OFICIAL AWS What's New

Amazon EC2 P6-B200 instances are now available in the AWS Asia Pacific (Hyderabad) Region

What happened
Based on AWS What's New · Sep 03, 2026

AWS has launched Amazon EC2 P6-B200 instances powered by NVIDIA Blackwell GPUs in the Asia Pacific (Hyderabad) Region, expanding access to high-performance AI training and inference capabilities.

Amazon EC2 P6-B200 instances are now available in the AWS Asia Pacific (Hyderabad) Region
AWS What's New — Amazon Web Services
Key points
·
Starting today, Amazon Elastic Compute Cloud (Amazon EC2) P6-B200 instances accelerated by NVIDIA Blackwell GPUs are available in the AWS Asia Pacific (Hyderabad) Region.
·
These instances offer up to 2x performance compared to P5en instances for AI training and inference.
·
P6-B200 instances are powered by the AWS Nitro System, so you can reliably and securely scale AI workloads within Amazon EC2 UltraClusters to tens of thousands of GPUs.
·
P6-B200 instances are now available in p6-b200.48xlarge size in the following AWS Regions: US West (Oregon), US East (N.
Key numbers
·
The new instances include 8 Blackwell GPUs with 1,440 GB of high-bandwidth GPU memory and a 60% increase in memory bandwidth compared to their predecessors.
·
2 terabits per second of Elastic Fabric Adapter (EFAv4) networking for improved data transfer efficiency.
·
48xlarge size across multiple AWS Regions, including the newly added Asia Pacific (Hyderabad) and existing locations such as US West (Oregon) and US East (N.

Amazon Web Services announced the availability of Amazon EC2 P6-B200 instances in the AWS Asia Pacific (Hyderabad) Region, featuring NVIDIA Blackwell GPUs. These instances are designed to enhance AI workloads by delivering up to twice the performance of P5en instances for both training and inference tasks. The new instances include 8 Blackwell GPUs with 1,440 GB of high-bandwidth GPU memory and a 60% increase in memory bandwidth compared to their predecessors. The instances also incorporate 5th Generation Intel Xeon processors (Emerald Rapids) and support up to 3.2 terabits per second of Elastic Fabric Adapter (EFAv4) networking for improved data transfer efficiency.

The P6-B200 instances are built on the AWS Nitro System, enabling secure and reliable scaling of AI workloads within Amazon EC2 UltraClusters to tens of thousands of GPUs. This infrastructure supports large-scale deployments while maintaining performance and security standards. The instances are now available in the p6-b200.48xlarge size across multiple AWS Regions, including the newly added Asia Pacific (Hyderabad) and existing locations such as US West (Oregon) and US East (N. Virginia, Ohio).

Organizations requiring high-performance AI capabilities can now leverage the P6-B200 instances in the Hyderabad Region to accelerate their machine learning and inference workloads. The instances are particularly suited for demanding applications such as generative AI, deep learning, and real-time data processing. AWS emphasizes the instances' compatibility with existing EC2 tools and frameworks, allowing for seamless integration into current workflows.

To facilitate adoption, AWS provides detailed documentation and resources for the P6-B200 instances, including specifications and best practices for deployment. Users can access these materials through the Amazon EC2 P6 instances page to evaluate performance, pricing, and technical requirements. The expansion into the Hyderabad Region reflects AWS's commitment to providing global access to advanced computing resources for AI-driven innovation.

Original source → Deals on Clipraptor.com →