DigestAI news desk

Cut through the AI noise.

Enterprise & Industry9 min read

Amazon Bedrock adds global cross‑Region inference for OpenAI GPT‑6 models

Amazon Bedrock now supports global cross‑Region inference for OpenAI GPT‑6 Sol, Luna, and Astra across five Asia Pacific regions. The post explains how to enable source regions, configure IAM policies and service control policies, and set a global inference profile ID in the model parameter.

1 source primary source

Key points

  • Amazon Bedrock now supports global cross‑Region inference for OpenAI GPT‑6 Sol, Luna, and Astra across five Asia Pacific regions.
  • Users must enable source regions, configure IAM policies with specific statements, and set a global inference profile ID in the model parameter.
  • Quota is measured in tokens per minute; each output token consumes 10 tokens of quota, and billing stays in the source region.

Users must activate the source region (Singapore is enabled by default; Jakarta, Malaysia, Thailand, and Taipei are opt‑in) and install the required SDKs. The guide details the IAM policy statements needed to invoke the profile and how to adjust quotas measured in tokens per minute.

Quota rules state that each output token consumes ten tokens of quota, and billing remains in the source region. CloudTrail and CloudWatch logs stay in the source region, while the model runs in the destination region selected by Bedrock.

Model pages: GPT-6 Sol → · GPT-6 Luna → · GPT-6 Astra →

Full story from AWS Machine Learning Blog · by Traci Lim primary sourceOpen source ↗

Accessing OpenAI GPT models on Amazon Bedrock with global cross-Region inference in Thailand, Malaysia, Singapore, Indonesia, and Taiwan

AWS Machine Learning Blog · 12 October 2026

Loading the full article…

This text was published by AWS Machine Learning Blog and written by Traci Lim. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Enterprise & Industry

All →

Related stories