Releasesby Ibis
Amazon Bedrock AgentCore Memory now supports configurable time-to-live for long-term memory
Update11 days agoUnverifiedAdded Oct 21, 2026
Amazon Bedrock AgentCore Memory now lets you set a time-to-live (TTL) on long-term memory records, so they are automatically deleted after a retention period you define. By default, long-term memory records do not expire.
Topics: AI agents, Security, Developer tools, Regions
More Amazon Bedrock releases
Every Amazon Bedrock releaseAnnouncing consumption-based pricing for short-term memory in Amazon Bedrock AgentCore
Announcing consumption-based pricing for short-term memory in Amazon Bedrock AgentCore Amazon Bedrock AgentCore memory now prices short-term memory (STM) based on the data your agents ingest, retrieve, and store, replacing the previous flat rate per event.
Web Search on Amazon Bedrock AgentCore expands to AWS GovCloud and 3 Regions
Web Search on Amazon Bedrock AgentCore is now available in four additional AWS Regions: US East (Ohio), US West (Oregon), Asia Pacific (Sydney), and AWS GovCloud (US-West).
Amazon Bedrock now supports reasoning summaries for OpenAI models
Amazon Bedrock now supports the reasoning.summary parameter for OpenAI models through the Responses API. This capability lets you request a human-readable summary of a model’s reasoning alongside its response, helping you understand its approach to complex tasks such as coding, analysis, and multi-step problem solving.
TwelveLabs Pegasus 1.5 model now available on Amazon Bedrock
Amazon Bedrock now supports TwelveLabs Pegasus 1.5, a video-to-text model that generates structured, time-coded metadata from video. Until now, finding a moment in a large video library meant knowing where to look before you could ask about it.
OpenAI GPT-6.1 Sol now supports Ultrafast mode on Amazon Bedrock
Today, AWS announces the availability of Ultrafast mode for GPT-6.1 Sol from OpenAI on Amazon Bedrock. Ultrafast mode provides faster inference for workloads where speed matters most. The Amazon Bedrock inference engine delivers the performance, security, and reliability required for production workloads.
AWS Cost Explorer, Budgets, and Dashboards now support Amazon Bedrock product attributes
AWS Cost Explorer, AWS Budgets, and AWS Cost Management Dashboards now let you analyze Amazon Bedrock costs by product attributes, a new dimension that breaks down Bedrock cost by model, model provider, inference type, and feature. In Cost Explorer and Dashboards, you can group and filter costs by these attributes.
Grok 4.7 is now available on Amazon Bedrock in AWS GovCloud (US)
Amazon Bedrock now supports SpaceXAI Grok 4.7, a frontier model built for coding, agentic tasks, and knowledge work in AWS GovCloud (US). Grok 4.7 builds on Grok 4.6 with better mixed-document handling, more dependable repo-scale coding with planning and error recovery, and enhanced browser-use agents for form fills and portal navigation.
Claude Haiku 5.5 is now available on AWS
AWS now offers Claude Haiku 5.5, the fastest and most efficient model in the Claude 5.5 family, built for subagents and high-volume, cost-sensitive work. According to Anthropic, it costs around 75% less than Claude Haiku 4.5 for most tasks.
Also shipped on Oct 13, 2026
AWS in October 2026What's included:
- Three training methods: Supervised fine-tuning (SFT) , direct preference optimization (DPO) , and reinforcement learning with group relative policy optimization (GRPO) . Each method trains a low-rank adapter (LoRA) or the full model weights. Custom loss functions : Train with any objective you compute in PyTorch from the model's log-probabilities.
The AI.AGG function is generally available (GA)
The AI.AGG function is generally available (GA). You can use this function to semantically aggregate unstructured input data based on natural language instructions.
BigQuery generative AI functions now support the gemini-4-argon model
BigQuery generative AI functions now support the gemini-4-argon model. This model is generally available .
Gemini 4 Argon in CodeMender (Preview)
CodeMender now supports Gemini 4 Argon. To use it, pass --model gemini-4-argon to cm find , cm verify , or cm fix . Gemini 3.8 Flash remains the default model. For more information, see Specifying the model .
Gemini 4 Argon and Gemini 4 Argon Cyber Permissive
Gemini 4 Argon ( gemini-4-argon ) is available in General Availability (GA) . Gemini 4 Argon is Google's frontier model that excels at deep work in complex, real-world tasks across domains including coding, finance, legal, cybersecurity, and science.
On-demand state repartitioning is now generally available
On-demand state repartitioning is now generally available. You can resize the number of shuffle partitions for a stateful Structured Streaming query or Lakeflow pipeline without losing checkpoint state. See On-demand state repartitioning for stateful streaming queries .