to the Amazon Bedrock console<\/a> within the Auckland Area (ap-southeast-6<\/code>).<\/li>\n Configure IAM and SCP permissions utilizing the coverage instance on this publish.<\/li>\n Make your first API name utilizing the au. inference profile ID.<\/li>\n Request quota will increase by way of the Service Quotas console<\/a> based mostly in your anticipated workload.<\/li>\n<\/ul>\nFor extra data, seek advice from:<\/p>\n \nConcerning the authors<\/h2>\n\n\n\n \n <\/div>\nZohreh Norouzi<\/h3>\nZohreh Norouzi is a Safety Options Architect at Amazon Internet Companies. She helps prospects make good safety selections and speed up their journey to the AWS Cloud. She has been actively concerned in generative AI safety initiatives throughout APJ, utilizing her experience to assist prospects construct safe generative AI options at scale.<\/p>\n<\/p><\/div>\n \n\n \n <\/div>\nMelanie Li<\/h3>\nMelanie Li, PhD, is a Senior Generative AI Specialist Options Architect at AWS based mostly in Sydney, Australia, the place her focus is on working with prospects to construct options utilizing state-of-the-art AI\/ML instruments. She has been actively concerned in a number of generative AI initiatives throughout APJ, harnessing the facility of LLMs. Previous to becoming a member of AWS, Dr. Li held knowledge science roles within the monetary and retail industries.<\/p>\n<\/p><\/div>\n \n\n \n <\/div>\nSaurabh Trikande<\/h3>\nSaurabh Trikande is a Senior Product Supervisor for Amazon Bedrock and Amazon SageMaker Inference. He’s keen about working with prospects and companions, motivated by the objective of democratizing AI. He focuses on core challenges associated to deploying advanced AI purposes, inference with multi-tenant fashions, price optimizations, and making the deployment of generative AI fashions extra accessible. In his spare time, Saurabh enjoys mountaineering, studying about progressive applied sciences, following TechCrunch, and spending time together with his household.<\/p>\n<\/p><\/div>\n \n\n \n <\/div>\nJames Zheng<\/h3>\nJames Zheng is a Software program Improvement Supervisor at Amazon Internet Companies.<\/p>\n<\/p><\/div>\n \n\n \n <\/div>\nWilliam Yap<\/h3>\nWilliam Yap is Principal Product Supervisor for Amazon Bedrock.<\/p>\n<\/p><\/div>\n \n\n \n <\/div>\nJulia Bodia<\/h3>\nJulia Bodia is Principal Product Supervisor for Amazon Bedrock.<\/p>\n<\/p><\/div>\n<\/footer>\n \n <\/div>\n\n","protected":false},"excerpt":{"rendered":" Kia ora! Clients in New Zealand have been asking for entry to basis fashions (FMs) on Amazon Bedrock from their native AWS Area. Right this moment, we\u2019re excited to announce that Amazon Bedrock is now accessible within the Asia Pacific (New Zealand) Area (ap-southeast-6). Clients in New Zealand can now entry Anthropic Claude fashions (Claude […]<\/p>\n","protected":false},"author":2,"featured_media":13166,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[55],"tags":[387,6465,1289,80,1028,8407,733,8408],"class_list":["post-13164","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-machine-learning","tag-amazon","tag-asia","tag-bedrock","tag-generative","tag-inference","tag-pacific","tag-run","tag-zealand"],"_links":{"self":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/13164","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=13164"}],"version-history":[{"count":1,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/13164\/revisions"}],"predecessor-version":[{"id":13165,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/posts\/13164\/revisions\/13165"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=\/wp\/v2\/media\/13166"}],"wp:attachment":[{"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=13164"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=13164"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/techtrendfeed.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=13164"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}

Understanding cross-Area inference<\/h2>\nCross-Area inference is an Amazon Bedrock functionality that distributes inference processing throughout a number of AWS Areas that will help you obtain greater throughput at scale.<\/p>\n

Getting began<\/h2>\n