Migrate to the Firebase AI Logic SDKs from the Google AI client SDKs

Stay organized with collections Save and categorize content based on your preferences.

Swift

Use Swift Package Manager to install and manage Firebase dependencies.

The Firebase AI Logic library provides access to the APIs for interacting with Gemini and Imagen models. The library is included as part of the Firebase SDK for Apple platforms (firebase-ios-sdk).

If you're already using Firebase, then make sure your Firebase package is v11.13.0 or later.

1. In Xcode, with your app project open, navigate to File > Add Package Dependencies.

2. When prompted, add the Firebase Apple platforms SDK repository:

   https://github.com/firebase/firebase-ios-sdk
   

3. Select the latest SDK version.

4. Select the FirebaseAI library.

When finished, Xcode will automatically begin resolving and downloading your dependencies in the background.

Kotlin

The Firebase AI Logic SDK for Android (firebase-ai) provides access to the APIs for interacting with Gemini and Imagen models.

In your module (app-level) Gradle file (like <project>/<app-module>/build.gradle.kts), add the dependency for the Firebase AI Logic library for Android. We recommend using the Firebase Android BoM to control library versioning.

dependencies {
  // ... other androidx dependencies

  // Import the BoM for the Firebase platform
  implementation(platform("com.google.firebase:firebase-bom:33.13.0"))

  // Add the dependency for the Firebase AI Logic library
  // When using the BoM, you don't specify versions in Firebase library dependencies
  implementation("com.google.firebase:firebase-ai")
}

By using the Firebase Android BoM, your app will always use compatible versions of Firebase Android libraries.

dependencies {
  // Add the dependency for the Firebase AI Logic library
  // When NOT using the BoM, you must specify versions in Firebase library dependencies
  implementation("com.google.firebase:firebase-ai:16.0.0")
}

Java

The Firebase AI Logic SDK for Android (firebase-ai) provides access to the APIs for interacting with Gemini and Imagen models.

In your module (app-level) Gradle file (like <project>/<app-module>/build.gradle.kts), add the dependency for the Firebase AI Logic library for Android. We recommend using the Firebase Android BoM to control library versioning.

For Java, you need to add two additional libraries.

dependencies {
  // ... other androidx dependencies

  // Import the BoM for the Firebase platform
  implementation(platform("com.google.firebase:firebase-bom:33.13.0"))

  // Add the dependency for the Firebase AI Logic library
  // When using the BoM, you don't specify versions in Firebase library dependencies
  implementation("com.google.firebase:firebase-ai")

  // Required for one-shot operations (to use `ListenableFuture` from Guava Android)
  implementation("com.google.guava:guava:31.0.1-android")

  // Required for streaming operations (to use `Publisher` from Reactive Streams)
  implementation("org.reactivestreams:reactive-streams:1.0.4")
}

By using the Firebase Android BoM, your app will always use compatible versions of Firebase Android libraries.

dependencies {
  // Add the dependency for the Firebase AI Logic library
  // When NOT using the BoM, you must specify versions in Firebase library dependencies
  implementation("com.google.firebase:firebase-ai:16.0.0")
}

Web

The Firebase AI Logic library provides access to the APIs for interacting with Gemini and Imagen models. The library is included as part of the Firebase JavaScript SDK for Web.

1. Install the Firebase JS SDK for Web using npm:

   npm install firebase
   

2. 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);
   

Dart

The Firebase AI Logic plugin for Flutter (firebase_ai) provides access to the APIs for interacting with Gemini and Imagen models.

1. From your Flutter project directory, run the following command to install the core plugin and the Firebase AI Logic plugin:

   flutter pub add firebase_core && flutter pub add firebase_ai
   

2. In your lib/main.dart file, import the Firebase core plugin, the Firebase AI Logic plugin, and the configuration file you generated earlier:

   import 'package:firebase_core/firebase_core.dart';
   import 'package:firebase_ai/firebase_ai.dart';
   import 'firebase_options.dart';
   

3. Also in your lib/main.dart file, initialize Firebase using the DefaultFirebaseOptions object exported by the configuration file:

   await Firebase.initializeApp(
     options: DefaultFirebaseOptions.currentPlatform,
   );
   

4. Rebuild your Flutter application:

   flutter run
   

Unity

Support for Unity wasn't available from the Google AI client SDKs.

Learn how to get started with the Firebase AI Logic SDK for Unity.

Swift

Remove the old library:

1. In Xcode, with your app project open, navigate to the Packages Dependencies pane.

2. Select the generative-ai-swift package from the list of package dependencies.

3. Click the - button from the bottom of the list and click Remove to confirm.

Kotlin

dependencies {
    implementation("com.google.ai.client.generativeai:generativeai:VERSION")
}

Java

dependencies {
    implementation("com.google.ai.client.generativeai:generativeai:VERSION")
}

Web

// BEFORE
import { initializeApp } from "firebase/app";
import { GoogleGenerativeAI } from "@google/generative-ai";

Dart

Delete the old package:
flutter pub remove google_generative_ai

Unity

Support for Unity wasn't available from Google AI client SDKs.

Learn how to get started with the Firebase AI Logic SDK for Unity.

Swift

// BEFORE
import GoogleGenerativeAI

let model = GenerativeModel(name: "MODEL_NAME", apiKey: APIKey.default)

// AFTER
import FirebaseAI

// Initialize the Gemini Developer API backend service
let ai = FirebaseAI.firebaseAI(backend: .googleAI())

// Create a `GenerativeModel` instance with a model that supports your use case
let model = ai.generativeModel(modelName: "gemini-2.0-flash")

Kotlin

// BEFORE
import com.google.ai.client.generativeai.Chat
import com.google.ai.client.generativeai.type.Content
import com.google.ai.client.generativeai.java.GenerativeModuleFutures

...

val generativeModel = GenerativeModel(modelName = "MODEL_NAME",
  // Access your API key as a Build Configuration variable
  apiKey = BuildConfig.apiKey
)

// AFTER
import com.google.firebase.Firebase
import com.google.firebase.ai.ai
import com.google.firebase.ai.type.GenerativeBackend

...

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
val model = Firebase.ai(backend = GenerativeBackend.googleAI())
                        .generativeModel("gemini-2.0-flash")

Java

// BEFORE
import com.google.ai.client.generativeai.Chat;
import com.google.ai.client.generativeai.type.Content;
import com.google.ai.client.generativeai.java.GenerativeModuleFutures;

...

GenerativeModel gm = new GenerativeModel("MODEL_NAME",
  // Access your API key as a Build Configuration variable
  BuildConfig.apiKey
);

GenerativeModelFutures model = GenerativeModelFutures.from(gm);

// AFTER
import com.google.firebase.ai.FirebaseAI;
import com.google.firebase.ai.GenerativeModel;
import com.google.firebase.ai.java.GenerativeModelFutures;
import com.google.firebase.ai.type.GenerativeBackend;

...

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI())
        .generativeModel("gemini-2.0-flash");

// Use the GenerativeModelFutures Java compatibility layer which offers
// support for ListenableFuture and Publisher APIs
GenerativeModelFutures model = GenerativeModelFutures.from(ai);

Web

// BEFORE
import { GoogleGenerativeAI } from "@google/generative-ai";

// Fetch your API_KEY and access your API
const API_KEY = "...";
const genAI = new GoogleGenerativeAI(API_KEY);

...

const model = genAI.getGenerativeModel({ model: "MODEL_NAME"});

// AFTER
import { initializeApp } from "firebase/app";
import { getAI, getGenerativeModel, GoogleAIBackend } 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 with a model that supports your use case
const model = getGenerativeModel(ai, { model: "gemini-2.0-flash" });

Dart

// BEFORE
import 'package:google_generative_ai/google_generative_ai.dart';

final apiKey = Platform.environment['API_KEY'];
if (apiKey == null) {
print('No \$API_KEY environment variable');
exit(1);
}

final model = GenerativeModel(model: 'MODEL_NAME', apiKey: apiKey);

// AFTER
import 'package:firebase_ai/firebase_ai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';

// Initialize FirebaseApp
await Firebase.initializeApp(
  options: DefaultFirebaseOptions.currentPlatform,
);

// Initialize the Gemini Developer API backend service
// Create a `GenerativeModel` instance with a model that supports your use case
final model =
      FirebaseAI.googleAI().generativeModel(model: 'gemini-2.0-flash');

Unity

Support for Unity wasn't available from Google AI client SDKs.

Learn how to get started with the Firebase AI Logic SDK for Unity.

Swift

• Enumerations

  • Replaced most enum types with structs with static variables. This change allows more flexibility for evolving the API in a backward-compatible way. When using switch statements, you must now include a default: case to cover unknown or unhandled values, including new values that are added to the SDK in the future.

  • Renamed the BlockThreshold enumeration to HarmBlockThreshold; this type is now a struct.

  • Removed unknown and unspecified cases from the following enumerations (now structs): HarmCategory, HarmBlockThreshold, HarmProbability, BlockReason, and FinishReason.

  • Replaced the enumeration ModelContent.Part with a protocol named Part to allow new types to be added in a backward-compatible way. This change is described in greater detail in the Content parts section.

• Content parts

  • Removed the ThrowingPartsRepresentable protocol, and simplified the initializers for ModelContent to avoid occasional compiler errors. Images that don't encode properly will still throw errors when being used in generateContent.

  • Replaced the ModelContent.Part cases with the following struct types conforming to the Part protocol:

    • .text to TextPart
    • .data to InlineDataPart
    • .fileData to FileDataPart
    • .functionCall to FunctionCallPart
    • .functionResponse to FunctionResponsePart

• Harm category

  • Changed the HarmCategory to no longer be nested in the SafetySetting type. If you're referring to it as SafetySetting.HarmCategory, that can be replaced with HarmCategory.

• Safety feedback

  • Removed the SafetyFeedback type, since it wasn't used in any of the responses.

• Citation metadata

  • Renamed the citationSources property to citations in CitationMetadata.

• Total billable characters

  • Changed the totalBillableCharacters property in CountTokensResponse to be optional to reflect situations where no characters are sent.

• Candidate response

  • Renamed CandidateResponse to Candidate to match other platforms.

• Generation configuration

  • Changed the public properties of GenerationConfig to internal. They all remain configurable in the initializer.

Kotlin

• Enumerations

  • Replaced enum classes and sealed classes with regular classes. This change allows more flexibility for evolving the API in a backward compatible way.

  • Renamed the BlockThreshold enumeration to HarmBlockThreshold.

  • Removed values from the following enumerations: HarmBlockThreshold, HarmProbability, HarmSeverity, BlockReason, and FinishReason.

• Blob methods

  • Renamed all methods that included Blob as part of their name to use InlineData instead.

• Safety settings

  • Changed the field method to be nullable.

• Duration class

  • Removed all usages of Kotlin's Duration class, and replaced it with long. This change provides better interoperability with Java.

• Citation metadata

  • Wrapped all the fields previously declared in CitationMetadata into a new class called Citation. Citations can be found in the list called citations in CitationMetadata. This change allows better alignment of types across platforms.

• Count tokens

  • Changed the field totalBillableCharacters to be nullable.

• Total billable characters

  • Changed the totalBillableCharacters property in CountTokensResponse to be optional to reflect situations where no characters are sent.

• Instantiating a model

  • Moved the requestOptions parameter to the end of the parameter list to align with other platforms.

Java

• Enumerations

  • Replaced enum classes and sealed classes with regular classes. This change allows more flexibility for evolving the API in a backward compatible way.

  • Renamed the BlockThreshold enumeration to HarmBlockThreshold.

  • Removed values from the following enumerations: HarmBlockThreshold, HarmProbability, HarmSeverity, BlockReason, and FinishReason.

• Blob methods

  • Renamed all methods that included Blob as part of their name to use InlineData instead.

• Safety settings

  • Changed the field method to be nullable.

• Duration class

  • Removed all usages of Kotlin's Duration class, and replaced it with long. This change provides better interoperability with Java.

• Citation metadata

  • Wrapped all the fields previously declared in CitationMetadata into a new class called Citation. Citations can be found in the list called citations in CitationMetadata. This change allows better alignment of types across platforms.

• Count tokens

  • Changed the field totalBillableCharacters to be nullable.

• Total billable characters

  • Changed the totalBillableCharacters property in CountTokensResponse to be optional to reflect situations where no characters are sent.

• Instantiating a model

  • Moved the requestOptions parameter to the end of the parameter list to align with other platforms.

Web

Note that the Google AI client SDK for JavaScript has had many changes since the time that the Firebase AI Logic client SDKs branched from it. The following list are some potential changes that you might need to consider as you migrate to the Firebase AI Logic client SDKs.

• Enumerations

  • Removed values from the following enumerations: HarmCategory, BlockThreshold, HarmProbability, HarmSeverity, BlockReason, and FinishReason.

• Block reason

  • Changed blockReason in PromptFeedback to be optional.

• Search Grounding

  • Removed all usages of this feature, since it's not yet supported in the Firebase AI Logic SDKs.

• Errors

  • Removed all usages of GoogleGenerativeAIError, and optionally move to AIError.

Dart

• Enumerations

  • Removed values from the following enumerations: HarmCategory, HarmProbability, BlockReason, and FinishReason.

• Data part

  • Renamed DataPart to InlineDataPart, and the static data function to inlineData to align with other platforms.

• Request options

  • Removed RequestOptions since timeout wasn't functional. It will be re-added in the near future, but it will be moved to the GenerativeModel type to match other platforms.

• Stop sequences

  • Changed the stopSequences parameter in GenerationConfig to be optional and to default to null instead of an empty array.

• Citations

  • Renamed the citationSources property to citations in CitationMetadata. The CitationSource type was renamed to Citation to match other platforms.

• Unnecessary public types, methods, and properties

  • Removed the following types, methods, and properties which were unintentionally exposed: defaultTimeout, CountTokensResponseFields, parseCountTokensResponse, parseEmbedContentResponse, parseGenerateContentResponse, parseContent, BatchEmbedContentsResponse, ContentEmbedding, EmbedContentRequest, and EmbedContentResponse.

• Count tokens

  • Removed extra fields from the countTokens function that are no longer necessary. Only contents is needed.

• Instantiating a model

  • Moved the systemInstruction parameter to the end of the parameter list to align with other platforms.

• Embedding functionality

  • Removed unsupported embedding functionality (embedContent and batchEmbedContents) from the model.

Unity

Support for Unity wasn't available from Google AI client SDKs.

Learn how to get started with the Firebase AI Logic SDK for Unity.