Model platforms / Google Cloud
Gemini Enterprise Agent Platform
Gemini Enterprise Agent Platform (formerly Vertex AI): Model Garden, generative AI APIs and agent tools on Google Cloud. Formerly Vertex AI.
Pay per use, by model. Pay per token on Standard PayGo, at a different price for each model; Provisioned Throughput is a fixed-term commitment. Official page
MCP serversYes · “Agent Registry”
Agents register and use remote MCP servers through Agent Registry and Agent Gateway.
It provides a unified catalog that lets you securely store, discover, and manage Model Context Protocol (MCP) servers, tools, standalone skills (Preview), and AI agents across your organization.
Claude modelsYes · “Claude on Google Cloud”
Claude models run as a managed API; pay as you go or Provisioned Throughput.
The following models are available from Anthropic to use in Gemini Enterprise Agent Platform.
OpenAI GPT modelsPartly · “GPT 6.0 Astra”
GPT 6 models are in private preview; open-weight gpt-oss-120b is a managed API.
GPT 6.0 Astra is the highest-capability partner model from OpenAI for complex multi-step reasoning, difficult engineering tasks, and long-horizon agent workflows.
Gemini modelsYes · “Google Models”
Google's own Gemini models are the platform's flagship models.
Flagship models developed by Google, including Gemini, Gemma, Veo, and Lyria.
Open-weight modelsYes · “Open Models”
Open-weight models run as managed APIs or deploy to your own endpoints from Model Garden.
Support for a wide range of open-weights models like DeepSeek, Llama, and Qwen.
Fine-tuningYes · “Model tuning”
Supervised, preference and reinforcement tuning for Gemini; open models can be tuned too.
Model tuning works by providing a model with a training dataset that contains a set of examples of specific downstream tasks.
Reserved capacityYes · “Provisioned Throughput”
Fixed-cost subscription in 1-week to 1-year terms that reserves throughput per model.
Provisioned Throughput is a fixed-cost, fixed-term subscription available in several term-lengths that reserves throughput for supported generative AI models on Gemini Enterprise Agent Platform.
Content filtersYes · “Content filters”
Configurable safety filters block harmful responses by category and threshold.
To further enhance safety and minimize misuse, you can configure content filters to block potentially harmful responses.
Audit logsYes · “Data Access audit logs”
Cloud Audit Logs record admin and data access on models and endpoints.
To get audit logs about the usage of your generative models and model endpoints, enable Data Access audit logs for Gemini Enterprise Agent Platform.
Data residencyYes · “Data residency”
Stored data stays in the chosen location; the global endpoint gives no processing guarantee.
When you store data on Agent Platform (such as custom model weights or metadata), it remains physically stored in the specific Google Cloud location you chose.
Your own encryption keysYes · “CMEK”
Customer-managed keys in Cloud KMS; Google says security controls don't cover preview models.
If you want to control your encryption keys, then you can use customer-managed encryption keys (CMEKs) in Cloud KMS with CMEK-integrated services including Agent Platform.
Private networkYes · “Private Service Connect”
Private Service Connect over Cloud VPN or Interconnect keeps traffic private.
On-premises hosts can reach Agent Platform either through the public internet or privately through a hybrid networking architecture that uses Private Service Connect (PSC) over Cloud VPN or Cloud Interconnect.
Not used for trainingYes · “Training restriction”
Google won't train on customer data without permission, for GA and preview models.
Google won't use your data to train or fine-tune any AI/ML models without your prior permission or instruction.
SOC 2 and ISO 27001Yes · “ISO/IEC 27001”
Listed in scope on Google Cloud's ISO 27001 page and its SOC 2 Type II page.
Generative AI on Gemini Enterprise Agent Platform (formerly Generative AI on Vertex AI)
HIPAA BAAYes · “Google Cloud BAA”
Gemini Enterprise Agent Platform and Generative AI on Agent Platform are listed under the BAA.
The Google Cloud BAA includes Google Cloud's entire infrastructure (all regions, all zones, all network paths, all points of presence), and the following products:
FedRAMPYes · “FedRAMP High”
FedRAMP High for Gemini and Anthropic models; open models are the customer's responsibility.
Consequently, using FedRAMP High authorized Agent Platform services allows for interaction with these supported models in a FedRAMP High environment.
Copyright protectionPartly · “Generative AI Indemnified Services”
Covers GA Google models (Gemini, Imagen, Veo), not partner models like Claude or GPT.
Gemini Enterprise Agent Platform API (formerly Vertex AI API) used with generally available versions of these foundation models
Changes
renameGemini Enterprise Agent Platform
Vertex AI becomes Gemini Enterprise Agent Platform
Google launched Gemini Enterprise Agent Platform as the successor to Vertex AI. All Vertex AI services and roadmap now ship only through the new platform.
cloud.google.com