Gemini Enterprise Agent Platform

xAI's Grok 4.6 <a href="https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/grok/grok-4-6">Grok 4.6</a> is available in <a…

CodeMender updates: Model support This release introduces updates to CodeMender: • Gemini 3 Flash removal: Gemini 3 Flash (gemini-3-flash-preview) is no longer supported as a model backend for…

Monitor semantic governance policies with built-in metrics (Preview) Built-in Cloud Monitoring metrics for the semantic governance policy engine are available in Preview. You can now observe request…

AlphaFold 3 is generally available AlphaFold 3 is now generally available (GA) and available for approved users for commercial research use. AlphaFold 3 Google DeepMind's and Isomorphic Labs' deep…

Gemini 3.7 Flash is generally available <a href="https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-7-flash">Gemini 3.7 Flash</a> is now generally available (GA) and…

Agent Runtime: ADK telemetry metrics Agents deployed to Agent Runtime with Agent Development Kit (ADK) 2.6.0 or later can emit gen_ai application metrics that follow OpenTelemetry's generative…

CodeMender CLI: Sandbox enabled by default This release updates the CodeMender CLI default behavior: • Sandbox enabled by default: The CLI now runs commands inside the process-level sandbox by…

This release updates the CodeMender CLI default behavior: • Sandbox enabled by default: The CLI now runs commands inside the process-level sandbox by default to protect your workstation. You can…

This release introduces process-level sandboxing, automatic update checks, and other improvements to the CodeMender CLI (Preview): • Process-level sandboxing: To safeguard your workstation against…

Process-level sandboxing and auto-updates (Preview) This release introduces process-level sandboxing, automatic update checks, and other improvements to the CodeMender CLI (Preview): •…

This release introduces process-level sandboxing and automatic update checks to the CodeMender CLI (Preview): • Process-level sandboxing: To safeguard your workstation against unintended file…

Anthropic's Claude Opus 5 <a href="https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/opus-5">Claude Opus 5</a> is available in Model Garden.

Gemini 3.6 Flash and 3.5 Flash-Lite are generally available (GA) <a href="https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-6-flash">Gemini 3.6 Flash</a> and <a…

Open model endpoint deprecations The following open model endpoints are deprecated and will be retired on October 21, 2026. For more information, see <a…

Security update for Server-Side Request Forgery (SSRF) in Agent Studio This release fixes a Server-Side Request Forgery (SSRF) vulnerability in the auto-generated /api-proxy backend endpoint for web…

Gemini 3.1 Flash Image Preview and 3 Pro Image Preview are retired The Nano Banana preview models gemini-3.1-flash-image-preview and gemini-3-pro-image-preview have been retired and are no longer…

Memory Bank memory profiles are generally available (GA) Memory profiles in Memory Bank are generally available (GA). Memory profiles allow you to generate structured profiles, which are data…

Retirement for preview models for 2.5 Flash, 2.5 Flash-Lite, and 3.1 Flash-Lite The following preview model endpoints have been retired and are no longer accessible: •…

Grok 4.1 models deprecation The Grok 4.1 model family (including xai/grok-4.1-fast-reasoning and xai/grok-4.1-fast-non-reasoning) on the Gemini Enterprise Agent Platform is deprecated and will be…

Memory Bank support for Gemini Embedding 2 Memory Bank supports the gemini-embedding-2 model for similarity search configurations. When you configure gemini-embedding-2 as the embedding model, you…

AlphaGenome released for Gemini Enterprise Agent Platform AlphaGenome, Google DeepMind's state-of-the-art genomics foundation model, is now available for deployment and use with Gemini Enterprise…

The following Provisioned Throughput features are generally available: • Change an order: See <a…

Model Armor for Agent Gateway in General Availability You can enable Model Armor on an Agent Gateway resource to apply your organization's content security guardrails to prompts and responses that…

AI security findings in Agent Platform Viewing AI security findings and posture management summaries in Gemini Enterprise Agent Platform is <a…

Agent Gateway in General Availability Agent Gateway is the networking component of the Gemini Enterprise Agent Platform ecosystem. It secures and governs connectivity for all agentic interactions,…

Agent Observability is generally available (GA) This release provides visibility into the performance, behavior, and health of deployed agents and Model Context Protocol (MCP) servers directly…

Agent Registry is generally available (GA) Agent Registry is <a href="https://cloud.google.com/products#product-launch-stages">generally available (GA)</a>. Agent Registry is a centralized catalog…

The Agent Identity API (agentidentity.googleapis.com) is available in <a href="https://cloud.google.com/products#product-launch-stages">Preview</a>. This new API replaces the legacy IAM Connectors…

Memory Bank and Sessions global and multi-regional endpoints GA Memory Bank and Sessions support for multi-regional and global endpoints is now in General Availability (GA). For more information,…

Anthropic's Claude Fable 5 <a href="https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/fable-5">Claude Fable 5</a> is available in Model Garden.

Updates to abuse monitoring and zero data retention documentation Documentation for abuse monitoring, zero data retention, and responsible AI has been updated to align with the Advanced AI Safety…

Gemini 2.0 Flash and Gemini 2.0 Flash-Lite are discontinued Gemini 2.0 Flash and 2.0 Flash-Lite are discontinued and are no longer available. This includes both model serving and Provisioned…

Gemini Enterprise Agent Platform Gemini 3.1 Flash Image Preview and Gemini 3 Pro Image Preview are deprecated. We recommend that you update your model endpoints before July 17, 2026, to avoid service…

Anthropic's Claude Opus 4.8 <a href="https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/opus-4-8">Claude Opus 4.8</a> is available in Model Garden.

<a href="https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/partner-models/claude/opus-4-8">Claude Opus 4.8</a> is available in Model Garden.

Agent Platform Gemini 3.1 Flash Image and Gemini 3 Pro Image Gemini Enterprise Agent Platform Gemini 3.1 Flash Image and Gemini 3 Pro Image are <a…

Additional Agent Platform <a href="https://docs.cloud.google.com/gemini-enterprise-agent-platform/scale/sandbox">sandbox</a> features are now available: • <a…

The Gemini Deep Research Agent is in Preview. The Gemini Deep Research Agent is a managed AI agent that plans, executes, and synthesizes complex, multi-step research workflows across the public web…

The Gemini Deep Research Agent releaased in Preview The Gemini Deep Research Agent has been released in Preview. The Gemini Deep Research Agent is a managed AI agent that plans, executes, and…

Agent Platform Sandboxes Additional Agent Platform <a href="https://docs.cloud.google.com/gemini-enterprise-agent-platform/scale/sandbox">sandbox</a> features are now available: • <a…

Supervised fine-tuning is now available for limited support for the gemini-3.1-flash-lite model. During this period, model tuning for Gemini 3.1 Flash Lite is restricted to us-central1 and…

Supervised fine-tuning now supports Part-level mediaResolution declarations for images, videos, and PDFs. Part-level media resolution declarations also support the MEDIA_RESOLUTION_ULTRA_HIGH…

Memory Bank and Sessions support for multi-regional and global endpoints is in <a href="https://cloud.google.com/products#product-launch-stages">Preview</a>. For more, see <a…

Managed Agents API on Agent Platform Managed Agents API on Agent Platform is in Preview. This feature allows you to build and scale autonomous agents, including those built from configuration using…

Manage and discover agent skills with Skill Registry. Manage and discover agent skills with the Skill Registry, in public preview. This secure, private, and low-latency repository stores skills…

Gemini 3.5 Flash is generally available (GA) For details, see the <a href="https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-5-flash">model specifications page</a>.

Manage agent revisions and traffic splitting Agent revisions and traffic splitting are now available in public preview. You can create immutable revisions of deployed agents, and split traffic…

AI Content Detection API available AI Content Detection API is available in <a href="https://cloud.google.com/products#product-launch-stages">Preview</a>. For details see <a…

Manage agent revisions and traffic splitting Agent revisions and traffic splitting are now available in public preview. You can create immutable revisions of deployed agents, and split traffic…

Priority PayGo is generally available (GA) Priority PayGo is a consumption option that provides more consistent performance than standard PayGo without the upfront commitment of Provisioned…

You can purchase Provisioned Throughput for Gemma 4. To learn more, see the list of <a…

Gemini Distillation Service Early Access We're introduction Gemini Distillation Service in Early Access. For information about requesting access, see <a…

Gemini 3.1 Flash-Lite is now generally available Our most cost-efficient Gemini model, 3.1 Flash-Lite, is out of preview and is now generally available. For technical information on this model, see…

You can purchase Provisioned Throughput for Gemini 3.1 Flash-Lite. To learn more, see the <a…

Agent Platform Gemini 3.1 Flash Image and Gemini 3 Pro Image Gemini Enterprise Agent Platform Gemini 3.1 Flash Image Preview and Gemini 3 Pro Image Preview are introducing the following changes: •…

Fixed an issue with Audio track extraction (Gemini Embedding 2 only) where the audio_track_extraction feature did not work. For more information, see <a…

Improved transcription quality for Gemini Live API You can now improve transcription quality for multilingual automatic speech recognition (ASR) by using…

Asynchronous function calling with Live API Asynchronous function calling is now available in <a href="https://cloud.google.com/products#product-launch-stages">public preview</a> in Gemini Live API.…

The table below lists all of the features that have been transitioned from Vertex AI and what their new names are in Agent Platform.

The following known issues affect Gemini Enterprise Agent Platform: • Audio track extraction (Gemini Embedding 2 only): The audio_track_extraction feature does not work. For more information, see <a…

This initial release includes (but is not limited to) the following releases or changes: • Change Vertex AI is now part of Gemini Enterprise Agent Platform. Information on model support for Vertex…