Beam, the first open weight model offered by US-based Reflection, is now available in Amazon SageMaker JumpStart, the model hub in Amazon SageMaker AI. According to Beam, they operate at the frontier of open weight models in its class, with strong performance across reasoning, coding, and agentic benchmarks. With it, customers can now build advanced coding agents and automated workflows on a frontier open weight model while keeping control of their data and infrastructure and adapting the model to their business. Beam runs alongside other models that customers already use in SageMaker AI and scales to meet production demand with the same controls, audit trails, and monitoring built into every SageMaker AI deployment. Additionally, Beam was ported and optimized for AWS Trainium3, giving customers a high-performance, cost-efficient option for deploying and scaling the model from day one. “Reflection is delivering frontier AI that developers can actually control, not just rent through an API. Bringing Beam to SageMaker AI puts that capability in front of millions of developers on infrastructure they already trust, running in their own AWS account, on their own data, fully in their control," said Misha Laskin, co-founder and CEO, Reflection. Engineering teams can use Beam to resolve software issues, generate and review code, and automate routine operations work. Businesses can also use it for complex workflows that span many steps and tools, and for advanced math and science reasoning. Because Beam is released under the Apache 2.0 license, customers can inspect and customize the model, while also running it in their own AWS accounts, so data stays private and under their control, protected by the same AWS security and compliance capabilities they already rely on.  “Advanced AI models like Beam, now available on Amazon SageMaker, let us run open weight frontier AI entirely inside our own secure environments, with full visibility into the weights, the data, and the pipeline. In the age of multi-model AI, the pairing of openness and managed infrastructure is an essential addition to the AI ecosystem. The freedom to deploy and adapt advanced AI, tailored to mission problems with client-specific security and controls, gives more agencies greater flexibility to deploy advanced AI across their enterprise." said Garrett Berntsen, Chief AI Officer, Accenture Federal Services. Beam is initially available in Amazon SageMaker JumpStart in US East (N. Virginia) and US East (Ohio). To start, search for "Beam" in SageMaker JumpStart within Amazon SageMaker Studio, or deploy it directly on SageMaker AI.  To learn more, read the AWS/Beam launch blog, SageMaker AI documentation and SageMaker JumpStart documentation.

Beam, the first open weight model offered by US-based Reflection, is now available in Amazon SageMaker JumpStart, the model hub in Amazon SageMaker AI. According to Beam, they operate at the frontier of open weight models in its class, with strong performance across reasoning, coding, and agentic benchmarks. With it, customers can now build advanced coding agents and automated workflows on a frontier open weight model while keeping control of their data and infrastructure and adapting the model to their business. Beam runs alongside other models that customers already use in SageMaker AI and scales to meet production demand with the same controls, audit trails, and monitoring built into every SageMaker AI deployment. Additionally, Beam was ported and optimized for AWS Trainium3, giving customers a high-performance, cost-efficient option for deploying and scaling the model from day one. “Reflection is delivering frontier AI that developers can actually control, not just rent through an API. Bringing Beam to SageMaker AI puts that capability in front of millions of developers on infrastructure they already trust, running in their own AWS account, on their own data, fully in their control," said Misha Laskin, co-founder and CEO, Reflection. Engineering teams can use Beam to resolve software issues, generate and review code, and automate routine operations work. Businesses can also use it for complex workflows that span many steps and tools, and for advanced math and science reasoning. Because Beam is released under the Apache 2.0 license, customers can inspect and customize the model, while also running it in their own AWS accounts, so data stays private and under their control, protected by the same AWS security and compliance capabilities they already rely on.  “Advanced AI models like Beam, now available on Amazon SageMaker, let us run open weight frontier AI entirely inside our own secure environments, with full visibility into the weights, the data, and the pipeline. In the age of multi-model AI, the pairing of openness and managed infrastructure is an essential addition to the AI ecosystem. The freedom to deploy and adapt advanced AI, tailored to mission problems with client-specific security and controls, gives more agencies greater flexibility to deploy advanced AI across their enterprise." said Garrett Berntsen, Chief AI Officer, Accenture Federal Services. Beam is initially available in Amazon SageMaker JumpStart in US East (N. Virginia) and US East (Ohio). To start, search for "Beam" in SageMaker JumpStart within Amazon SageMaker Studio, or deploy it directly on http://aws.amazon.com/sagemaker/ai/.  To learn more, read the https://aws.amazon.com/blogs/machine-learning/introducing-reflection-beam-an-open-weight-model-for-agentic-coding-on-aws/, https://docs.aws.amazon.com/sagemaker/ and https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.

NVIDIA's Nemotron 3.5 Super VL is now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. This vision-language model from the Nemotron 3.5 family accepts images, video, and text as input and generates text, enabling customers to deploy multimodal AI solutions on AWS infrastructure. Nemotron 3.5 Super VL is designed for document intelligence, GUI understanding, video question answering, and multimodal agentic applications. It pairs a 120B-parameter hybrid Mixture-of-Experts (MoE) language backbone with 12B active parameters and a vision encoder, supporting context lengths of up to 1 million tokens. The model includes a built-in Multi-Token Prediction (MTP) head for speculative decoding to accelerate text generation, with reasoning configurable per request. It supports ten languages including English, French, Spanish, German, Japanese, Hindi, Korean, and Chinese. Post-trained with multimodal supervised fine-tuning on image, video, document, chart, and GUI data followed by GRPO reinforcement learning, it delivers structured JSON output, tool calling, and configurable reasoning for enterprise agent workflows. SageMaker JumpStart offers two variants: NVFP4 for optimized inference on G7 instances with NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs, and BF16 reference weights on ml.p5en.48xlarge for customization including SFT, RL, distillation, and domain adaptation. With SageMaker JumpStart, customers can deploy Nemotron 3.5 Super VL with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

NVIDIA's Nemotron 3.5 Super VL is now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. This vision-language model from the Nemotron 3.5 family accepts images, video, and text as input and generates text, enabling customers to deploy multimodal AI solutions on AWS infrastructure. Nemotron 3.5 Super VL is designed for document intelligence, GUI understanding, video question answering, and multimodal agentic applications. It pairs a 120B-parameter hybrid Mixture-of-Experts (MoE) language backbone with 12B active parameters and a vision encoder, supporting context lengths of up to 1 million tokens. The model includes a built-in Multi-Token Prediction (MTP) head for speculative decoding to accelerate text generation, with reasoning configurable per request. It supports ten languages including English, French, Spanish, German, Japanese, Hindi, Korean, and Chinese. Post-trained with multimodal supervised fine-tuning on image, video, document, chart, and GUI data followed by GRPO reinforcement learning, it delivers structured JSON output, tool calling, and configurable reasoning for enterprise agent workflows. SageMaker JumpStart offers two variants: NVFP4 for optimized inference on G7 instances with NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs, and BF16 reference weights on ml.p5en.48xlarge for customization including SFT, RL, distillation, and domain adaptation. With SageMaker JumpStart, customers can deploy Nemotron 3.5 Super VL with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the models to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.

Meta's Muse Spark Open is now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. This coding-optimized open-weight model from Meta is purpose-built for agentic coding workflows, bringing multi-step reasoning and tool calling to enterprise software engineering on AWS infrastructure. Muse Spark Open is designed for long-running coding agents and multimodal engineering workflows. Built on a Mixture-of-Experts (MoE) architecture with 816B total parameters and 42B active per token, it delivers the capacity of a very large network while keeping per-token compute closer to that of a much smaller dense model. The model holds a 1M-token context window, enabling it to ingest an entire project—including dependencies, legacy code, and thousands of files—without splitting tasks into smaller pieces. It accepts text, images, documents, audio, and audio-video as input and generates text output. Trained on real developer workflows such as multi-file refactors and long debugging sessions, it plans, acts, observes results, and self-corrects over long horizons rather than making single tool calls. SageMaker JumpStart offers two variants: BF16 (Muse-Spark-Open-816B-A42B) and NVFP4 quantized (Muse-Spark-Open-816B-A42B-NVFP4), with the NVFP4 variant requiring roughly a quarter of the memory for cost-efficient deployment. With SageMaker JumpStart, customers can deploy Muse Spark Open with just a few clicks, with the endpoint running in their own AWS account for full control over source code and prompts. To get started with this model, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the model to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the Amazon SageMaker JumpStart documentation.

Meta's Muse Spark Open is now available on Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. This coding-optimized open-weight model from Meta is purpose-built for agentic coding workflows, bringing multi-step reasoning and tool calling to enterprise software engineering on AWS infrastructure. Muse Spark Open is designed for long-running coding agents and multimodal engineering workflows. Built on a Mixture-of-Experts (MoE) architecture with 816B total parameters and 42B active per token, it delivers the capacity of a very large network while keeping per-token compute closer to that of a much smaller dense model. The model holds a 1M-token context window, enabling it to ingest an entire project—including dependencies, legacy code, and thousands of files—without splitting tasks into smaller pieces. It accepts text, images, documents, audio, and audio-video as input and generates text output. Trained on real developer workflows such as multi-file refactors and long debugging sessions, it plans, acts, observes results, and self-corrects over long horizons rather than making single tool calls. SageMaker JumpStart offers two variants: BF16 (Muse-Spark-Open-816B-A42B) and NVFP4 quantized (Muse-Spark-Open-816B-A42B-NVFP4), with the NVFP4 variant requiring roughly a quarter of the memory for cost-efficient deployment. With SageMaker JumpStart, customers can deploy Muse Spark Open with just a few clicks, with the endpoint running in their own AWS account for full control over source code and prompts. To get started with this model, navigate to the SageMaker JumpStart model catalog in the SageMaker console or use the SageMaker Python SDK to deploy the model to your AWS account. For more information about deploying and using foundation models in SageMaker JumpStart, see the https://docs.aws.amazon.com/sagemaker/latest/dg/studio-jumpstart.html.

Amazon SageMaker AI now supports Amazon EC2 G6e instances for batch transform. Batch Transform enables you to run predictions on datasets stored in Amazon S3 and is suited for large datasets that do not require a persistent inference endpoint. Amazon EC2 G6e instances are powered by up to eight NVIDIA L40S Tensor Core GPUs with 48 GB of memory per GPU and third-generation AMD EPYC processors. G6e instances deliver improved performance for GPU-intensive workloads. With this launch, you can use G6e instances for GPU-intensive offline inference workloads, including large language models and diffusion models that generate images, video, and audio. To get started, select a supported ml.g6e instance type when creating a Batch Transform job through AWS SDKs, AWS CLI, or the CreateTransformJob API. G6e support for Batch Transform is available in US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), and Asia Pacific (Hyderabad). To learn more, visit the Amazon SageMaker AI product page and see the Batch Transform documentation. For pricing information on these instances, please visit our pricing page.

Amazon SageMaker AI now supports https://aws.amazon.com/ec2/instance-types/g6e/ for batch transform. Batch Transform enables you to run predictions on datasets stored in Amazon S3 and is suited for large datasets that do not require a persistent inference endpoint. Amazon EC2 G6e instances are powered by up to eight NVIDIA L40S Tensor Core GPUs with 48 GB of memory per GPU and third-generation AMD EPYC processors. G6e instances deliver improved performance for GPU-intensive workloads. With this launch, you can use G6e instances for GPU-intensive offline inference workloads, including large language models and diffusion models that generate images, video, and audio. To get started, select a supported ml.g6e instance type when creating a Batch Transform job through AWS SDKs, AWS CLI, or the CreateTransformJob API. G6e support for Batch Transform is available in US East (N. Virginia), US East (Ohio), US West (Oregon), Asia Pacific (Mumbai), and Asia Pacific (Hyderabad). To learn more, visit the https://aws.amazon.com/sagemaker/ai/deploy/ product page and see the https://docs.aws.amazon.com/sagemaker/latest/dg/batch-transform.html. For pricing information on these instances, please visit our https://aws.amazon.com/sagemaker/ai/pricing/?refid=ft_sagemaker.

Amazon SageMaker AI now offers Generative AI Inference Recommendations in SageMaker AI Studio, giving customers a guided, low-code, no-code path to find the best inference configuration for their workload. This builds on the API-based launch in April 2026, extending the same benchmarking infrastructure to teams that prefer a visual workflow over programmatic access. Deploying generative AI models in production requires finding the right combination of instance type, serving container, and optimization strategy. Getting this right typically involves weeks of manual benchmarking, configuration tuning, and trial-and-error, with no easy way to know if the final setup is actually optimal. With the new experience, customers describe their workload and what matters most, whether that's latency, throughput, or cost, and SageMaker AI does the rest. It benchmarks multiple configurations on real GPU infrastructure using NVIDIA AIPerf, applies goal-aligned techniques like speculative decoding for throughput or kernel tuning for latency, and returns ranked, production-ready recommendations with measured performance data. Teams get to a validated configuration in hours instead of weeks, without needing to decide which techniques to apply or how to configure them. With the new experience, customers describe their workload and what matters most, whether that's latency, throughput, or cost, and SageMaker AI does the rest. It benchmarks multiple configurations on real GPU infrastructure using NVIDIA AIPerf, applies goal-aligned techniques like speculative decoding for throughput or kernel tuning for latency, and returns ranked, production-ready recommendations with measured performance data. Teams get to a validated configuration in hours instead of weeks, without needing to decide which techniques to apply or how to configure them. In SageMaker AI Studio under Jobs, Inference optimization, customers select a use-case profile (Interact, Generate, Summarize, or Custom), choose an optimization goal (minimize latency, maximize throughput, or minimize cost), and pick their model from JumpStart, S3, Model Registry, or an existing SageMaker model. Recommendations are ranked by TTFT, inter-token latency, throughput, and cost, and can be compared visually before deploying to a SageMaker real-time endpoint directly from Studio. There is no additional cost for generating recommendations. Standard compute costs apply for optimization jobs and endpoints provisioned during benchmarking. This capability is available in US East (N. Virginia), US West (Oregon), US East (Ohio), Europe (Ireland), Europe (Frankfurt), Asia Pacific (Singapore), Asia Pacific (Tokyo). To learn more, visit the https://aws.amazon.com/blogs/machine-learning/launching-ui-for-generative-ai-inference-recommendations-in-amazon-sagemaker-ai/ or the https://docs.aws.amazon.com/sagemaker/latest/dg/generative-ai-inference-recommendations.html.

Amazon SageMaker AI now offers Generative AI Inference Recommendations in SageMaker AI Studio, giving customers a guided, low-code, no-code path to find the best inference configuration for their workload. This builds on the API-based launch in April 2026, extending the same benchmarking infrastructure to teams that prefer a visual workflow over programmatic access. Deploying generative AI models in production requires finding the right combination of instance type, serving container, and optimization strategy. Getting this right typically involves weeks of manual benchmarking, configuration tuning, and trial-and-error, with no easy way to know if the final setup is actually optimal. With the new experience, customers describe their workload and what matters most, whether that's latency, throughput, or cost, and SageMaker AI does the rest. It benchmarks multiple configurations on real GPU infrastructure using NVIDIA AIPerf, applies goal-aligned techniques like speculative decoding for throughput or kernel tuning for latency, and returns ranked, production-ready recommendations with measured performance data. Teams get to a validated configuration in hours instead of weeks, without needing to decide which techniques to apply or how to configure them. With the new experience, customers describe their workload and what matters most, whether that's latency, throughput, or cost, and SageMaker AI does the rest. It benchmarks multiple configurations on real GPU infrastructure using NVIDIA AIPerf, applies goal-aligned techniques like speculative decoding for throughput or kernel tuning for latency, and returns ranked, production-ready recommendations with measured performance data. Teams get to a validated configuration in hours instead of weeks, without needing to decide which techniques to apply or how to configure them. In SageMaker AI Studio under Jobs, Inference optimization, customers select a use-case profile (Interact, Generate, Summarize, or Custom), choose an optimization goal (minimize latency, maximize throughput, or minimize cost), and pick their model from JumpStart, S3, Model Registry, or an existing SageMaker model. Recommendations are ranked by TTFT, inter-token latency, throughput, and cost, and can be compared visually before deploying to a SageMaker real-time endpoint directly from Studio. There is no additional cost for generating recommendations. Standard compute costs apply for optimization jobs and endpoints provisioned during benchmarking. This capability is available in US East (N. Virginia), US West (Oregon), US East (Ohio), Europe (Ireland), Europe (Frankfurt), Asia Pacific (Singapore), Asia Pacific (Tokyo). To learn more, visit the blog post or the documentation.

Amazon SageMaker Studio quick setup now completes in under twenty seconds, reduced from over two minutes. Whether you are building ML pipelines, exploring data, developing with notebooks, or fine-tuning foundation models, you can go from sign-in to a fully configured Studio environment almost instantly. As part of this streamlined setup, newly created Studio environments now come with serverless model customization permissions automatically configured. A new managed policy, AmazonSageMakerModelCustomizationCoreAccess, is created and attached for you, providing permissions for serverless model customization jobs including fine-tuning with custom reward functions for reinforcement learning, model evaluation, and deployment to SageMaker or Bedrock endpoints. This eliminates the need to manually create and configure IAM roles and policies before you can start experimenting. For existing Studio environments, actionable messages with direct links to documentation guide you through adding these permissions. This feature is available in all AWS Commercial Regions where Amazon SageMaker Studio is supported. To get started, create a new Studio environment using quick setup in the SageMaker AI Console. To learn more, see https://docs.aws.amazon.com/sagemaker/latest/dg/onboard-quick-start.html and https://docs.aws.amazon.com/sagemaker/latest/dg/model-customize-open-weight-prereq.html in the Amazon SageMaker documentation.

Amazon SageMaker Studio now supports direct integration from Hugging Face, letting you go from discovering a model to working with it inside a fully configured Studio environment in a single click. Select any supported model on Hugging Face and choose "Customize on SageMaker AI" or "Deploy on SageMaker AI" to land directly on the corresponding workflow page with the model pre-loaded and ready to use. Previously, getting from model discovery to a working environment required navigating the AWS Console to find SageMaker AI, configuring an environment, setting up IAM permissions for serverless model customization, and in many cases requesting GPU quota increases through Service Quotas before running a first job. Now, new customers complete a standard AWS sign-up and receive a SageMaker Studio environment created in seconds with pre-configured permissions for serverless model customization jobs including fine-tuning with custom reward functions for reinforcement learning, model evaluation, and deployment to SageMaker or Bedrock endpoints. Verified customers receive default GPU access to G5, G6, and G4dn instances across endpoint deployments, training jobs, and notebooks without requesting quota increases, and quota limit and utilization information is visible for each instance type directly inside the Studio environment. Returning customers signing in from Hugging Face or SageMaker product pages select their environment and land directly inside SageMaker Studio with the model ready to use. This feature is available in all AWS Commercial Regions where Amazon SageMaker Studio is supported. To get started, visit any supported model on https://huggingface.co/models and select "Customize on SageMaker AI" or "Deploy on SageMaker AI," or click Get Started from the https://aws.amazon.com/sagemaker/ai/studio/ page. To learn more, see https://docs.aws.amazon.com/sagemaker/latest/dg/studio-updated-launch.html in the Amazon SageMaker documentation.

We are pleased to announce the availability of https://aws.amazon.com/ec2/instance-types/g6/instances in the AWS GovCloud (US-East) region on Amazon SageMaker AI inference. G6 instances are powered by up to 8 NVIDIA L4 Tensor Core GPUs, each with 24 GB of memory, and third-generation AMD EPYC processors, delivering up to 2x the deep learning inference performance compared to G4dn instances. With this region expansion, government agencies and organizations operating in GovCloud can deploy inference endpoints on G6 instances to serve generative AI workloads—including small-to-medium language models, image generation, and computer vision tasks—while meeting strict compliance and data residency requirements. G6 instances offer strong price-performance for production inference workloads that fit within 24 GB of GPU memory. G6 instances for SageMaker AI inference are now available in AWS GovCloud (US-East), in addition to previously supported regions. For pricing information on these instances, please visit our https://aws.amazon.com/sagemaker/ai/pricing/?refid=ft_sagemaker.

We are pleased to announce the availability of https://aws.amazon.com/ec2/instance-types/g7e/in Asia Pacific (Seoul), Europe (London), and Asia Pacific (Tokyo) on Amazon SageMaker AI inference. G7e instances feature up to 8 NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs with 96 GB of memory per GPU, 5th Generation Intel Xeon processors, and up to 1,600 Gbps of Elastic Fabric Adapter networking bandwidth, delivering up to 2.3x inference performance compared to previous-generation G6e instances. With this region expansion, you can now deploy inference endpoints on G7e instances closer to your end users in Asia and Europe, reducing latency for generative AI workloads. G7e instances provide up to 768 GB of total GPU memory on a single instance, enabling you to serve medium-to-large language models of up to 70B parameters with FP8 precision without multi-node configurations. These instances are well suited for LLM inference, image and video generation, spatial computing, and scientific computing workloads that require high GPU memory capacity and bandwidth. G7e instances for SageMaker AI inference are now available in Asia Pacific (Seoul), Europe (London), and Asia Pacific (Tokyo), in addition to previously supported regions. For pricing information on these instances, please visit our https://aws.amazon.com/sagemaker/ai/pricing/?refid=ft_sagemaker.

Amazon SageMaker AI inference endpoints now support flexible provisioning across a prioritized list of instance types. When your preferred instance type has insufficient capacity, SageMaker AI automatically provisions from the next available option in your list — keeping endpoint creation and autoscaling running smoothly without manual intervention. This gives teams deploying AI/ML models in production the resilience to handle capacity constraints gracefully, ensuring endpoints come up reliably and scale on demand. With instance pool support, you define a prioritized list of instance types and SageMaker AI automatically provisions capacity by working through your list in order. This applies across endpoint creation, updates, and scaling. When scaling down, SageMaker AI removes lowest-priority instances first, preserving your preferred infrastructure as the fleet contracts. This works for Single Model Endpoints, InferenceComponent-based endpoints, and Asynchronous Inference endpoints — including endpoints that scale to zero, where SageMaker AI provisions from your highest-priority available pool when scaling back up. Because fallback instance types differ in GPU memory and compute capability, you can specify a different optimized model for each instance type in your priority list. You can prepare these artifacts yourself or use SageMaker AI inference recommendations, which automatically generates hardware-specific optimized configurations per instance type. Additionally, per-instance-type CloudWatch metrics give you visibility into latency, throughput, GPU utilization, and instance count by hardware type within a single endpoint. This capability is available today in US East (N. Virginia), US East (Ohio), US West (Oregon), Canada (Central), South America (São Paulo), Europe (Ireland), Europe (London), Europe (Frankfurt), Europe (Stockholm), Europe (Zurich), Asia Pacific (Tokyo), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Mumbai), and Asia Pacific (Jakarta). To learn more, visit the https://docs.aws.amazon.com/sagemaker/latest/dg/realtime-endpoints-heterogeneous.html.

We are pleased to announce the availability of Amazon EC2 G6 instances in the AWS GovCloud (US-East) region on Amazon SageMaker AI inference. G6 instances are powered by up to 8 NVIDIA L4 Tensor Core GPUs, each with 24 GB of memory, and third-generation AMD EPYC processors, delivering up to 2x the deep learning inference performance compared to G4dn instances. With this region expansion, government agencies and organizations operating in GovCloud can deploy inference endpoints on G6 instances to serve generative AI workloads—including small-to-medium language models, image generation, and computer vision tasks—while meeting strict compliance and data residency requirements. G6 instances offer strong price-performance for production inference workloads that fit within 24 GB of GPU memory. G6 instances for SageMaker AI inference are now available in AWS GovCloud (US-East), in addition to previously supported regions. For pricing information on these instances, please visit our pricing page.

We are pleased to announce the availability of Amazon EC2 G7e instances in Asia Pacific (Seoul), Europe (London), and Asia Pacific (Tokyo) on Amazon SageMaker AI inference. G7e instances feature up to 8 NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs with 96 GB of memory per GPU, 5th Generation Intel Xeon processors, and up to 1,600 Gbps of Elastic Fabric Adapter networking bandwidth, delivering up to 2.3x inference performance compared to previous-generation G6e instances. With this region expansion, you can now deploy inference endpoints on G7e instances closer to your end users in Asia and Europe, reducing latency for generative AI workloads. G7e instances provide up to 768 GB of total GPU memory on a single instance, enabling you to serve medium-to-large language models of up to 70B parameters with FP8 precision without multi-node configurations. These instances are well suited for LLM inference, image and video generation, spatial computing, and scientific computing workloads that require high GPU memory capacity and bandwidth. G7e instances for SageMaker AI inference are now available in Asia Pacific (Seoul), Europe (London), and Asia Pacific (Tokyo), in addition to previously supported regions. For pricing information on these instances, please visit our pricing page.

Amazon SageMaker Studio quick setup now completes in under twenty seconds, reduced from over two minutes. Whether you are building ML pipelines, exploring data, developing with notebooks, or fine-tuning foundation models, you can go from sign-in to a fully configured Studio environment almost instantly. As part of this streamlined setup, newly created Studio environments now come with serverless model customization permissions automatically configured. A new managed policy, AmazonSageMakerModelCustomizationCoreAccess, is created and attached for you, providing permissions for serverless model customization jobs including fine-tuning with custom reward functions for reinforcement learning, model evaluation, and deployment to SageMaker or Bedrock endpoints. This eliminates the need to manually create and configure IAM roles and policies before you can start experimenting. For existing Studio environments, actionable messages with direct links to documentation guide you through adding these permissions. This feature is available in all AWS Commercial Regions where Amazon SageMaker Studio is supported. To get started, create a new Studio environment using quick setup in the SageMaker AI Console. To learn more, see Quick setup and Model Customization permissions setup in the Amazon SageMaker documentation.

Amazon SageMaker AI inference endpoints now support flexible provisioning across a prioritized list of instance types. When your preferred instance type has insufficient capacity, SageMaker AI automatically provisions from the next available option in your list — keeping endpoint creation and autoscaling running smoothly without manual intervention. This gives teams deploying AI/ML models in production the resilience to handle capacity constraints gracefully, ensuring endpoints come up reliably and scale on demand. With instance pool support, you define a prioritized list of instance types and SageMaker AI automatically provisions capacity by working through your list in order. This applies across endpoint creation, updates, and scaling. When scaling down, SageMaker AI removes lowest-priority instances first, preserving your preferred infrastructure as the fleet contracts. This works for Single Model Endpoints, InferenceComponent-based endpoints, and Asynchronous Inference endpoints — including endpoints that scale to zero, where SageMaker AI provisions from your highest-priority available pool when scaling back up. Because fallback instance types differ in GPU memory and compute capability, you can specify a different optimized model for each instance type in your priority list. You can prepare these artifacts yourself or use SageMaker AI inference recommendations, which automatically generates hardware-specific optimized configurations per instance type. Additionally, per-instance-type CloudWatch metrics give you visibility into latency, throughput, GPU utilization, and instance count by hardware type within a single endpoint. This capability is available today in US East (N. Virginia), US East (Ohio), US West (Oregon), Canada (Central), South America (São Paulo), Europe (Ireland), Europe (London), Europe (Frankfurt), Europe (Stockholm), Europe (Zurich), Asia Pacific (Tokyo), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Mumbai), and Asia Pacific (Jakarta). To learn more, visit the Amazon SageMaker AI documentation.