# Google Vertex AI integrations: publisher models

> Generate content, create an endpoint and create a batch prediction job in Google Vertex AI.

**Canonical page:** https://tray.ai/connectors/google-vertex-ai-integrations/
**Categories:** AI
**Connects through:** HTTP Connector

## Overview

Google Vertex AI is Google Cloud's service for running Gemini and other models, with tuning, batch prediction, and model deployment. Tray.ai connects to Google Vertex AI through the HTTP Connector, so your workflows can call the Google Vertex AI API alongside the rest of your stack.

## Use cases

### Publisher models

Work with publisher models in Google Vertex AI from any Tray.ai workflow. The Google Vertex AI API covers calls such as generate content and stream generated content.

- Generate content
- Stream generated content
- Count tokens

### Endpoints

Read and create endpoints in Google Vertex AI from any Tray.ai workflow. The Google Vertex AI API covers calls such as create an endpoint and list endpoints.

- Create an endpoint
- List endpoints
- Deploy a model

### Batch prediction jobs

Read, create, and delete batch prediction jobs in Google Vertex AI from any Tray.ai workflow. The Google Vertex AI API covers calls such as create a batch prediction job and list batch prediction jobs.

- Create a batch prediction job
- List batch prediction jobs
- Cancel a batch prediction job

### Tuning jobs

Read, create, and delete tuning jobs in Google Vertex AI from any Tray.ai workflow. The Google Vertex AI API covers calls such as create a tuning job and list tuning jobs.

- Create a tuning job
- List tuning jobs
- Cancel a tuning job

### Cached contents

Read, create, and delete cached contents in Google Vertex AI from any Tray.ai workflow. The Google Vertex AI API covers calls such as create cached content and list cached contents.

- Create cached content
- List cached contents
- Delete cached content

### Datasets

Read and create datasets in Google Vertex AI from any Tray.ai workflow. The Google Vertex AI API covers calls such as create a dataset and import data.

- Create a dataset
- Import data
- Export data

## Challenges Tray.ai solves

### Keeping Google Vertex AI credentials out of logs

A raw API call usually means pasting a key or token into the request, where it ends up in step inputs, logs, and screenshots.

**How Tray.ai helps:** Store Google Vertex AI credentials once as a Tray.ai authentication and reference them from the HTTP Connector. Tray.ai masks authentication values in logs, so the secret never shows up in a step's input or output.

### Going from the Google Vertex AI API docs to a working call

Translating an example request from API docs into a workflow step means copying the method, URL, headers, and body by hand.

**How Tray.ai helps:** Paste a cURL example from the Google Vertex AI API docs into the HTTP Connector and Tray.ai fills in the method, URL, headers, and body for you.

### Handling files and non-JSON responses

Not every API answers in JSON. Some return XML, files, or binary data, or expect a multipart upload.

**How Tray.ai helps:** The HTTP Connector parses JSON and XML responses, returns files you can pass to the next step, and sends multipart form data for uploads.

## Frequently asked questions

### Does Tray.ai connect to Google Vertex AI?

Yes. Tray.ai connects to Google Vertex AI through the HTTP Connector, which calls the Google Vertex AI API directly. Any call the Google Vertex AI API documents can run as a step in a Tray.ai workflow.

### How does Tray.ai authenticate with Google Vertex AI?

The Google Vertex AI API uses OAuth 2.0. You save it once as a Tray.ai authentication, and the HTTP Connector adds it to every request.

### Can I get a dedicated Google Vertex AI connector?

Google Vertex AI runs through the HTTP Connector rather than a dedicated connector. If your team wants one, the Tray.ai connector SDK can build a dedicated Google Vertex AI connector from the Google Vertex AI API.

## Learn more

- Intelligent Integration: https://tray.ai/platform/intelligent-ipaas/
- Merlin Agent Builder: https://tray.ai/platform/merlin-agent-builder/
- Agent Gateway for MCP: https://tray.ai/platform/agent-gateway/
- Book a demo: https://tray.ai/contact/