Accessing OpenAI models on Amazon Bedrock from Australia with global cross-Region inference
Australian teams can now access OpenAI GPT-5.6 Sol, Terra, and Luna models on Amazon Bedrock with global cross-Region inference from the Asia Pacific (Sydney) and Asia Pacific (Melbourne) Regions. This post shows how to invoke the models, use prompt caching, set up Codex with OpenID Connect authentication, and monitor usage with Amazon CloudWatch.
Australian developers can now utilize OpenAI models like GPT-5.6 Sol, Terra, and Luna via Amazon Bedrock with cross-Region inference in Australia. By directing requests through the Asia Pacific (Sydney) or Melbourne AWS regions, applications gain access to a larger capacity pool. The GPT-5.6 Sol model excels at complex tasks like reasoning and coding, Terra balances performance and cost, while Luna offers rapid, budget-friendly inference for high-volume, low-latency workloads.
Both models accept text and images, generating text and supporting up to 1 million tokens of context. To use these models, invoke the Amazon Bedrock Runtime endpoint from Sydney or Melbourne, which routes requests to a suitable commercial AWS region for processing. This setup eliminates the need for applications to manage destination region routing.
Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
This story
This is one outlet's version. Read the fullest account.
