Gemini Enterprise Agent Platform release notes

Anthropic's Claude Opus 5

Claude Opus 5 is available in Model Garden.

Gemini 3.6 Flash and 3.5 Flash-Lite are generally available (GA)

Gemini 3.6 Flash and Gemini 3.5 Flash-Lite are now generally available (GA) and available for production use. These models are designed to improve upon their predecessors' capabilities, including improved token usage and improved document understanding. See the linked model information pages for more information.

This release includes some potentially breaking changes from previous Flash and Flash-Lite models:

• Sampling parameters: Custom values for temperature, top-K, and top-P are not supported and will be ignored if set.
• Penalty parameters: Custom values for frequency and presence penalty parameters are not supported. Setting these will result in an API error.
• API turn structure: API requests where the last input turn has a role of Model are no longer supported and will return an error:
  • Interactions API: Requests where the last object in the input array has "type": "model_output" will fail.
  • GenerateContent API: Requests where the last object in the contents array has "role": "model" will fail.

Open model endpoint deprecations

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

• deepseek-ocr-maas
• deepseek-r1-0528-maas
• deepseek-v3.2-maas
• deepseek-v3.1-maas
• glm-5-maas
• glm-4.7-maas
• gpt-oss-20b-maas
• kimi-k2-thinking-maas
• llama-3.3-70b-instruct-maas
• minimax-m2-maas
• multilingual-e5-large-instruct-maas
• multilingual-e5-small-maas
• qwen3-235b-a22b-instruct-2507-maas
• qwen3-coder-480b-a35b-instruct-maas
• qwen3-next-80b-a3b-instruct-maas
• qwen3-next-80b-a3b-thinking-maas

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 applications created before July 1, 2026, using Agent Studio.

If you downloaded, generated, or deployed web application code from Agent Studio before July 1, 2026, regenerate the app from Agent Studio and deploy the new version. For more information, see Quickstart: Deploy your Agent Studio prompt as a web application

The updated backend code includes strict domain allowlist validation, ensuring that destination hostnames for the /api-proxy endpoint end with allowed Google Cloud domains, such as *-aiplatform.clients6.google.com

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 accessible. Update your code to use either gemini-3.1-flash-image or gemini-3-flash-image instead.

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 structures with static schemas populated and updated using LLMs. By defining a fixed schema, you ensure your agents have immediate, low-latency access to evolving information without the need for expensive search operations during a session.

For details, see Memory profiles.

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:

• gemini-2.5-flash-lite-preview-09-2025
• gemini-2.5-flash-preview-05-2025
• gemini-3.1-flash-lite-preview

See Migrate to the latest Google models for information on how to migrate your project.

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 shut down on August 20, 2026. After this date, Google Agent Platform Model as a Service (MaaS) will no longer serve these models. Specifically, API requests directed to the https://aiplatform.googleapis.com/v1/projects/<your-project>/locations/global/endpoints/openapi/chat/completions endpoint using the Grok 4.1 model IDs will fail and return a 400 error. To maintain service, migrate your applications to newer xAI models (such as Grok 4.2 or Grok 4.3) or choose an alternative model from the Google Cloud Model Garden.

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 must use one of the global, us, or eu endpoints in the model's resource name (for example, projects/{project}/locations/us/publishers/google/models/gemini-embedding-2). Memory Bank does not support using regional locations (for example, us-central1) for gemini-embedding-2.

For details, see Similarity search configuration.

Memory Bank IngestEvents is generally available (GA)

The Memory Bank IngestEvents API is generally available. The IngestEvents API decouples event ingestion from memory generation, letting you continuously stream content to Memory Bank and configure when memory generation is triggered.

This GA release includes the following features:

• Carry over context between generation windows: Use the overlap_event_count parameter to re-include already-processed events at the start of the next window to keep memories coherent.
• Configure memory revisions for ingested events: Use revision_labels, revision_ttl, or disable_memory_revisions to customize how generated revisions are managed.
• Attach metadata to memories: Use the metadata and metadata_merge_strategy configuration parameters to store structured information alongside generated memories.

For details, see Ingest events.

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 Agent Platform.

Designed to decipher the functional regulatory code of the human genome, AlphaGenome analyzes large-scale DNA sequences at single-base resolution to predict how genetic variations affect molecular and biological mechanisms like gene expression, chromatin accessibility, and RNA splicing. For information on how to use AlphaGenome in Agent Platform, see the documentation.

Provisioned Throughput: Multiple pending new orders GA

The ability to submit multiple pending orders is generally available. you can submit up to seven Google model orders for the same model and region. See Multiple pending orders.

Anthropic's Claude Sonnet 5

Claude Sonnet 5 is available in Model Garden.

Gemini 3.5 Flash default model for Memory Bank

The default model used for Memory Bank generation is now Gemini 3.5 Flash instead of Gemini 2.5 Flash. For information, see Set up Memory Bank.

Semantic Governance Policies available in Public Preview

Semantic governance policies and the policy engine are now available in Preview. Semantic governance policy provides an intelligent security and compliance layer that evaluates an AI agent's proposed tool calls against user intent and organizational business rules at runtime.

Key capabilities include:

• Natural Language Constraints (NLC): Author declarative business rules and security guardrails in plain English without needing to write code or redeploy agent applications.
• Layered Intent Gating: Intercepts agent tool calls at runtime to verify alignment with trusted user intent and prevent unauthorized actions, rogue tool use, and data exfiltration.
• Granular Scoping: Apply constraints globally across all tools for an agent or target specific tools and parameters (e.g., enforcing strict financial limits or geographic restrictions).
• Agent Skills Lifecycle Governance: Protects agents from context poisoning and supply-chain exploits by governing the dynamic loading of Agent Skills (tool packages) during sessions.
• Dry Run Mode: Test and observe policy verdicts in Log Explorer before enforcing them on active traffic.

For more information, see Semantic governance policies overview.

Provisioned Throughput: Email notifications GA

The ability to get email notifications for Provisioned Throughput events is generally available. See Get email notifications.

Administrative correction to Gemini Online Inference API on Gemini Enterprise Agent Platform SLA

We made an administrative correction to the Gemini Online Inference API on Gemini Enterprise Agent Platform Service Level Agreement (SLA), addressing a clerical issue.

AI security findings in Agent Platform

Viewing AI security findings and posture management summaries in Gemini Enterprise Agent Platform is generally available.

With this release, the Security dashboard introduces the Top security findings widget.

Also, specific features within the AI security widgets are available in Preview, including the following:

• Vulnerability findings and threat monitoring for agent runtimes (such as Cloud Run)
• Historical content violation trends (Violations over time)

For more information, see View security findings.

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 pass through the gateway. This feature is generally available (GA).

For more information, see Configure Model Armor on a gateway.

Supervised fine-tuning available for Gemini 3.1 Flash Lite and Gemini 3.5 Flash in Public Preview

Supervised fine-tuning is now available for the gemini-3.1-flash-lite and gemini-3.5-flash models in Preview. Model tuning for Gemini 3.1 Flash Lite and Gemini 3.5 Flash is restricted to us-central1 and europe-west4 and tuned model serving is restricted to the us and eu multi-region endpoints.

See About supervised fine-tuning for more information.

Provisioned Throughput support for supervised fine-tuned Gemini 3 model inference.

Provisioned Throughput can be used to assure supervised fine-tuned inference using the same quota. Supervised fine-tuned inference for Gemini 3 models incurs a higher burndown rate compared to base model inference. Learn more here.

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, whether they occur between users and agents, agents and tools, or among agents themselves.

For details, see Agent Gateway overview.

Agent Registry is generally available (GA)

Agent Registry is generally available (GA). Agent Registry is a centralized catalog for discovering and registering agents and Model Context Protocol (MCP) servers.

The following features are available in Agent Registry for the GA launch stage:

• API v1 and client libraries: The v1 version of the Agent Registry API is available. Cloud client libraries are available in C#, Go, Java, Node.js, PHP, Python, and Ruby.
• A2A v1 support: Agent Registry supports Agent-to-Agent (A2A) protocol version 1.0, letting you explicitly declare transport endpoints and bindings inside the supportedInterfaces array, in addition to the existing 0.3 schema support.
• Terraform support: Terraform scripts for Application Default Credentials (ADC) have graduated to General Availability. You can use Terraform to configure and manage your agents, MCP servers, endpoints, and bindings.

Known limitations:

• Access Transparency and Access Approval: Access Transparency logs, which provide visibility into when Google personnel access your content, and Access Approval controls aren't available for Agent Registry configurations.
• Data Residency: If you configure the resource location constraint in your organization policy, Agent Registry enforces the constraint when you register a resource. However, detective controls for data residency compliance reporting are limited.

For more information, see the Agent Registry overview.

The Agent Identity API (agentidentity.googleapis.com) is available in Preview. This new API replaces the legacy IAM Connectors API (iamconnectors.googleapis.com) for managing auth providers and agent identities.

During the preview migration period, both APIs operate side-by-side. Existing auth providers are automatically mirrored to the new V2 resource hierarchy (authProviders/), allowing you to migrate your IAM policies, agent code, and client applications without downtime.

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, see Supported locations for agents. Note that Customer-Managed Encryption Keys (CMEK) cannot be used if your Memory Bank or Sessions instance is configured to use the global endpoint.

Reinforcement Learning fine-tuning is available for Gemini 3.5 Flash in Public Preview

Reinforcement Learning fine-tuning is now available for the gemini-3.5-flash models in Preview. Model tuning for Gemini 3.5 Flash is restricted to us-central1 and europe-west4, and tuned model serving is restricted to the us and eu multi-region endpoints.

See About reinforcement learning fine-tuning for more information.

Anthropic's Claude Fable 5

Claude Fable 5 is available in Model Garden.

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 Throughput. Use Gemini 3.1 Flash-Lite, Gemma 4, or more recent Gemini releases.

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 Generally Available.

With this release, Gemini 3.1 Flash Image and Gemini 3 Pro Image support 4K image outputs in Preview.

Also supported in this release, Gemini 3.1 Flash Image supports video inputs in Preview. You can use video inputs to generate thumbnails or representative images of videos.

For more information, see the following:

• Gemini 3.1 Flash Image (Nano Banana 2)
• Gemini 3 Pro Image (Nano Banana Pro)

Agent Platform Gemini 3.1 Flash Image Preview and Gemini 3 Pro Image Preview deprecation

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 disruption.

The following are the discontinued endpoints and recommended endpoint migration:

Anthropic's Claude Opus 4.8

Claude Opus 4.8 is available in Model Garden.

User ID logging now included with agent logs when you opt in to "Enable logging of prompt inputs and response outputs"

Prompt input and response output logging now includes the user.id field. This addition allows better tracking of anomalous tool interactions.

For details on configuration, see Write traces for an agent.

The Gemini Deep Research Agent released 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 synthesizes complex, multi-step research workflows across the public web and private enterprise data to generate comprehensive, cited reports.

For more information, see Use the Gemini Deep Research Agent.

Agent Platform Sandboxes

Additional Agent Platform sandbox features are now available:

• Computer use (Preview): Enables agents to automate browser-based tasks within an isolated web browser environment. You can control the browser using the API or connect directly using the Chrome DevTools Protocol (CDP).
• Custom container sandboxes (Preview): Bring your own container (BYOC) to run custom workloads with specialized dependencies hosted in Artifact Registry.
• Sandbox templates (Preview): Define sandbox specifications as reusable templates relying on pre-warmed pools to facilitate rapid, reliable startups.
• Sandbox snapshots (Preview): Save the exact state of your sandbox environment (including dependencies and file systems) and restore it to a new sandbox.

Identify the agents with the most content security violations

The Security dashboard displays the top 10 agents with the most content violations detected by Model Armor. The list shows the agent ID of each agent and the number of violations detected for that agent. For more information, see Monitor content security.

Supervised fine-tuning available for Gemini 3.1 Flash Lite (Preview)

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 europe-west4 and tuned model serving is restricted to the us and eu multi-region endpoints.

See About supervised fine-tuning for more information.

Set media resolution at a Part-level for data when using supervised fine-tuning

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 level.

See the following media type–specific pages for more information:

• Document tuning
• Image tuning
• Video tuning

Gemini 3.5 Flash is generally available (GA)

For details, see the model specifications page.

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 between the different active revisions. This enables canary deployments and safe testing of new agent versions. For more information, see Manage revisions and traffic.

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 as self-contained packages, including instructions, code, and documentation, to enhance agent abilities.

For more information, see:

• Skill Registry overview
• Create and manage skills

Managed Agents API on Agent Platform released in Preview

The Managed Agents API on Agent Platform has been released in Preview.

This feature allows you to build and scale autonomous agents, including those built from configuration using the Antigravity harness. These agents run in a fully managed and isolated sandbox environment, equipped with tools and skills, and can be interacted with via a dedicated API.

For more information, see the following:

• Managed Agents API on Agent Platform overview
• Create and manage agents
• Interact with agents
• Managed Agents API on Agent Platform sandbox environment

AI Content Detection API available

AI Content Detection API is available in Preview. For details see AI Content Detection.

Provisioned Throughput for Gemini now supports latency SLA

Provisioned Throughput now provides a tokens per second latency SLA, covering generation speed from the first returned token to the last.

For more information, see the Gemini Enterprise Agent Platform Online Inference Service Level Agreement (SLA).

Memory Bank and Sessions support for multi-regional and global endpoints is in Preview. For more, see Supported locations for agents in Agent Platform.

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 Throughput. It is ideal for business-critical workloads with fluctuating or unpredictable traffic patterns.

For more information, see Priority PayGo.

You can purchase Provisioned Throughput for Gemma 4. To learn more, see the list of supported open models.

Gemini Distillation Service Early Access

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

Improvements to the Provisioned Throughput orders page have now made it possible to:

• View all scheduled orders by using the Start Date column.
• Enable filtering and sorting of orders by using column names.
• Download all order data to a CSV file (including across all regions).

See View standard Provisioned Throughput orders.

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 the model information card.

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

Fixed an issue with Audio track extraction (Gemini Embedding 2 only) where the audio_track_extraction feature did not work. For more information, see Issue #504505771.

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:

• Upgrades to improve 4K outputs and efficiency in both models
• Gemini 3.1 Flash Image Preview and Gemini 3 Pro Image Preview will now return a maximum of 1 thought image.
• The image_size parameter for Gemini 3.1 Flash Image Preview now accepts "512", "512p", "512P", "512PX", "512px" to generate 0.5MP resolution output images.
• The default thinking level for Gemini 3.1 Flash Image Preview changed to Minimal.

Improved transcription quality for Gemini Live API

You can now improve transcription quality for multilingual automatic speech recognition (ASR) by using the [input/output]_audio_transcription.language_codes field.

For more information, see Enable audio transcription for the session.

Asynchronous function calling with Live API

Asynchronous function calling is now available in public preview in Gemini Live API. You can run functions in parallel with conversation, manage background processing, and handle function responses with policies including SILENT, WHEN_IDLE, and INTERRUPT. For more information, see Asynchronous function calling with Gemini Live API.

Vertex AI to Gemini Enterprise Agent Platform naming changes

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

Initial release of Gemini Enterprise Agent Platform

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 AI is now under Gemini Enterprise Agent Platform > Models.
• Change Agent Builder is now part of Gemini Enterprise Agent Platform. Features have been renamed as follows:
  • Agent Engine is now Agent Runtime.
  • Agent Builder Sessions is Agent Platform Sessions.
  • Memory Bank is now Agent Platform Memory Bank.
• Change Agent Runtime now supports long-running operations (up to 7 days).
• Change Agent Runtime now supports sub-second cold starts.
• Change Provisioning for Agent Runtime has been reduced to less than 1 minute.
• Release You can now use your own custom-built containers when you deploy agents with Agent Runtime.
• Change When creating a Session, you can specify your own session ID.
• Release Memory Bank now enables continuous event streaming with automated memory generation triggered by configurable criteria like event count or idle time. For more information, see Ingest events.
• Release Memory Bank now automatically maintains an immutable version history of memories through revision resources. For more information, see Memory revisions.
• Release Agent Identity for General Availability. Agent Identity helps let your agent securely authenticate to MCP servers, cloud resources, endpoints, and other agents, either acting as itself or acting on behalf of the end user.
• Release Agent Gateway for Private Preview. Agent Gateway is the networking component of the Gemini Enterprise Agent Platform ecosystem. It secures and governs connectivity for all agentic interactions, whether they occur between users and agents, agents and tools, or among agents themselves.
• Release Agent Registry for Public Preview. Agent Registry is a centralized, unified catalog that lets you store, discover, and govern Model Context Protocol (MCP) servers, tools, and AI agents within Google Cloud.
• Release New IAM governance policies are available in Private Preview.
• Release Agent Observability for Preview. Agent Observability in Gemini Enterprise Agent Platform provides comprehensive visibility into the performance, behavior, and health of your deployed agents and Model Context Protocol (MCP) servers. By monitoring key metrics, tracing execution paths, and observing your multi-agent system as a whole, you can diagnose issues, optimize resource consumption, and improve the reliability of your agents.
• Release Gemini Embedding 2 (gemini-embedding-2) for General Availability.
• Release The Gemini Deep Research Agent, a pre-built agent designed to help you plan, execute, and synthesize multi-step research tasks. It uses Gemini 3.1 Pro to bridge the gap between public web data and private enterprise context by simultaneously grounding research across three distinct, high-fidelity data streams.
• Release Agent Platform remote MCP server for General Availability. Support for Model Context Protocol (MCP) use is available for Agent Platform.
• Change Google Cloud console navigation: The navigation menus under Agent Platform (formerly Vertex AI) and Data Analytics have been updated to centralize agentic products and features. Bookmarked links will continue to work via automatic redirects.