[Product News](https://developer.android.com/blog/categories/product-news.md.txt) # ML Kit's Prompt API: Unlock Custom On-Device Gemini Nano Experiences 2 min read ![](https://developer.android.com/static/blog/assets/kakao_8769e675f9_Pq2bf.webp) 30 Oct 2025 3 Authors [Caren Chang,](https://developer.android.com/blog/authors/caren-chang.md.txt) [Chengji Yan,](https://developer.android.com/blog/authors/chengji-yan.md.txt) [Penny Li](https://developer.android.com/blog/authors/penny-li.md.txt) AI is making it easier to create personalized app experiences that transform content into the right format for users. We previously enabled developers to integrate with Gemini Nano through [ML Kit GenAI APIs](https://android-developers.googleblog.com/2025/05/on-device-gen-ai-apis-ml-kit-gemini-nano.html) tailored for specific use cases like summarization and image description. Today marks a major milestone for Android's on-device generative AI. We're announcing the **Alpha release of the ML Kit GenAI Prompt API**. This API allows you to send natural language and multimodal requests to Gemini Nano, addressing the demand for more control and flexibility when building with generative models. [Partners like Kakao are already building with Prompt API](https://android-developers.googleblog.com/2025/10/kakao-mobility-uses-gemini-nano-on.html), creating unique experiences with real-world impact. You can experiment with Prompt API's powerful features today with minimal code. [Video](https://www.youtube.com/watch?v=PoqJh_60Wrw) **Move beyond pre-built to custom on-device GenAI** Prompt API moves beyond pre-built functionality to support custom, app-specific GenAI use cases, allowing you to create unique features with complex data transformation. Prompt API uses Gemini Nano on-device to process data locally, enabling offline capability and improved user privacy. **Key use cases for Prompt API:** Prompt API allows for highly customized GenAI use cases. Here are some recommended examples: - Image understanding: Analyzing photos for classification (e.g., creating a draft social media post or identifying tags such as "pets," "food," or "travel"). - Intelligent document scanning: Using a traditional ML model to extract text from a receipt, and then categorizing each item with Prompt API. - Transforming data for the UI: Analyzing long-form content to create a short, engaging notification title. - Content prompting: Suggesting topics for new journal entries based on a user's preference for themes. - Content analysis: Classifying customer reviews into a positive, neutral, or negative category. - Information extraction: Extracting important details about an upcoming event from an email thread. **Implementation** Prompt API lets you create custom prompts and set optional generation parameters with just a few lines of code: ``` Generation.getClient().generateContent( generateContentRequest( ImagePart(bitmapImage), TextPart("Categorize this image as one of the following: car, motorcycle, bike, scooter, other. Return only the category as the response."), ) { // Optional parameters temperature = 0.2f topK = 10 candidateCount = 1 maxOutputTokens = 10 }, ) ``` For more detailed examples of implementing Prompt API, check out the [official documentation](https://developers.google.com/ml-kit/genai/prompt/android) and [sample on Github](https://github.com/googlesamples/mlkit/tree/master/android/genai). **Gemini Nano, performance, and prototyping** Prompt API currently performs best on the Pixel 10 device series, which runs the latest version of Gemini Nano (nano-v3). This version of Gemini Nano is built on the same architecture as Gemma 3n, the model we first shared with the open model community at I/O. The shared foundation between Gemma 3n and nano-v3 enables developers to more easily prototype features. For those without a Pixel 10 device, you can start experimenting with prompts today by prototyping with Gemma 3n locally. For the full list of devices that support GenAI APIs, refer to our [device support documentation.](https://developers.google.com/ml-kit/genai#device-support) **Learn more** Start implementing Prompt API in your Android apps today with guidance from our [official documentation](https://developers.google.com/ml-kit/genai/prompt/android) and the [sample on Github](https://github.com/googlesamples/mlkit/tree/master/android/genai). Written by: - ## [Caren Chang](https://developer.android.com/blog/authors/caren-chang.md.txt) ###### Developer Relations Engineer [read_more View profile](https://developer.android.com/blog/authors/caren-chang) ![View Caren Chang's profile](https://developer.android.com/static/blog/assets/Caren_Chang_e58d793559_Z7OUJq.webp) ![View Caren Chang's profile](https://developer.android.com/static/blog/assets/Caren_Chang_e58d793559_Z7OUJq.webp) - ## [Chengji Yan](https://developer.android.com/blog/authors/chengji-yan.md.txt) ###### Software Engineer [read_more View profile](https://developer.android.com/blog/authors/chengji-yan) ![View Chengji Yan's profile](https://developer.android.com/static/blog/assets/Chengji_Yan_575ccacca8_1LkRjE.webp) ![View Chengji Yan's profile](https://developer.android.com/static/blog/assets/Chengji_Yan_575ccacca8_1LkRjE.webp) - ## [Penny Li](https://developer.android.com/blog/authors/penny-li.md.txt) ###### Software Engineer [read_more View profile](https://developer.android.com/blog/authors/penny-li) ![](https://developer.android.com/static/blog/assets/default-avatar.DvQ_6oi6_Z1SMg9h.svg) ![View Charles Munger's profile](https://developer.android.com/static/blog/assets/default-avatar.DvQ_6oi6_Z1SMg9h.svg) Continue reading - [![View Caren Chang's profile](https://developer.android.com/static/blog/assets/Caren_Chang_e58d793559_Z7OUJq.webp)](https://developer.android.com/blog/authors/caren-chang.md.txt)[![View David Chou's profile](https://developer.android.com/static/blog/assets/David_Chou_226df78370_ZVseX2.webp)](https://developer.android.com/blog/authors/david-chou.md.txt) 02 Apr 2026 02 Apr 2026 ![](https://developer.android.com/static/blog/assets/announcing_gemma4_aicore_ce479292b9_Z2rWEol.webp) [Product News](https://developer.android.com/blog/categories/product-news.md.txt) ## [Announcing Gemma 4 in the AICore Developer Preview](https://developer.android.com/blog/posts/announcing-gemma-4-in-the-ai-core-developer-preview.md.txt) [arrow_forward](https://developer.android.com/blog/posts/announcing-gemma-4-in-the-ai-core-developer-preview.md.txt) At Google, we're committed to bringing the most capable AI models directly to the Android devices in your pocket. Today, we're thrilled to announce the release of our latest state-of-the-art open model: Gemma 4. [Caren Chang](https://developer.android.com/blog/authors/caren-chang.md.txt), [David Chou](https://developer.android.com/blog/authors/david-chou.md.txt) • 3 min read - 4 Authors 28 Jan 2026 28 Jan 2026 ![](https://developer.android.com/static/blog/assets/Prompt_API_Banner_1_ff0c780828_Zxdllo.webp) [Product News](https://developer.android.com/blog/categories/product-news.md.txt) ## [How Automated Prompt Optimization Unlocks Quality Gains for ML Kit's GenAI Prompt API](https://developer.android.com/blog/posts/how-automated-prompt-optimization-unlocks-quality-gains-for-ml-kit-s-gen-ai-prompt-api.md.txt) [arrow_forward](https://developer.android.com/blog/posts/how-automated-prompt-optimization-unlocks-quality-gains-for-ml-kit-s-gen-ai-prompt-api.md.txt) To further help bring your ML Kit Prompt API use cases to production, we are excited to announce Automated Prompt Optimization (APO) targeting On-Device models on Vertex AI. Automated Prompt Optimization is a tool that helps you automatically find the optimal prompt for your use cases. [Chetan Tekur](https://developer.android.com/blog/authors/chetan-tekur.md.txt), [Chao Zhao](https://developer.android.com/blog/authors/chao-zhao.md.txt), [Paul Zhou](https://developer.android.com/blog/authors/paul-zhou.md.txt), [Caren Chang](https://developer.android.com/blog/authors/caren-chang.md.txt) • 3 min read - [![View Michelle Martin's profile](https://developer.android.com/static/blog/assets/unnamed_29_8358471ffe_MSkhy.webp)](https://developer.android.com/blog/authors/michelle-martin.md.txt) 10 Nov 2026 10 Nov 2026 ![](https://developer.android.com/static/blog/assets/ABL_Sign_in_with_Google_Plugin_for_Unity_Gaming_DESIGN_Header_and_metadata_V01_26433b75fe_Z260GOa.webp) [Product News](https://developer.android.com/blog/categories/product-news.md.txt) ## [Powering Seamless Player Sign-In: Introducing the Open-Source Sign in with Google Plugin for Unity](https://developer.android.com/blog/posts/open-source-google-sign-in-unity.md.txt) [arrow_forward](https://developer.android.com/blog/posts/open-source-google-sign-in-unity.md.txt) With Unity powering over half of all mobile titles worldwide, first impressions matter. For game developers, a smooth, reliable player onboarding experience is essential to driving day-one retention and long-term engagement. [Michelle Martin](https://developer.android.com/blog/authors/michelle-martin.md.txt) • 1 min read Stay in the loop Get the latest Android development insights delivered to your inbox weekly. [mail Subscribe](https://developer.android.com/subscribe) ![A 3D illustration of the Android mascot, wearing a jetpack that's emitting a large cloud of bubbles](https://developer.android.com/static/blog/assets/rocket-android.CVJQZOf1_1zVtXW.webp)