AWS Weekly Roundup: GPT-6.1 Terra on Bedrock, Step Functions as Agent Tools, and More

The agentic launches that stood out last week weren't about how capable a model is - they were about reach. AWS Step Functions, which already orchestrates over 220 AWS services, can now be handed to an agent as a tool, so workflows teams already trust became callable without a rewrite. In the same week, the AI blog published how one engagement platform exposed roughly 400 internal API operations the same way. Neither story involves rebuilding anything, only describing what exists and letting the agent find it.

The other thread was cost. OpenAI's newest Terra model reached Amazon Bedrock priced well below the model beside it, and two post-quantum launches landed for a deadline nobody can put on a calendar yet.

OpenAI GPT-6.1 Terra is now generally available on Amazon Bedrock, and what interests me is where it sits rather than what it tops. Terra is the everyday-workload line of the GPT-6 family. In OpenAI's Agents' Last Exam evaluation it scored 15 percentage points higher than GPT-5.6 Terra, performed on par with GPT-6 Astra, and completed tasks more than three times faster than both. Those are OpenAI's figures, not an independent test. The price is what I would check first: input and output tokens are at least 50% lower than GPT-6.1 Sol and GPT-5.6 Terra. It takes up to 1 million input tokens with text and image input, and you can reach it from the Bedrock APIs or ChatGPT Work and Codex.

AWS Step Functions workflows are now available as AI agent tools through Amazon Bedrock AgentCore Gateway, which connects agents to tools over the Model Context Protocol (MCP). The division of labor is the idea: the agent decides when to run a workflow and what input to pass; Step Functions runs each step exactly as you defined it. A support agent can trigger a refund, and the eligibility check, the manager approval, and the credit still happen in that order every time, because the ordering was never the model's to improvise. Your existing Standard and Express workflows qualify as connector targets, and agents can also look up runs. It's available in all Regions where AgentCore Gateway is, at standard rates.

Last week's launches: AWS Key Management Service now supports ML-KEM for post-quantum key encapsulation, with private keys in FIPS 140-3 Level 3 validated HSMs and all three NIST FIPS 203 parameter sets supported through Encapsulate and Decapsulate. It's available everywhere KMS runs except the Middle East (UAE and Bahrain) and China Regions. Amazon Aurora PostgreSQL added post-quantum TLS key exchange the same week, on versions 18 and higher.

AWS IAM Identity Center now supports cross-Region trusted identity propagation, so a user's identity travels with their request to AWS services in another Region. Previously every service accessing that identity had to sit in the same Region, leaving two unappealing options: broad IAM roles that cannot distinguish individual users, or consolidating all services into a single Region. It's available at no additional cost everywhere IAM Identity Center runs.

Amazon ECS now supports GPU sharing with NVIDIA Multi-Process Service (MPS), letting multiple ECS tasks run concurrently on a single NVIDIA GPU - the practical answer to work that only ever uses a fraction of one, like small-model inference and multi-model serving. You declare the GPU memory each container needs and can optionally cap its share of GPU compute, and ECS places tasks on GPUs with available capacity as your services scale, with no code changes. It works on ECS Managed Instances and ECS on Amazon EC2, and is available in all commercial and AWS GovCloud (US) Regions.

AWS Lambda supports Seekable OCI (SOCI) lazy loading for Lambda Managed Instances, fetching only the files needed at each stage of startup instead of pulling a whole container image first - which AWS puts at up to 70% off container startup time. The technique also reached Amazon SageMaker AI training and processing jobs, with benchmarks showing lazy loading held at 3 to 11 seconds regardless of image size, against a median 3 minutes 42 seconds for a 13.2 GB image.

Amazon EKS Auto Mode now supports Kubernetes Gateway API, letting you declare how traffic reaches your applications with Gateway and HTTPRoute resources without installing a separate controller. You get HTTP and gRPC routing, cross-namespace routing, weighted traffic splitting, header-based routing, and automatic TLS certificate discovery through AWS Certificate Manager. Existing Ingress workloads keep working alongside them. Gateway API support is included with EKS Auto Mode; standard load balancing charges apply.

Other AWS news: Nubank reports that handing evidence collection and report writing to the AWS DevOps Agent cut a disaster recovery test cycle from about 4.3 hours to roughly 40 minutes, and quadrupled flow coverage in 2026 to more than 160. MoEngage estimates the managed path saved about six months of platform engineering after turning roughly 400 internal REST API operations into agent tools. And an engagement described using S3 Storage Lens groups and Storage Class Analysis to prove access patterns before moving 5.8 PB of logs, where a 90-day transition to Glacier Instant Retrieval cut the bill by roughly 70%.

Upcoming AWS events: re:Invent returns to Las Vegas from November 30 to December 4, with more than 2,200 sessions; the event catalog is live and reserved seating is open. AWS Community Days are winding down the 2026 season as re:Invent approaches, so check the hub for what's still on.

That's all for this week. Check back next Monday for another Weekly Roundup! - Daniel Abib

Source: AWS