Amazon Bedrock expands API support and introduces Cross Region Inferencing for OpenAI models

Amazon Bedrock Updates

Amazon Bedrock now supports the latest OpenAI GPT-5.6 models (Sol, Terra, and Luna) on the bedrock-runtime endpoint, with support for the Responses, Converse, and Chat Completions APIs. Cross-Region inference is also available, providing higher throughput and lower costs.

Cross-Region Inference

Cross-Region inference automatically routes inference requests across multiple AWS Regions to increase throughput. Geo cross-region inference routes requests within a predefined geography, including new US Geo (US CRIS) support. Global cross-region inference serves requests from any commercial AWS Region, offering the broadest access to Bedrock capacity and lower costs.

API Support

OpenAI GPT models can now be used with the Responses API, Chat Completions API, and the Converse API on the bedrock-runtime endpoint. These APIs run with the same account-level controls as other models on Bedrock, including logging, metrics, and cost attribution.

What to do

• Review the model cards for GPT 5.6 (Sol, Terra, and Luna) in the Amazon Bedrock User Guide.
• Utilize the new APIs for higher throughput and lower costs.
• Monitor usage and costs through Amazon CloudWatch and AWS Cost Explorer.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.