Gemini Developer API

To access the Gemini Pro and Flash models, we recommend Android developers to use Gemini Developer API using Firebase AI Logic. It lets you to get started without requiring a credit card, and provides a generous free tier. Once you validate your integration with a small user base, you can scale by switching to the paid tier.

Figure 1. Firebase AI Logic integration architecture to access the Gemini Developer API.

Getting started

Before you interact with the Gemini API directly from your app, you'll need to do a few things first, including getting familiar with prompting as well as setting up Firebase and your app to use the SDK.

Experiment with prompts

Experimenting with prompts can help you find the best phrasing, content, and format for your Android app. Google AI Studio is an IDE that you can use to prototype and design prompts for your app's use cases.

Creating the right prompt for your use-case is more art than science, which makes experimentation critical. You can learn more about prompting in the Firebase documentation.

Once you are happy with your prompt, click the "<>" button to get code snippets that you can add to your code.

Set up a Firebase project and connect your app to Firebase

Once you're ready to call the API from your app, follow the instructions in the "Step 1" of the Firebase AI Logic getting started guide to set up Firebase and the SDK in your app.

Add the Gradle dependency

Add the following Gradle dependency to your app module:

Kotlin

dependencies {
  // ... other androidx dependencies

  // Import the BoM for the Firebase platform
  implementation(platform("com.google.firebase:firebase-bom:34.2.0"))

  // 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")
}

Java

dependencies {
  // Import the BoM for the Firebase platform
  implementation(platform("com.google.firebase:34.2.0"))

  // 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")
}

Initialize the generative model

Start by instantiating a GenerativeModel and specifying the model name:

Kotlin

val model = Firebase.ai(backend = GenerativeBackend.googleAI())
                        .generativeModel("gemini-2.5-flash")

Java

GenerativeModel firebaseAI = FirebaseAI.getInstance(GenerativeBackend.googleAI())
        .generativeModel("gemini-2.5-flash");

GenerativeModelFutures model = GenerativeModelFutures.from(firebaseAI);

Learn more about the available models for use with the Gemini Developer API. You can also learn more about configuring model parameters.

Interact with the Gemini Developer API from your app

Now that you've set up Firebase and your app to use the SDK, you're ready to interact with the Gemini Developer API from your app.

Generate text

To generate a text response, call generateContent() with your prompt.

Kotlin

scope.launch {
  val response = model.generateContent("Write a story about a magic backpack.")
}

Java

Content prompt = new Content.Builder()
    .addText("Write a story about a magic backpack.")
    .build();

ListenableFuture<GenerateContentResponse> response = model.generateContent(prompt);
Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        String resultText = result.getText();
        [...]
    }

    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

Generate text from images and other media

You can also generate text from a prompt that includes text plus images or other media. When you call generateContent(), you can pass the media as inline data.

For example, to use a bitmap, use the image content type:

Kotlin

scope.launch {
  val response = model.generateContent(
    content {
      image(bitmap)
      text("what is the object in the picture?")
    }
  )
}

Java

Content content = new Content.Builder()
        .addImage(bitmap)
        .addText("what is the object in the picture?")
        .build();

ListenableFuture<GenerateContentResponse> response = model.generateContent(content);
Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        String resultText = result.getText();
        [...]
    }

    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

To pass an audio file, use the inlineData content type:

Kotlin

val contentResolver = applicationContext.contentResolver
val inputStream = contentResolver.openInputStream(audioUri).use { stream ->
    stream?.let {
        val bytes = stream.readBytes()

        val prompt = content {
            inlineData(bytes, "audio/mpeg")  // Specify the appropriate audio MIME type
            text("Transcribe this audio recording.")
        }

        val response = model.generateContent(prompt)
    }
}

Java

ContentResolver resolver = getApplicationContext().getContentResolver();

try (InputStream stream = resolver.openInputStream(audioUri)) {
    File audioFile = new File(new URI(audioUri.toString()));
    int audioSize = (int) audioFile.length();
    byte audioBytes = new byte[audioSize];
    if (stream != null) {
        stream.read(audioBytes, 0, audioBytes.length);
        stream.close();

        // Provide a prompt that includes audio specified earlier and text
        Content prompt = new Content.Builder()
              .addInlineData(audioBytes, "audio/mpeg")  // Specify the appropriate audio MIME type
              .addText("Transcribe what's said in this audio recording.")
              .build();

        // To generate text output, call `generateContent` with the prompt
        ListenableFuture<GenerateContentResponse> response = model.generateContent(prompt);
        Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
            @Override
            public void onSuccess(GenerateContentResponse result) {
                String text = result.getText();
                Log.d(TAG, (text == null) ? "" : text);
            }
            @Override
            public void onFailure(Throwable t) {
                Log.e(TAG, "Failed to generate a response", t);
            }
        }, executor);
    } else {
        Log.e(TAG, "Error getting input stream for file.");
        // Handle the error appropriately
    }
} catch (IOException e) {
    Log.e(TAG, "Failed to read the audio file", e);
} catch (URISyntaxException e) {
    Log.e(TAG, "Invalid audio file", e);
}

And to provide a video file, continue using the inlineData content type:

Kotlin

val contentResolver = applicationContext.contentResolver
contentResolver.openInputStream(videoUri).use { stream ->
  stream?.let {
    val bytes = stream.readBytes()

    val prompt = content {
        inlineData(bytes, "video/mp4")  // Specify the appropriate video MIME type
        text("Describe the content of this video")
    }

    val response = model.generateContent(prompt)
  }
}

Java

ContentResolver resolver = getApplicationContext().getContentResolver();

try (InputStream stream = resolver.openInputStream(videoUri)) {
    File videoFile = new File(new URI(videoUri.toString()));
    int videoSize = (int) videoFile.length();
    byte[] videoBytes = new byte[videoSize];
    if (stream != null) {
        stream.read(videoBytes, 0, videoBytes.length);
        stream.close();

        // Provide a prompt that includes video specified earlier and text
        Content prompt = new Content.Builder()
                .addInlineData(videoBytes, "video/mp4")
                .addText("Describe the content of this video")
                .build();

        // To generate text output, call generateContent with the prompt
        ListenableFuture<GenerateContentResponse> response = model.generateContent(prompt);
        Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
            @Override
            public void onSuccess(GenerateContentResponse result) {
                String resultText = result.getText();
                System.out.println(resultText);
            }

            @Override
            public void onFailure(Throwable t) {
                t.printStackTrace();
            }
        }, executor);
    }
} catch (IOException e) {
    e.printStackTrace();
} catch (URISyntaxException e) {
    e.printStackTrace();
}

Similarly you can also pass PDF (application/pdf) and plain text (text/plain) documents passing their respective MIME Type as a parameter.

Multi-turn chat

You can also support multi-turn conversations. Initialize a chat with the startChat() function. You can optionally provide the model with a message history. Then call the sendMessage() function to send chat messages.

Kotlin

val chat = model.startChat(
    history = listOf(
        content(role = "user") { text("Hello, I have 2 dogs in my house.") },
        content(role = "model") { text("Great to meet you. What would you like to know?")   }
    )
)

scope.launch {
   val response = chat.sendMessage("How many paws are in my house?")
}

Java

Content.Builder userContentBuilder = new Content.Builder();
userContentBuilder.setRole("user");
userContentBuilder.addText("Hello, I have 2 dogs in my house.");
Content userContent = userContentBuilder.build();

Content.Builder modelContentBuilder = new Content.Builder();
modelContentBuilder.setRole("model");
modelContentBuilder.addText("Great to meet you. What would you like to know?");
Content modelContent = userContentBuilder.build();

List<Content> history = Arrays.asList(userContent, modelContent);

// Initialize the chat
ChatFutures chat = model.startChat(history);

// Create a new user message
Content.Builder messageBuilder = new Content.Builder();
messageBuilder.setRole("user");
messageBuilder.addText("How many paws are in my house?");

Content message = messageBuilder.build();

// Send the message
ListenableFuture<GenerateContentResponse> response = chat.sendMessage(message);
Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        String resultText = result.getText();
        System.out.println(resultText);
    }

    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

Generate images

The Gemini 2.5 Flash Image model (a.k.a Nano Banana) can generate and edit images leveraging world knowledge and reasoning. It generates contextually relevant images, seamlessly blending or interleaving text and image outputs. It can also generate accurate visuals with long text sequences and supports conversational image editing while maintaining context.

As an alternative to Gemini, you can use Imagen models, especially for high-quality image generation that requires photorealism, artistic detail, or specific styles. However, for the majority of client-side use cases for Android apps, Gemini will be more than sufficient.

This guide describes how to use the Gemini 2.5 Flash Image model using the Firebase AI Logic SDK for Android. For more details on generating images with Gemini, see the Generate images with Gemini on Firebase documentation. If you're interested in using Imagen models, check out the documentation.

Google AI Studio showing image generation capabilities. — **Figure 1.** Use Google AI Studio to refine your image generation prompts

Initialize the generative model

Instantiate a GenerativeModel and specify the model name gemini-2.5-flash-image-preview. Verify that you configure responseModalities to include both TEXT and IMAGE.

Kotlin

val model = Firebase.ai(backend = GenerativeBackend.googleAI()).generativeModel(
    modelName = "gemini-2.5-flash-image-preview",
    // Configure the model to respond with text and images (required)
    generationConfig = generationConfig {
        responseModalities = listOf(ResponseModality.TEXT,
        ResponseModality.IMAGE)
    }
)

Java

GenerativeModel ai = FirebaseAI.getInstance(GenerativeBackend.googleAI()).generativeModel(
    "gemini-2.5-flash-image-preview",
    // Configure the model to respond with text and images (required)
    new GenerationConfig.Builder()
        .setResponseModalities(Arrays.asList(ResponseModality.TEXT, ResponseModality.IMAGE))
        .build()
);
GenerativeModelFutures model = GenerativeModelFutures.from(ai);

Generate images (text-only input)

You can instruct a Gemini model to generate images by providing a text-only prompt:

Kotlin

// Provide a text prompt instructing the model to generate an image
val prompt = "A hyper realistic picture of a t-rex with a blue bag pack roaming a pre-historic forest."
// To generate image output, call `generateContent` with the text input
val generatedImageAsBitmap = model.generateContent(prompt)
.candidates.first().content.parts.filterIsInstance<ImagePart>()
.firstOrNull()?.image

Java

// Provide a text prompt instructing the model to generate an image
Content prompt = new Content.Builder()
    .addText("Generate an image of the Eiffel Tower with fireworks in the background.")
    .build();
// To generate an image, call `generateContent` with the text input
ListenableFuture<GenerateContentResponse> response = model.generateContent(prompt);
Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        // iterate over all the parts in the first candidate in the result object
        for (Part part : result.getCandidates().get(0).getContent().getParts()) {
            if (part instanceof ImagePart) {
                ImagePart imagePart = (ImagePart) part;
                // The returned image as a bitmap
                Bitmap generatedImageAsBitmap = imagePart.getImage();
                break;
            }
        }
    }
    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

Edit images (text and image input)

You can ask a Gemini model to edit existing images by providing both text and one or more images in your prompt:

Kotlin

// Provide an image for the model to edit
val bitmap = BitmapFactory.decodeResource(context.resources, R.drawable.scones)
// Provide a text prompt instructing the model to edit the image
val prompt = content {
    image(bitmap)
    text("Edit this image to make it look like a cartoon")
}
// To edit the image, call `generateContent` with the prompt (image and text input)
val generatedImageAsBitmap = model.generateContent(prompt)
    .candidates.first().content.parts.filterIsInstance<ImagePart>().firstOrNull()?.image
// Handle the generated text and image

Java

// Provide an image for the model to edit
Bitmap bitmap = BitmapFactory.decodeResource(resources, R.drawable.scones);
// Provide a text prompt instructing the model to edit the image
Content promptcontent = new Content.Builder()
    .addImage(bitmap)
    .addText("Edit this image to make it look like a cartoon")
    .build();
// To edit the image, call `generateContent` with the prompt (image and text input)
ListenableFuture<GenerateContentResponse> response = model.generateContent(promptcontent);
Futures.addCallback(response, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        // iterate over all the parts in the first candidate in the result object
        for (Part part : result.getCandidates().get(0).getContent().getParts()) {
            if (part instanceof ImagePart) {
                ImagePart imagePart = (ImagePart) part;
                Bitmap generatedImageAsBitmap = imagePart.getImage();
                break;
            }
        }
    }
    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

Iterate and edit images through multi-turn chat

For a conversational approach to image editing, you can use multi-turn chat. This allows for follow-up requests to refine edits without needing to re-send the original image.

First, initialize a chat with startChat(), optionally providing a message history. Then, use sendMessage() for subsequent messages:

Kotlin

// Provide an image for the model to edit
val bitmap = BitmapFactory.decodeResource(context.resources, R.drawable.scones)
// Create the initial prompt instructing the model to edit the image
val prompt = content {
    image(bitmap)
    text("Edit this image to make it look like a cartoon")
}
// Initialize the chat
val chat = model.startChat()
// To generate an initial response, send a user message with the image and text prompt
var response = chat.sendMessage(prompt)
// Inspect the returned image
var generatedImageAsBitmap = response
    .candidates.first().content.parts.filterIsInstance<ImagePart>().firstOrNull()?.image
// Follow up requests do not need to specify the image again
response = chat.sendMessage("But make it old-school line drawing style")
generatedImageAsBitmap = response
    .candidates.first().content.parts.filterIsInstance<ImagePart>().firstOrNull()?.image

Java

// Provide an image for the model to edit
Bitmap bitmap = BitmapFactory.decodeResource(resources, R.drawable.scones);
// Initialize the chat
ChatFutures chat = model.startChat();
// Create the initial prompt instructing the model to edit the image
Content prompt = new Content.Builder()
    .setRole("user")
    .addImage(bitmap)
    .addText("Edit this image to make it look like a cartoon")
    .build();
// To generate an initial response, send a user message with the image and text prompt
ListenableFuture<GenerateContentResponse> response = chat.sendMessage(prompt);
// Extract the image from the initial response
ListenableFuture<@Nullable Bitmap> initialRequest = Futures.transform(response,
    result -> {
        for (Part part : result.getCandidates().get(0).getContent().getParts()) {
            if (part instanceof ImagePart) {
                ImagePart imagePart = (ImagePart) part;
                return imagePart.getImage();
            }
        }
        return null;
    }, executor);
// Follow up requests do not need to specify the image again
ListenableFuture<GenerateContentResponse> modelResponseFuture = Futures.transformAsync(
    initialRequest,
    generatedImage -> {
        Content followUpPrompt = new Content.Builder()
            .addText("But make it old-school line drawing style")
            .build();
        return chat.sendMessage(followUpPrompt);
    }, executor);
// Add a final callback to check the reworked image
Futures.addCallback(modelResponseFuture, new FutureCallback<GenerateContentResponse>() {
    @Override
    public void onSuccess(GenerateContentResponse result) {
        for (Part part : result.getCandidates().get(0).getContent().getParts()) {
            if (part instanceof ImagePart) {
                ImagePart imagePart = (ImagePart) part;
                Bitmap generatedImageAsBitmap = imagePart.getImage();
                break;
            }
        }
    }
    @Override
    public void onFailure(Throwable t) {
        t.printStackTrace();
    }
}, executor);

Best practices and limitations

Output Format: Images are generated as PNGs with a maximum dimension of 1024 px.
Input Types: The model does not support audio or video inputs for image generation.
Language Support: For best performance, use the following languages: English (en), Mexican Spanish (es-mx), Japanese (ja-jp), Simplified Chinese (zh-cn), and Hindi (hi-in).
Generation Issues:
- Image generation may not always trigger, sometimes resulting in text-only output. Try asking for image outputs explicitly (e.g., "generate an image", "provide images as you go along", "update the image").
- The model may stop generating partway through. Try again or try a different prompt.
- The model may generate text as an image. Try asking for text outputs explicitly (e.g., "generate narrative text along with illustrations").

See the Firebase documentation for more details.

Next steps

Review the Android Quickstart Firebase sample app and the Android AI Sample Catalog on GitHub.
Prepare your app for production, including setting up Firebase App Check to protect the Gemini API from abuse by unauthorized clients.
Learn more about Firebase AI Logic in the Firebase documentation.

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

Getting started

Experiment with prompts

Set up a Firebase project and connect your app to Firebase

Add the Gradle dependency

Kotlin

Java

Initialize the generative model

Kotlin

Java

Interact with the Gemini Developer API from your app

Generate text

Kotlin

Java

Generate text from images and other media

Kotlin

Java

Kotlin

Java

Kotlin

Java

Multi-turn chat

Kotlin

Java

Generate images

Initialize the generative model

Kotlin

Java

Generate images (text-only input)

Kotlin

Java

Edit images (text and image input)

Kotlin

Java

Iterate and edit images through multi-turn chat

Kotlin

Java

Best practices and limitations

Next steps

Gemini Developer API