Overview of Generative AI on Vertex AI

Build production-ready generative AI agents and applications using Vertex AI using Google's advanced models and infrastructure.

  • Build, deploy, and connect agents

    Build agents with an open approach and deploy them with enterprise-grade controls. Connect agents across your enterprise ecosystem.

  • Enterprise ready

    Deploy your generative AI agents and applications at scale with enterprise-grade security, data residency and privacy, access transparency, and low latency.

  • State-of-the-art features

    Expand the capabilities of your applications by using the 2 million token context window that Gemini supports, and the built-in multimodality and thinking capabilities from Gemini 2.5 models.

  • Open and flexible platform

    Vertex AI Model Garden provides a library of over 200 enterprise-ready models and Vertex AI Model Builder helps you test, customize, deploy, and monitor Google proprietary and select third-party models, including Anthropic's Claude 3.7 Sonnet, Meta's Llama 4, Mistral's AI Mixtral 8x7B, and AI21 Labs's Jamba 1.5.

Get started

Generate text using the Gemini API in Vertex AI

Use the Gen AI SDK to send requests to the Gemini API in Vertex AI
Test out prompts with no setup required

Generate images and verify watermarks using Imagen

Create a watermarked image using Imagen on Vertex AI

Agent Builder

A suite of features for building and deploying AI agents

Live API

Use the Live API to provide your end users with the experience of natural, human-like voice conversations

Thinking

Solve complex requests and show the model's thought process behind its response using Gemini's built-in reasoning capabilities

Grounding

Ground your responses using Google Search, Maps, or even your own data

Generate embeddings

Generate embeddings to perform tasks such as search, classification, clustering, and outlier detection

Tuning

Adapt your model to perform specific tasks with greater precision and accuracy

Image generation

Build next-generation AI products that transform your user's imagination into high quality visual assets using AI generation in seconds

Video generation

Use Veo on Vertex AI to generate new videos from a text prompt or an image prompt

Generative AI evaluation service

Vertex AI lets you evaluate any generative model or application and benchmark the evaluation results against your own judgment, using your own evaluation criteria

Build using the SDK

Use the Gen AI SDK to send requests to the Gemini API in Vertex AI

Run example Jupyter notebooks

Explore various Gemini use cases with our example Jupyter notebooks

Best practices for prompt design

Learn how to design prompts to improve the quality of your responses from the model

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025年06月27日 UTC.