Amazon Bedrock now supports OpenAI models in India
Amazon Bedrock now offers OpenAI’s GPT-5.6 models (Terra and Luna) in India with in-country inference, enabling data residency compliance while supporting cross-region scaling.
Amazon Web Services announced that Amazon Bedrock now supports OpenAI’s GPT-5.6 models, Terra and Luna, for customers in India. The models are accessible through India Geo cross-Region inference, which processes requests within Indian AWS Regions such as Asia Pacific (Mumbai) and Asia Pacific (Hyderabad). This ensures data residency compliance for organizations with regulatory requirements mandating in-country processing.
The new India Geo inference profiles, in.openai.gpt-5.6-terra and in.openai.gpt-5.6-luna, automatically route inference requests across multiple Indian AWS Regions to optimize throughput and scalability. Customers can scale model usage without managing capacity across Regions, while maintaining data processed within India’s geography.
The models operate on the bedrock-runtime endpoint and support standard APIs including Responses, Chat Completions, and Converse. Existing Bedrock account-level controls, such as model invocation logging to Amazon S3 or CloudWatch Logs, CloudWatch metrics, and cost tracking via AWS Cost Explorer and the Cost and Usage Report, remain applicable to these models.
OpenAI’s GPT-5.6 models with India cross-Region inference are available in the Asia Pacific (Mumbai) and Asia Pacific (Hyderabad) Regions. Customers can begin using the models by reviewing the model cards for GPT-5.6 (Terra and Luna) and consulting the Cross-Region inference section in the Amazon Bedrock User Guide.