Releasesby GlyphProvisioned Throughput supports more detailed order statuses
Provisioned Throughput now provides detailed order lifecycle tracking in the Google Cloud console, including statuses like Declined, Cancelled, and Terminated.
Also shipped Nov 10, 2026Google Cloud in November 2026 →
Amazon Bedrock AgentCore now offers a Web Search API
AWS launched the InvokeWebSearch API on Amazon Bedrock AgentCore, enabling direct web search execution billed at $7 per 1,000 queries.
Flagship - Evaluate Flagship feature flags from Rust
Cloudflare released an official Rust SDK (`cloudflare-flagship`) for Flagship, enabling async Rust applications to evaluate feature flags via OpenFeature with remote or in-process local evaluation.
Amazon OpenSearch Service announces managed cross-Region disaster recovery
AWS introduced managed cross-Region disaster recovery for Amazon OpenSearch Service, providing continuous data replication with an RPO under one minute and RTO under 20 minutes.
Amazon Bedrock adds bedrock-runtime endpoint support for Daybreak models
AWS added support for OpenAI Daybreak Red and Daybreak Blue cybersecurity models on Amazon Bedrock runtime endpoints via US and Global cross-Region inference profiles.
Amazon ElastiCache Serverless now supports vector, full-text and hybrid searches plus aggregations
AWS launched vector, full-text, and hybrid search capabilities along with server-side aggregations for Amazon ElastiCache Serverless for Valkey.
Amazon OpenSearch Service now lets you validate and roll back version upgrades
AWS launched clone-based upgrades for Amazon OpenSearch Service, allowing users to validate software upgrades on a cloned cluster before switching traffic or rolling back.
More from Gemini Enterprise Agent PlatformEvery Gemini Enterprise Agent Platform release →
Cross-project governance for semantic governance policies
Google Cloud introduced cross-project governance for semantic governance policies in Gemini Enterprise Agent Platform, enabling centralized policy enforcement across multi-project environments.
Gemini 4 Carbon and Gemini 4 Carbon for cyber (GA)
Google Cloud announced the general availability of Gemini 4 Carbon and Gemini 4 Carbon for cyber, featuring a 1,048,576-token context limit and configurable thinking levels.
End-user safety identifier labels for abuse monitoring
End-user safety identifier labels are now generally available for Gemini and Veo API calls. This allows API resellers and multi-tenant applications to attribute policy violations to specific end users.
Gemini 4 Carbon in CodeMender (Preview)
CodeMender now supports the Gemini 4 Carbon model in preview. Users can specify the model using the --model gemini-4-carbon flag.
Govern agents on any CNCF-conformant Kubernetes cluster with Agent Gateway for cross-cloud (Limited Preview)
Agent Gateway for cross-cloud is available in limited preview, allowing governance of agents running on CNCF-conformant Kubernetes clusters outside of Google Cloud. It provides verifiable identity, registration, and traffic routing through local proxies.
Fast mode for Anthropic Claude models is generally available
Fast mode for Anthropic Claude models, starting with Claude Fable 5.2, is now generally available in the Gemini Enterprise Agent Platform. Users can enable it by setting "speed": "fast" in prediction requests to reduce latency.
Anthropic's Claude Fable 5.2
Claude Fable 5.2 is now generally available in the Gemini Enterprise Agent Platform Model Garden, including support for fast mode.
Meta Muse models in Preview
Meta Muse Wonder 1.0, Muse Ember 1.0, and Muse Spark 1.3 are now available in preview on the Gemini Enterprise Agent Platform. These models support reasoning, function calling, and a 1M-token context window.