Get started with the Gemini API using the Vertex AI in Firebase SDKs

iOS+ Android Web Flutter

This guide shows you how to get started making calls to the Vertex AI Gemini API directly from your app using the Vertex AI in Firebase SDK for your chosen platform.

Other options for working with the Gemini API

• Optionally experiment with an alternative "Google AI" version of the Gemini API
  Get free-of-charge access (within limits and where available) using Google AI Studio and Google AI client SDKs. These SDKs should be used for prototyping only in mobile and web apps.

  After you're familiar with how a Gemini API works, migrate to our Vertex AI in Firebase SDKs (this documentation), which have many additional features important for mobile and web apps, like protecting the API from abuse using Firebase App Check and support for large media files in requests.

• Optionally call the Vertex AI Gemini API server-side (like with Python, Node.js, or Go)
  Use the server-side Vertex AI SDKs, Genkit, or Firebase Extensions for the Gemini API.

Note that you can also use this guide to get started with accessing Imagen models using the Vertex AI in Firebase SDKs.

Prerequisites

Step 1: Set up a Firebase project and connect your app to Firebase

If you already have a Firebase project and an app connected to Firebase

1. In the Firebase console, go to the Vertex AI page.

2. Click the Vertex AI in Firebase card to launch a workflow that helps you complete the following tasks:

   • Upgrade your project to use the pay-as-you-go Blaze pricing plan.

   • Enable the required APIs in your project (Vertex AI API and Vertex AI in Firebase API).

3. Continue to the next step in this guide to add the SDK to your app.

If you do not already have a Firebase project and an app connected to Firebase

Set up a Firebase project

1. Sign into the Firebase console.

2. Click Create project, and then use either of the following options:

   • Option 1: Create a wholly new Firebase project (and its underlying Google Cloud project automatically) by entering a new project name in the first step of the "Create project" workflow.

   • Option 2: "Add Firebase" to an existing Google Cloud project by selecting your Google Cloud project name from the drop-down menu in the first step of the "Create project" workflow.

   Note that when prompted, you do not need to set up Google Analytics to use the Vertex AI in Firebase SDKs.

3. In the Firebase console, go to the Vertex AI page.

4. Click the Vertex AI in Firebase card to launch a workflow that helps you complete the following tasks:

   • Upgrade your project to use the pay-as-you-go Blaze pricing plan.

   • Enable the required APIs in your project (Vertex AI API and Vertex AI in Firebase API).

Connect your app to Firebase

Note: In the Firebase console, you're strongly encouraged to set up Firebase App Check. If you're just trying out the Gemini API, you don't need to set up App Check right away; however, we recommend setting it up as soon as you start seriously developing your app.

Step 2: Add the SDK

With your Firebase project set up and your app connected to Firebase (see previous step), you can now add the Vertex AI in Firebase SDK to your app.

iOS+ Android Web Flutter

Step 3: Initialize the Vertex AI service and create a GenerativeModel instance

Before you can make any API calls and send a prompt to a Gemini model, you need to initialize the Vertex AI service and create a GenerativeModel instance.

Note: Depending on the capability you're using, you might not always create a GenerativeModel instance.

• To access an Imagen model, create an ImagenModel instance.
• To stream input and output using the Gemini Live API, create a LiveModel instance.

After you finish this getting started guide, learn how to choose a model and (optionally) a location appropriate for your use case and app.

Step 4: Send a prompt request to a model

Now that you've connected your app to Firebase, added the SDK, and initialized the Vertex AI service and the generative model, you're ready to send a prompt request to a Gemini model.

You can use generateContent() to generate text from a text-only prompt request:

The Gemini API can also stream responses for faster interactions, as well as handle multimodal prompts that include content like images, video, and audio. See all the capabilities of the Gemini API later on this page.

What else can you do?

Learn more about the supported models

Learn about the models available for various use cases and their quotas and pricing.

Try out other capabilities

• Learn more about generating text from text-only prompts, including how to stream the response.
• Generate text from multimodal prompts (including text, images, PDFs, video, and audio).
• Build multi-turn conversations (chat).
• Generate structured output (like JSON) from both text and multimodal prompts.
• Generate images from text prompts.
• Stream input and output (including audio) using the Gemini Live API.
• Use function calling to connect generative models to external systems and information.

Learn how to control content generation

• Understand prompt design, including best practices, strategies, and example prompts.
• Configure model parameters like temperature and maximum output tokens (for Gemini) or aspect ratio and person generation (for Imagen).
• Use safety settings to adjust the likelihood of getting responses that may be considered harmful.

You can also experiment with prompts and model configurations using Vertex AI Studio.

Give feedback about your experience with Vertex AI in Firebase