AI PlatformAI-native
Gemini Enterprise Agent Platform
Google Cloud's comprehensive platform to build, scale, govern and optimize enterprise-grade AI agents; the evolution of Vertex AI.
Regional availability·42 regions
- us-central1 (Iowa)
- us-east1 (South Carolina)
- us-east4 (N. Virginia)
- us-east5 (Columbus)
- us-south1 (Dallas)
- us-west1 (Oregon)
- us-west4 (Las Vegas)
- northamerica-northeast1 (Montréal)
- southamerica-east1 (São Paulo)
- europe-west1 (Belgium)
- europe-west2 (London)
- europe-west3 (Frankfurt)
- europe-west4 (Netherlands)
- europe-west6 (Zurich)
- europe-west9 (Paris)
- europe-west12 (Turin)
- europe-north1 (Finland)
- europe-southwest1 (Madrid)
- europe-central2 (Warsaw)
- me-west1 (Tel Aviv)
- me-central1 (Doha)
- me-central2 (Dammam)
- asia-east1 (Taiwan)
- asia-east2 (Hong Kong)
- asia-northeast1 (Tokyo)
- asia-northeast2 (Osaka)
- asia-northeast3 (Seoul)
- asia-south1 (Mumbai)
- asia-south2 (Delhi)
- asia-southeast1 (Singapore)
- asia-southeast2 (Jakarta)
- australia-southeast1 (Sydney)
- australia-southeast2 (Melbourne)
- africa-south1 (Johannesburg)
Data residencySovereign cloud
Supported models
17SLM/LLM
Regions
42totalRegions
SDK / Languages
4python, javascript…
Uptime SLA
99.5%
Robotics-Ready
✓
Description
Gemini Enterprise Agent Platform is Google Cloud's unified platform announced on April 22, 2026 at Cloud Next '26. It is the direct evolution of Vertex AI — all existing Vertex AI services and future roadmap updates are delivered exclusively through Agent Platform. The platform provides full-stack infrastructure for building, deploying, governing, and optimizing enterprise-grade AI agents.
MLOps LifecycleMLOps LifecycleFull model lifecycle: registry, feature store, prompt management, monitoring and human-in-the-loop.
Model Registry
Versioning — model artifact versioning
Approval workflows — approval workflow before production
Immutable artifacts — immutability of stored versions
Lineage tracking — tracking data and model relationships
3 / 4 supported · 1 unsupported hidden
Feature Store
Online serving — real-time feature serving
Offline storage — feature storage for training
Streaming ingestion — streaming ingestion (Kafka, Flink)
3 / 3 supported · none unsupported
Prompt Management
Prompt registry — central prompt repository
Versioning — prompt versioning and history
Testing frameworks — A/B testing and prompt evaluation
3 / 3 supported · none unsupported
Monitoring
Data drift detection — input data drift detection
Concept drift detection — concept drift detection
Hallucination monitoring — LLM hallucination monitoring
Bias evaluation tools — bias evaluation tooling
3 / 4 supported · 1 unsupported hidden
Human-in-the-Loop
Labeling services — data labeling tools
RLHF workflows — reinforcement learning from human feedback
Manual override — manual override of model decisions
1 / 3 supported · 2 unsupported hidden
Data & KnowledgeData & Knowledge ManagementData connectors, vector database integration, native vector search and data management (PII, provenance, synthetic data).
ApplicationsAI ApplicationsDomains and use cases this platform is best suited for — from RAG and fine-tuning to scientific research.
SecurityEnterprise SecurityCertifications, access controls and data-protection features essential for corporate deployments and cloud privacy compliance.
Developer EcosystemDeveloper EcosystemDeveloper resources: available SDKs, supported programming languages, and infrastructure features and model-deployment methods.
SDK Languages
PyPythonJSJavaScriptTSTypeScriptGoGo
API Type
RESTgRPC
Community & resources
Templates library
Quickstarts
API Reference
Tutorials
Pricing & Business ModelPricing & Business ModelBilling models (usage-based, provisioned throughput), resource limits and SLA parameters (uptime, support tiers).
Pricing models
Usage-based
Token-based
Resource quotas
Per project
Per user
Cost alerting
SLA & Support
99.5%uptime SLA
StandardEnterprise 24/7
Supported AI Models
Robotics & Humanoids ExtensionRobotics & Humanoids ExtensionSimulation engines (Isaac Sim, Gazebo, MuJoCo), communication protocols (ROS2, MQTT, Zenoh), robotics standards (URDF, OpenUSD) and edge orchestration.
Robotics-Ready
Robotics standards
- URDF Support
- OpenUSD Interoperability
- Sim-to-Real Pipelines
Edge Orchestration
- OTA updates (over-the-air)
- Real-time kernel support
SourcesDocumentation VaultCentralized hub of links to official sources, technical guides, repositories and release notes.
SustainabilitySustainabilityCarbon footprint, renewable-energy share powering data centers, and energy-efficiency metrics (e.g. PUE).
Carbon footprint tracking
64% renewable energy
Average annual Power Usage Effectiveness (PUE) across Google data centers is 1.09 (vs industry average ~1.56). Goal: 100% carbon-free energy 24/7 across all data centers and offices by 2030.