Gemini 3 Pro & Flash, Gemini 3 Pro Image (nano banana pro), and the latest Gemini Live API native audio models are now available to use with Firebase AI Logic on all platforms!

Gemini 2.0 Flash and Flash-Lite models will be retired on March 31, 2026. To avoid service disruption, update to a newer model like gemini-2.5-flash-lite. Learn more.

Build hybrid experiences with on-device and cloud-hosted models

Build AI-powered web apps and features with hybrid inference using Firebase AI Logic. Hybrid inference enables running inference using on-device models when available and seamlessly falling back to cloud-hosted models otherwise (and vice versa).

This page describes how to get started using the client SDK, as well as showing additional configuration options and capabilities, like structured output.

Note that on-device inference is supported for web apps running on Chrome on Desktop.

Jump to the code examples

Recommended use cases and supported capabilities

Recommended use cases:

Using an on-device model for inference offers:
- Enhanced privacy
- Local context
- Inference at no-cost
- Offline functionality
Using hybrid functionality offers:
- Reach 100% of your audience, regardless of on-device model availability or internet connectivity

Supported capabilities and features for on-device inference:

Single-turn content generation, streaming and non-streaming
Generating text from text-only input
Generating text from text-and-image input, specifically input image types of JPEG and PNG
Generating structured output, including JSON and enums

Before you begin

Take note of the following:

Inference using an on-device model uses the Prompt API from Chrome; whereas inference using a cloud-hosted model uses your chosen Gemini API provider (either the Gemini Developer API or the Vertex AI Gemini API).
This page describes how to get started developing using localhost (learn more about using APIs on localhost in the Chrome documentation). Also, check out the additional configuration options and capabilities (like structured output) later on this page.
After you've implemented your feature, you can enable end-users to try your feature in your actual app.

Get started on localhost

These get started steps describe the required general setup for any supported prompt request that you want to send.

Step 1: Set up Chrome and the Prompt API for on-device inference

Make sure you're using a recent version of Chrome. Update in chrome://settings/help.
On-device inference is available from Chrome v139 and higher.
Enable the on-device multimodal model by setting the following flag to Enabled:
- chrome://flags/#prompt-api-for-gemini-nano-multimodal-input
Restart Chrome.
(Optional) Download the on-device model before the first request.

The Prompt API is built into Chrome; however, the on-device model isn't available by default. If you haven't yet downloaded the model before your first request for on-device inference, the request will automatically start the model download in the background.

Note: Downloading the model can take several minutes, so waiting to auto-download with the first request can significantly delay receiving a response to that request.
View instructions to download the on-device model
1. Open Developer Tools > Console.
2. Run the following:
```
await LanguageModel.availability();
```
3. Make sure that the output is available, downloading, or downloadable.
4. If the output is downloadable, start the model download by running:
```
await LanguageModel.create();
```
5. You can use the following monitor callback to listen for download progress and make sure that the model is available before making requests:
```
const session = await LanguageModel.create({
  monitor(m) {
    m.addEventListener("downloadprogress", (e) => {
      console.log(`Downloaded ${e.loaded * 100}%`);
    });
  },
});
```

Step 2: Set up a Firebase project and connect your app to Firebase

Sign into the Firebase console, and then select your Firebase project.
Don't already have a Firebase project?

If you don't already have a Firebase project, click the button to create a new Firebase 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 workflow.
- Option 2: "Add Firebase" to an existing Google Cloud project by clicking Add Firebase to Google Cloud project (at bottom of page). In the first step of the workflow, start entering the project name of the existing project, and then select the project from the displayed list.
Complete the remaining steps of the on-screen workflow to create a Firebase project. Note that when prompted, you do not need to set up Google Analytics to use the Firebase AI Logic SDKs.
In the Firebase console, go to the Firebase AI Logic page.
Click Get started to launch a guided workflow that helps you set up the required APIs and resources for your project.
Set up your project to use a "Gemini API" provider.

We recommend getting started using the Gemini Developer API. At any point, you can always set up the Vertex AI Gemini API (and its requirement for billing).

For the Gemini Developer API, the console will enable the required APIs and create a Gemini API key in your project.
Do not add this Gemini API key into your app's codebase. Learn more.
If prompted in the console's workflow, follow the on-screen instructions to register your app and connect it to Firebase.
Continue to the next step in this guide to add the SDK to your app.

Step 3: Add the SDK

The Firebase library provides access to the APIs for interacting with generative models. The library is included as part of the Firebase JavaScript SDK for Web.

Install the Firebase JS SDK for Web using npm:
```
npm install firebase
```

Initialize Firebase in your app:

import { initializeApp } from "firebase/app";

// TODO(developer) Replace the following with your app's Firebase configuration
// See: https://firebase.google.com/docs/web/learn-more#config-object
const firebaseConfig = {
  // ...
};

// Initialize FirebaseApp
const firebaseApp = initializeApp(firebaseConfig);

Step 4: Initialize the service and create a model instance

Click your Gemini API provider to view provider-specific content and code on this page.

Set up the following before you send a prompt request to the model.

Initialize the service for your chosen API provider.
Create a GenerativeModel instance. Make sure to do the following:
1. Call getGenerativeModel after or on an end-user interaction (like a button click). This is a prerequisite for inferenceMode.
2. Set the mode to one of:
  - PREFER_ON_DEVICE: Use the on-device model if it's available; otherwise, fall back to the cloud-hosted model.
  - ONLY_ON_DEVICE: Use the on-device model if it's available; otherwise, throw an exception.
  - PREFER_IN_CLOUD: Use the cloud-hosted model if it's available; otherwise, fall back to the on-device model.
  - ONLY_IN_CLOUD: Use the cloud-hosted model if it's available; otherwise, throw an exception.
  Note: For requests sent to the on-device model, make sure it's supported by on-device inference.
  For requests sent off-device, the device must be online. Also, the default cloud-hosted model is gemini-2.5-flash-lite, but you can override the default.

import { initializeApp } from "firebase/app";
import { getAI, getGenerativeModel, GoogleAIBackend, InferenceMode } from "firebase/ai";

// TODO(developer) Replace the following with your app's Firebase configuration
// See: https://firebase.google.com/docs/web/learn-more#config-object
const firebaseConfig = {
  // ...
};

// Initialize FirebaseApp
const firebaseApp = initializeApp(firebaseConfig);

// Initialize the Gemini Developer API backend service
const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Create a `GenerativeModel` instance
// Call `getGenerativeModel` after or on an end-user interaction
// Set the mode (for example, use the on-device model if it's available)
const model = getGenerativeModel(ai, { mode: InferenceMode.PREFER_ON_DEVICE });

Step 5: Send a prompt request to a model

This section shows you how to send various types of input to generate different types of output, including:

Generate text from text-only input
Generate text from text-and-image (multimodal) input

If you want to generate structured output (like JSON or enums), then use one of the following "generate text" examples and additionally configure the model to respond according to a provided schema.

Generate text from text-only input

Before trying this sample, make sure that you've completed the Get started section of this guide.

You can use generateContent() to generate text from a prompt that contains text:

// Imports + initialization of FirebaseApp and backend service + creation of model instance

// Wrap in an async function so you can use await
async function run() {
  // Provide a prompt that contains text
  const prompt = "Write a story about a magic backpack."

  // To generate text output, call `generateContent` with the text input
  const result = await model.generateContent(prompt);

  const response = result.response;
  const text = response.text();
  console.log(text);
}

run();

Note that Firebase AI Logic also supports streaming of text responses using generateContentStream (instead of generateContent).

Generate text from text-and-image (multimodal) input

Before trying this sample, make sure that you've completed the Get started section of this guide.

You can use generateContent() to generate text from a prompt that contains text and image files—providing each input file's mimeType and the file itself.

The supported input image types for on-device inference are PNG and JPEG.

// Imports + initialization of FirebaseApp and backend service + creation of model instance

// Converts a File object to a Part object.
async function fileToGenerativePart(file) {
  const base64EncodedDataPromise = new Promise((resolve) => {
    const reader = new FileReader();
    reader.onloadend = () => resolve(reader.result.split(',')[1]);
    reader.readAsDataURL(file);
  });
  return {
    inlineData: { data: await base64EncodedDataPromise, mimeType: file.type },
  };
}

async function run() {
  // Provide a text prompt to include with the image
  const prompt = "Write a poem about this picture:";

  const fileInputEl = document.querySelector("input[type=file]");
  const imagePart = await fileToGenerativePart(fileInputEl.files[0]);

  // To generate text output, call `generateContent` with the text and image
  const result = await model.generateContent([prompt, imagePart]);

  const response = result.response;
  const text = response.text();
  console.log(text);
}

run();

Note that Firebase AI Logic also supports streaming of text responses using generateContentStream (instead of generateContent).

Enable end-users to try your feature

For end-users to try your feature in your app, you must enroll in the Chrome Origin Trials. Note that there's a limited duration and usage for these trials.

Register for the Prompt API Chrome Origin Trial. You'll be given a token.
Provide the token on every web page for which you want the trial feature to be enabled. Use one of the following options:
- Provide the token as a meta tag in the <head> tag: <meta http-equiv="origin-trial" content="TOKEN">
- Provide the token as an HTTP header: Origin-Trial: TOKEN
- Provide the token programmatically.

What else can you do?

In this section, learn how to set an inference mode, override the default cloud-hosted fallback model, and use model configuration to control responses (like generate structured output).

Set an inference mode

The examples in the general setup use the PREFER_ON_DEVICE mode, but this is only one of the four available inference modes.

PREFER_ON_DEVICE: Use the on-device model if it's available; otherwise, fall back to the cloud-hosted model.
```
const model = getGenerativeModel(ai, { mode: InferenceMode.PREFER_ON_DEVICE });
```
ONLY_ON_DEVICE: Use the on-device model if it's available; otherwise, throw an exception.
```
const model = getGenerativeModel(ai, { mode: InferenceMode.ONLY_ON_DEVICE });
```
PREFER_IN_CLOUD: Use the cloud-hosted model if it's available; otherwise, fall back to the on-device model.
```
const model = getGenerativeModel(ai, { mode: InferenceMode.PREFER_IN_CLOUD });
```
ONLY_IN_CLOUD: Use the cloud-hosted model if it's available; otherwise, throw an exception.
```
const model = getGenerativeModel(ai, { mode: InferenceMode.ONLY_IN_CLOUD });
```

Determine whether on-device or in-cloud inference was used

If you use PREFER_ON_DEVICE or PREFER_IN_CLOUD inference modes, then it might be helpful to know which mode was used for given requests. This information is provided by the inferenceSource property of each response (available starting with JS SDK v12.5.0).

When you access this property, the returned value will be either ON_DEVICE or IN_CLOUD.

// ...

console.log('You used: ' + result.response.inferenceSource);

console.log(result.response.text());

Override the default fallback model

The default cloud-hosted model is gemini-2.5-flash-lite (starting with JS SDK v12.8.0).

This model is the fallback cloud-hosted model when you use the PREFER_ON_DEVICE mode. It's also the default model when you use the ONLY_IN_CLOUD mode or the PREFER_IN_CLOUD mode.

You can use the inCloudParams configuration option to specify an alternative default cloud-hosted model.

const model = getGenerativeModel(ai, {
  mode: InferenceMode.INFERENCE_MODE,
  inCloudParams: {
    model: "GEMINI_MODEL_NAME"
  }
});

Find model names for all supported Gemini models.

Use model configuration to control responses

In each request to a model, you can send along a model configuration to control how the model generates a response. Cloud-hosted models and on-device models offer different configuration options.

The configuration is maintained for the lifetime of the instance. If you want to use a different config, create a new GenerativeModel instance with that config.

Set the configuration for a cloud-hosted model

Use the inCloudParams option to configure a cloud-hosted Gemini model. Learn about available parameters.

const model = getGenerativeModel(ai, {
  mode: InferenceMode.INFERENCE_MODE,
  inCloudParams: {
    model: "GEMINI_MODEL_NAME"
    temperature: 0.8,
    topK: 10
  }
});

Set the configuration for an on-device model

Note that inference using an on-device model uses the Prompt API from Chrome.

Use the onDeviceParams option to configure an on-device model. Learn about available parameters.

const model = getGenerativeModel(ai, {
  mode: InferenceMode.INFERENCE_MODE,
  onDeviceParams: {
    createOptions: {
      temperature: 0.8,
      topK: 8
    }
  }
});

Set the configuration for structured output (like JSON)

Generating structured output (like JSON and enums) is supported for inference using both cloud-hosted and on-device models.

For hybrid inference, use both inCloudParams and onDeviceParams to configure the model to respond with structured output. For the other modes, use only the applicable configuration.

For inCloudParams: Specify the appropriate responseMimeType (in this example, application/json) as well as the responseSchema that you want the model to use.
For onDeviceParams: Specify the responseConstraint that you want the model to use.

JSON output

The following example adapts the general JSON output example for hybrid inference:

import {
  getAI,
  getGenerativeModel,
  Schema
} from "firebase/ai";

const jsonSchema = Schema.object({
 properties: {
    characters: Schema.array({
      items: Schema.object({
        properties: {
          name: Schema.string(),
          accessory: Schema.string(),
          age: Schema.number(),
          species: Schema.string(),
        },
        optionalProperties: ["accessory"],
      }),
    }),
  }
});

const model = getGenerativeModel(ai, {
  mode: InferenceMode.INFERENCE_MODE,
  inCloudParams: {
    model: "gemini-2.5-flash"
    generationConfig: {
      responseMimeType: "application/json",
      responseSchema: jsonSchema
    },
  }
  onDeviceParams: {
    promptOptions: {
      responseConstraint: jsonSchema
    }
  }
});

Enum output

As above, but adapting the documentation on enum output for hybrid inference:

// ...

const enumSchema = Schema.enumString({
  enum: ["drama", "comedy", "documentary"],
});

const model = getGenerativeModel(ai, {

// ...

    generationConfig: {
      responseMimeType: "text/x.enum",
      responseSchema: enumSchema
    },

// ...
});

// ...

Features not yet available for on-device inference

As an experimental release, not all the capabilities of the Web SDK are available for on-device inference. The following features are not yet supported for on-device inference (but they are usually available for cloud-based inference).

Generating text from image file input types other than JPEG and PNG
- Can fallback to the cloud-hosted model; however, ONLY_ON_DEVICE mode will throw an error.
Generating text from audio, video, and documents (like PDFs) inputs
- Can fallback to the cloud-hosted model; however, ONLY_ON_DEVICE mode will throw an error.
Generating images using Gemini or Imagen models
- Can fallback to the cloud-hosted model; however, ONLY_ON_DEVICE mode will throw an error.
Providing files using URLs in multimodal requests. You must provide files as inline data to on-device models.
Multi-turn chat
- Can fallback to the cloud-hosted model; however, ONLY_ON_DEVICE mode will throw an error.
Bi-directional streaming with the Gemini Live API
Providing the model with tools to help it generate its response (like function calling, code execution, URL context, and grounding with Google Search)
Count tokens
- Always throws an error. The count will differ between cloud-hosted and on-device models, so there is no intuitive fallback.
AI monitoring in the Firebase console for on-device inference.
- Note that any inference using the cloud-hosted models can be monitored just like other inference using the Firebase AI Logic client SDK for Web.

Give feedback about your experience with Firebase AI Logic