The Google AI Dart SDK is the easiest way for Dart developers to build with the Gemini API. The Gemini API gives you access to Gemini models created by Google DeepMind. Gemini models are built from the ground up to be multimodal, so you can reason seamlessly across text, images, and code.

[!CAUTION] Using the Google AI SDK for Dart (Flutter) to call the Google AI Gemini API directly from your app is recommended for prototyping only. If you plan to enable billing, we strongly recommend that you use the SDK to call the Google AI Gemini API only server-side to keep your API key safe. You risk potentially exposing your API key to malicious actors if you embed your API key directly in your mobile or web app or fetch it remotely at runtime.

1. Go to Google AI Studio.
2. Login with your Google account.
3. Create an API key. Note that in Europe the free tier is not available.
4. Try a Dart CLI sample or the Flutter sample app.
5. For detailed instructions, try the Dart SDK tutorial on ai.google.dev.

See the Gemini API Cookbook or ai.google.dev for complete code.

1. Add a dependency on the package:google_generative_ai package via:

dart pub add google_generative_ai

or:

flutter pub add google_generative_ai

1. Initialize the API client

final model = GenerativeModel(model: 'gemini-1.5-flash-latest', apiKey: apiKey);

1. Call the API to run a prompt

final prompt = 'Do these look store-bought or homemade?';
final imageBytes = await File('cookie.png').readAsBytes();
final content = [
  Content.multi([
    TextPart(prompt),
    DataPart('image/png', imageBytes),
  ])
];

final response = await model.generateContent(content);
print(response.text);

See the Gemini API Cookbook or ai.google.dev for complete documentation.

See Contributing for more information on contributing to the Generative AI SDK for Dart.

The contents of this repository are licensed under the Apache License, version 2.0.