Introducing OpenAI models on Amazon Bedrock for in-country inferencing in India
Amazon Bedrock now supports the OpenAI GPT-5.6 models, Terra and Luna, in India with India geographic cross-Region inference. If you have local data processing requirements, you can now use these models at scale while Amazon Bedrock keeps inference requests and data within India.
Amazon Bedrock now offers access to the OpenAI GPT-5.6 models, Terra and Luna, in the Indian Regions of Mumbai and Hyderabad. This enables businesses with data processing needs in India, particularly in finance, healthcare and government, to utilize these advanced models while adhering to data residency regulations. The models support a 1-million-token context window and can handle both text and image inputs, generating text outputs.
They are designed to process extensive documents, large code bases, and mixed text-and-image content within a single request, eliminating the need for local servers. The processing remains within India, with inference requests and data routed within the country. There are two profiles for each model – one for Terra and one for Luna.
These inference profiles ensure that all routing and billing are tracked against the source Region, regardless of where the request is handled. Amazon Bedrock's global cross-Region inference feature also allows requests to be routed to other AWS Regions worldwide, maximizing capacity, but the India-profiled models keep all processing within India.
The India geographic profile ensures that data is encrypted in transit, and Amazon Bedrock follows a zero data retention (ZDR) model, meaning it does not store model inputs or outputs by default, except for certain flagged content for abuse detection.
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.
