xAI's Grok 4.6 is generally available

GASep 18, 2026VerifiedAdded Sep 22, 2026

Grok 4.6 is now generally available (GA) and available for production use on the global endpoint and the US multi-region endpoint.

Regions

Read Google Cloud's release notes

https://docs.cloud.google.com/gemini-enterprise-agent-platform/docs/release-notes#September_18_2026

Summaries of vendors' own notes. Product names and logos belong to their owners; logos via logo.dev.

More Gemini Enterprise Agent Platform releases

Gemini Enterprise Agent PlatformSep 18, 2026

Agent Platform SDK for Python version 2.0.1 is available

Version 2.0.1 of the Agent Platform SDK for Python ( google-cloud-agentplatform ) is now available. This release migrates generative AI modules to the Google Gen AI SDK, decouples the agent surface from google-cloud-aiplatform into a dedicated package, and introduces restructured namespaces.

DeprecationAI agentsDeveloper toolsSource

Gemini Enterprise Agent PlatformSep 17, 2026

Gemini Omni Flash supports stateful and streaming video generation (Preview)

Gemini Omni Flash supports stateful ( store: true ) and server-sent event (SSE) streaming ( stream: true ) video generation in the Interactions API in Preview . You can temporarily store generated videos and interaction state on the server, stream status updates and final outputs over an SSE connection, or retrieve completed asynchronous interactions using...

PreviewLLMsStreamingDeveloper toolsSource

Gemini Enterprise Agent PlatformSep 16, 2026

CodeMender updates (v0.8.0)

This release introduces updates to CodeMender: Gemini 3.8 Flash default : Gemini 3.8 Flash ( gemini-3.8-flash ) is now supported and enabled as the default model for CodeMender CLI sessions, delivering faster inference and improved reasoning. A one-time notice in the CLI informs users when the new default is active.

UpdateLLMsStreamingDeveloper toolsSource

Gemini Enterprise Agent PlatformSep 15, 2026

Reinforcement learning fine-tuning in the Google Cloud console (Preview)

You can create, monitor, and test reinforcement learning fine-tuning jobs for Gemini models in the Google Cloud console ( Preview ). From the Models > Tuning page, you can configure Python code or model-based reward functions, test reward logic against sample prompts before launching a job, track training and evaluation metrics in real time, and test tuned...

PreviewAI agentsLLMsObservabilitySource

Gemini Enterprise Agent PlatformSep 22, 2026

Anthropic's Claude Opus 5.5

Claude Opus 5.5 is available in Model Garden.

UpdateLLMsSource

Gemini Enterprise Agent PlatformSep 14, 2026

Gemini model deprecation and retirement date updates

The retirement and deprecation dates for the following Gemini models have been updated: Gemini 2.5 Flash Image ( gemini-2.5-flash-image ) : Deprecated and scheduled for retirement on March 15, 2027 (extended from October 2, 2026). Migrate to Gemini 3.1 Flash-Lite Image ( gemini-3.1-flash-lite-image ).

DeprecationLLMsSource

Gemini Enterprise Agent PlatformSep 14, 2026

Cyber Verification Program for Claude is available in Preview

Anthropic's Cyber Verification Program (CVP) is available in Preview on Gemini Enterprise Agent Platform. CVP enables verified organizations to use supported Claude models (Claude Opus 4.7, Claude Opus 4.8, Claude Sonnet 5, and Claude Opus 5) for legitimate defensive cybersecurity tasks with default dual-use restrictions lifted.

PreviewAI agentsLLMsSecuritySource

Gemini Enterprise Agent PlatformSep 10, 2026

Provisioned Throughput: Support for multiple pending orders and change requests

Provisioned Throughput now directly supports from the self service console the ability to schedule multiple new orders at the same time and change requests across multiple orders within the same project. For more information, see Purchase Provisioned Throughput .

UpdatePerformanceSource

Also shipped on Sep 18, 2026

Databricks Databricks AppsSep 18, 2026

Databricks Apps telemetry is now generally available

Configuring telemetry for your Databricks apps is now generally available. Databricks Apps telemetry collects traces, logs, and metrics and persists them to Unity Catalog tables using the OpenTelemetry (OTel) protocol.

GAGovernanceObservabilityDeveloper toolsSource

Databricks LakebaseSep 18, 2026

Lakebase Search is generally available

Lakebase Search is now generally available. It brings scalable vector and keyword search to Lakebase projects through two Postgres extensions, so you can run semantic and exact-term search in a single database without a separate search stack: lakebase_vector adds the lakebase_ann index type for approximate nearest-neighbor vector search.

GAVector searchSQLPostgresSource

Snowflake SnowflakeSep 18, 2026

Apache Iceberg™ tables: Partition evolution (General availability)

With this release, we're pleased to announce the general availability of partition evolution for Snowflake-managed Iceberg tables. You can now change a table's partition specification after you create the table by adding, dropping, or replacing partition fields, without rewriting existing data.

GAApache IcebergSource

Microsoft Microsoft FoundrySep 18, 2026

[In preview] Public Preview: Foundry Routines in Foundry Agent Service

In public preview, Foundry Agent Service adds Foundry Routines, a native trigger primitive for running published agents automatically. Production agents often need to run on a schedule or when a business event occurs, and today that means assembling exter

PreviewAI agentsSource

Microsoft Microsoft FoundrySep 18, 2026

[Launched] Generally Available: Enable and disable controls for Microsoft Foundry agents in Agent 365

Microsoft Foundry now exposes enable and disable actions for Foundry agent objects within the Agent 365 governance surface in Microsoft Admin Center, generally available. Administrators can control whether a Foundry agent is available for use across their

GAAI agentsGovernanceSource

Microsoft Microsoft FoundrySep 18, 2026

[In preview] Public Preview: Network egress controls for hosted agents in Microsoft Foundry

In public preview, Microsoft Foundry now lets customers govern the outbound connections a hosted agent can make. Customers author ordered rules matched on destination host, including FQDN with wildcards such as *.contoso.com, with actions to allow, deny,

PreviewAI agentsSource