Overview of Generative AI on Vertex AI

Generative AI on Vertex AI lets you build production-ready applications that are powered by state-of-the-art generative AI models hosted on Google's advanced, global infrastructure.

Enterprise ready features for genAI

Enterprise ready

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

State of the art features

State-of-the-art features

Expand the capabilities of your applications by using the 2,000,000-token context window supported by Gemini 1.5 Pro.

Access to third party models

Open platform

Vertex AI Model Garden provides a library of over 100 models that helps you discover, test, customize, and deploy Google proprietary and select third-party models, including Anthropic's Claude 3.5 Sonnet, Meta Llama 3, Mistral AI Mixtral 8x7B, and AI21 Labs Jamba 1.5.

Core capabilities

  • Text generation

    Send chat prompts to a Gemini model and receive streaming or non-streaming responses.

  • Multimodal processing

    Process multiple types of input media at the same time, such as image, video, audio, and documents.

  • Embeddings generation

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

  • Model tuning

    Adapt models to perform specific tasks with greater precision and accuracy.

  • Function calling

    Connect models to external APIs to extend the model's capabilities.

  • Grounding

    Connect models to external data sources to reduce hallucinations in responses.

  • Image generation

    Generate and edit images by using natural language text prompts.


  • Generative AI Evaluation Service

    Evaluate any generative model or application and benchmark the evaluation results.

Vertex AI and Google AI differences

Gemini API in Vertex AI and Google AI both let you incorporate the capabilities of Gemini models into your applications. The platform that's right for you depends on your goals as detailed in the following table.

API Designed for Features
Vertex AI Gemini API
  • Scaled deployments
  • Enterprise
  • Technical support
  • Modality-based pricing
  • Indemnity protection
  • 100+ models in Model Garden
Google AI Gemini API
  • Experimentation
  • Prototyping
  • Ease of use
  • Free tier
  • Token-based pricing

Build using Vertex AI SDKs

Client libraries make it easier to access Google Cloud APIs from a supported language. Although you can use Google Cloud APIs directly by making requests to the server, client libraries provide simplifications that significantly reduce the amount of code you need to write.

Vertex AI provides Vertex Generative AI SDKs for these languages: Python, Node.js, Java, Go, and C#.

Get started

Try one of these quickstarts to get started with generative AI on Vertex AI.

More ways to get started

Here are some notebooks, tutorials, and other examples to help you get started. Vertex AI offers Google Cloud console tutorials and Jupyter notebook tutorials that use the Vertex AI SDK for Python. You can open a notebook tutorial in Colab or download the notebook to your preferred environment.

Get started with Gemini using notebooks

Get started with Gemini

The Gemini model is a groundbreaking multimodal language model developed by Google AI, capable of extracting meaningful insights from a diverse array of data formats, including images, and video. This notebook explores various use cases with multimodal prompts.

Google Colaboratory product logo
Run in Colab
Google Cloud Colab Enterprise logo
Run in Colab Enterprise
Vertex AI product logo
Open in Vertex AI Workbench
GitHub product logo small
View on GitHub

Get started with Vertex AI Studio

GenAI studio product icon

Use Vertex AI Studio to engineer and manage prompts, get prompt code, and tune models, all in a code-free environment.

GitHub product logo small
View on GitHub

Best practices for prompt design

Model garden product icon

Learn how to design prompts to improve the quality of your responses from the model. This tutorial covers the essentials of prompt engineering, including some best practices.

Google Colaboratory product logo
Open in Colab
Google Cloud Colab Enterprise logo
Open in Colab Enterprise
Vertex AI product logo
Open in Vertex AI Workbench
GitHub product logo small
View on GitHub