Today, AWS announced the availability of gemma-4-E2B-it in Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. This model from Google DeepMind is a multimodal, instruction-tuned model optimized for efficient local execution, enabling customers to build capable AI applications on AWS infrastructure.
Gemma-4-E2B-it processes text, image, and audio input and generates text output, with a built-in reasoning mode that lets the model think step-by-step before answering. It offers image understanding including object detection, document parsing, screen and UI understanding, chart comprehension, and OCR; video understanding; native function calling for agentic workflows; code generation, completion, and correction; and multilingual support across dozens of languages.
With SageMaker JumpStart, customers can deploy this model with just a few clicks to address their specific AI use cases. To get started with this model, navigate to the Models section of SageMaker Studio 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.
Today, AWS announced the availability of privacy-filter in Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. This model from OpenAI is a bidirectional token-classification model for personally identifiable information (PII) detection and masking in text, enabling customers to build data sanitization workflows on AWS infrastructure.
Privacy-filter is fast, context-aware, and tunable, designed for high-throughput data sanitization workflows that teams can run on-premises. It labels an input sequence in a single forward pass and detects PII span categories including account numbers, addresses, emails, names, phone numbers, URLs, dates, and secrets.
With SageMaker JumpStart, customers can deploy this model with just a few clicks to address their specific AI use cases. To get started with this model, navigate to the Models section of SageMaker Studio 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.
Today, AWS announced the availability of Voxtral-Mini-4B-Realtime-2602 in Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. This model from Mistral AI is a multilingual, real-time speech-transcription model, enabling customers to build low-latency speech applications on AWS infrastructure.
Voxtral-Mini-4B-Realtime excels at high-quality transcription of audio to text with a natively streaming architecture that enables real-time transcription. It supports multilingual transcription across 13 languages and offers configurable transcription delays, allowing users to balance latency and accuracy based on their needs.
With SageMaker JumpStart, customers can deploy this model with just a few clicks to address their specific AI use cases. To get started with this model, navigate to the Models section of SageMaker Studio 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.
Today, AWS announced the availability of Qwen3-VL-Embedding-2B and Qwen3-Reranker-4B in Amazon SageMaker JumpStart, expanding the portfolio of foundation models available to AWS customers. These models from Qwen are designed for information retrieval and cross-modal understanding, enabling customers to build comprehensive search pipelines on AWS infrastructure. The two models are typically used in tandem: the embedding model performs efficient initial recall, while the reranker refines results in a subsequent re-ranking stage.
These models address different stages of the retrieval pipeline with specialized capabilities:
Qwen3-VL-Embedding-2B accepts diverse inputs including text, images, screenshots, and videos, as well as inputs containing a mixture of these modalities, and generates semantically rich vectors that capture both visual and textual information in a shared space. It delivers performance across diverse multimodal tasks such as image-text retrieval, video-text matching, visual question answering, and multimodal content clustering, with support for over 30 languages.
Qwen3-Reranker-4B takes a query and document pair as input and outputs a precise relevance score to refine retrieval results. It supports text retrieval, code retrieval, text classification, text clustering, and bitext mining across over 100 languages, with user-defined instructions to enhance performance for specific tasks, languages, or scenarios.
With SageMaker JumpStart, customers can deploy any of these models with just a few clicks to address their specific AI use cases. To get started with these models, navigate to the Models section of SageMaker Studio 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.
Amazon DocumentDB (with MongoDB compatibility) is now available as a specialized database skill in the Agent Toolkit for AWS. With this skill, AI coding agents can set up, manage, migrate, optimize, and troubleshoot Amazon DocumentDB clusters using step-by-step best-practice workflows, reducing errors and helping developers move faster without needing to look up DocumentDB operations guidance manually.
The Amazon DocumentDB skill covers seven workflows: cluster provisioning, schema design, MongoDB compatibility assessment, DMS-based migration with change data capture, performance tuning, a 41-check well-architected review, and major version upgrades. When paired with the AWS MCP Server, agents can execute AWS CLI commands and run diagnostic queries with IAM-based guardrails, CloudTrail audit logging, and sandboxed execution. The skill also works standalone via the AWS CLI for teams that prefer local execution.
The Amazon DocumentDB skill is available at no additional charge as part of the Agent Toolkit for AWS. To get started, see the Amazon DocumentDB skill on GitHub or browse the Agent Toolkit Quick Start guide. For more information about Amazon DocumentDB, see the Amazon DocumentDB Developer Guide.
Amazon Managed Service for Prometheus is now available in Asia Pacific (New Zealand) Region. Amazon Managed Service for Prometheus is a fully managed, Prometheus-compatible monitoring service that makes it easy to monitor and alert on operational metrics at scale.
Amazon Managed Service for Prometheus is available in multiple AWS Regions. Customers can send up to 1 billion active metric series to a single workspace and can create many workspaces per account, where a workspace is a logical space dedicated to the storage and querying of Prometheus metrics.
To learn about Amazon Managed Service for Prometheus pricing, visit the pricing page.
GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock, bringing the smartest family of models from OpenAI yet to Bedrock's next-generation inference engine built for high-performance, security and reliability. GPT-5.6 sets a new standard for intelligence and efficiency, allowing you to solve harder problems in less time and with more intelligence per token. The three models span capability tiers from flagship reasoning (Sol) to balanced performance (Terra) to fast, cost-efficient inference (Luna), all accessible through the Responses API on Amazon Bedrock.
With GPT-5.6, you can build autonomous coding agents, run long-horizon genomics and biology analyses, and perform advanced cybersecurity research. Sol delivers state-of-the-art results on agentic coding benchmarks, Terra provides GPT-5.5-level performance at half the cost, and Luna brings fast, affordable inference at the lowest price point. GPT-5.6 also supports prompt caching with explicit cache breakpoints, so repeated context across agentic workflows is billed at a 90% discount and doesn't compound cost as you scale. Pricing matches OpenAI first-party rates and usage counts toward your AWS commitments.
GPT-5.6 Sol is available in the following AWS Regions: US East (N. Virginia) and US East (Ohio). GPT-5.6 Terra and Luna are available in US East (N. Virginia), US East (Ohio), and US West (Oregon). Get started with Sol, Terra, and Luna using the Amazon Bedrock Console or the Responses API on the bedrock-mantle endpoint. To learn more, see the Amazon Bedrock documentation and read the launch blog post.
AWS Builder Center turned one year old last week. Launched on July 9, 2025, the platform has grown from a community hub with Wishlist voting, community profiles, and a toolbox into a full ecosystem with sandbox environments, workshops, Spaces, and a Builders’ Library. To mark the anniversary, Rick Suttles published a full feature timeline covering […]
On July 13, 2006, we launched Amazon Simple Queue Service (Amazon SQS) as one of the first three services available to customers, alongside Amazon EC2 and Amazon S3. We had learned firsthand that distributed systems need a reliable way to pass messages between components without creating tight dependencies. If one service called another directly and […]
In this post, we introduce the UI for optimized generative AI inference recommendations in Amazon SageMaker AI Studio, a low-code no-code (LCNC) experience. The API already gives you programmatic access to recommendations, but it assumes you know which parameters to set and how to interpret raw benchmark output. The UI removes that assumption. It guides you through preset use-case profiles, visual comparisons of results, and one-click deployment, so teams without deep infrastructure expertise can get a validated configuration on their own.
Building multi-tenant agents with Amazon Bedrock AgentCore and Apply fine-grained access control with Bedrock AgentCore Gateway interceptors establish the conceptual foundation for on-behalf-of (OBO) token exchange in agentic systems. This post is the implementation guide. It walks through a complete multi-tenant OBO setup against Okta, shows the JSON Web Token (JWT) claim transformations on each hop, and demonstrates how audience binding produces defense in depth that scales across tenants.
In this post, we describe how Bluesight used two AWS engagements and Amazon Bedrock AgentCore to evolve from a single-product AI prototype to Prism, a unified agentic AI solution spanning six healthcare compliance products. Prism Assistant for ControlCheck launched in May 2026 and is already in use by 20 health systems. A more complex multi-product agentic solution is on track for later in 2026.
In this post, I share how AI serves as an accessibility tool for neurodivergent professionals. The system is built on Amazon Quick on your desktop, an AI-powered desktop and web assistant that compensates for executive function gaps every day.
Today, GPT-5.6 Sol, Terra, and Luna from OpenAI are generally available on Amazon Bedrock, bringing the smartest family of models from OpenAI yet to Amazon Bedrock’s next-generation inference engine built for high-performance, security and reliability.
A single cold start can push your Java Lambda function’s response time from milliseconds to seconds, enough to violate your p99 SLA, timeout a downstream service, and page your on-call. The Java Virtual Machine (JVM) performs best in long-running processes. Its Just-In-Time (JIT) compiler progressively optimizes code over thousands of invocations. Standard serverless execution environments […]