--- title: Introducing Vertex AI for Firebase | daily.dev description: Google introduces Vertex AI for Firebase, a suite of client SDKs (Swift, Kotlin, Java, Dart, JavaScript) that let mobile and web developers call Gemini models... canonical: https://daily.dev/posts/introducing-vertex-ai-for-firebase-tuaucwsdr twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing Vertex AI for Firebase | daily.dev og:description: Google introduces Vertex AI for Firebase, a suite of client SDKs (Swift, Kotlin, Java, Dart, JavaScript) that let mobile and web developers call Gemini models... og:url: https://daily.dev/posts/introducing-vertex-ai-for-firebase-tuaucwsdr og:image: https://api.daily.dev/og/posts/TuaUcWSDr.png og:image:alt: Introducing Vertex AI for Firebase og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Introducing Vertex AI for Firebase **[Firebase](https://daily.dev/sources/firebase-blog)** · 7 min read · 0 upvotes · 0 comments ## Summary Google introduces Vertex AI for Firebase, a suite of client SDKs (Swift, Kotlin, Java, Dart, JavaScript) that let mobile and web developers call Gemini models directly from their apps without building a backend service layer. The SDKs include Firebase App Check integration for securing API calls, Cloud Storage integration for multimodal file uploads, and Remote Config support for updating prompts and model versions without app releases. The product launches in public preview now, with general availability planned for fall of the same year. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Can I call the Vertex AI Gemini API directly from a mobile or web app without building my own backend? Yes, Vertex AI for Firebase provides client SDKs for Swift, Kotlin, Java, Dart, and JavaScript that let apps call Gemini models like Gemini 1.5 Pro and 1.5 Flash directly, removing the need for a Python, Java, Node.js, or Go backend service layer. Security is handled through Firebase App Check, which verifies that requests come from genuine apps and devices. _daily.dev surfaces updates like this for developers deciding how to add AI features without standing up a backend._ ### How do I prevent unauthorized use of my API key when calling generative AI models from a client app? Vertex AI for Firebase SDKs integrate with Firebase App Check, which verifies the authenticity of each call to the Vertex AI Gemini API so only legitimate requests from genuine apps and devices get processed. This protects against malicious actors extracting client-side API keys, which could otherwise cause unexpected costs, data breaches, or quota overages. _Developers securing client-side AI calls can track tooling like this on daily.dev._ ### How can I update AI model versions and prompts in my app without shipping a new app release? Firebase Remote Config lets you store default prompt text and model name values in your app, then change those defaults from the Firebase console for all users or specific test groups, without requiring an app update download. This supports A/B testing prompts and switching Gemini model versions as new ones are released. _daily.dev helps developers keep up with tools for iterating on AI prompts and models in production._ ## Similar posts on daily.dev - [Build smarter apps with Gemini 3 Flash](https://daily.dev/posts/build-smarter-apps-with-gemini-3-flash-rgootmsr4) · Android Developers Blog · 76 upvotes · 2 comments - [Introducing Google Cloud Vertex AI Extensions for .NET](https://daily.dev/posts/introducing-google-cloud-vertex-ai-extensions-for-net-0ffxvzvkv) · Google Cloud · 33 upvotes · 1 comments - [Serverless AI for Android with Firebase AI Logic](https://daily.dev/posts/serverless-ai-for-android-with-firebase-ai-logic-33d7pefc4) · ProAndroidDev · 0 upvotes · 0 comments - [Building Arc: An AI Messenger Powered by Firebase, Flutter, and Vertex AI](https://daily.dev/posts/building-arc-an-ai-messenger-powered-by-firebase-flutter-and-vertex-ai-q8gkjyhtf) · Firebase Developers · 45 upvotes · 7 comments - [Using the new Google Gen AI SDK for Kotlin](https://daily.dev/posts/using-the-new-google-gen-ai-sdk-for-kotlin-tzotbujuu) · John O'Reilly · 2 upvotes · 0 comments --- Tags: [#mobile](https://daily.dev/tags/mobile), [#genai](https://daily.dev/tags/genai), [#firebase](https://daily.dev/tags/firebase), [#google-gemini](https://daily.dev/tags/google-gemini), [#vertex-ai](https://daily.dev/tags/vertex-ai) [View this post on daily.dev](https://daily.dev/posts/introducing-vertex-ai-for-firebase-tuaucwsdr) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Introducing Vertex AI for Firebase","url":"https://daily.dev/posts/introducing-vertex-ai-for-firebase-tuaucwsdr","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-vertex-ai-for-firebase-tuaucwsdr"},"datePublished":"2026-08-23T12:18:28.340Z","dateModified":"2026-08-23T12:28:33.217Z","description":"Google introduces Vertex AI for Firebase, a suite of client SDKs (Swift, Kotlin, Java, Dart, JavaScript) that let mobile and web developers call Gemini models...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c878454ec3a164c5737864e766f8f5a9?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/c878454ec3a164c5737864e766f8f5a9?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Firebase","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Firebase","logo":"https://media.daily.dev/image/upload/s--i395oqZH--/f_auto,q_auto/v1787487448/logos/firebase-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/firebase-blog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/introducing-vertex-ai-for-firebase-tuaucwsdr","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"mobile,genai,firebase,google-gemini,vertex-ai","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Firebase","item":"https://daily.dev/sources/firebase-blog"},{"@type":"ListItem","position":3,"name":"Introducing Vertex AI for Firebase"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/introducing-vertex-ai-for-firebase-tuaucwsdr#faq","mainEntity":[{"@type":"Question","name":"Can I call the Vertex AI Gemini API directly from a mobile or web app without building my own backend?","acceptedAnswer":{"@type":"Answer","text":"Yes, Vertex AI for Firebase provides client SDKs for Swift, Kotlin, Java, Dart, and JavaScript that let apps call Gemini models like Gemini 1.5 Pro and 1.5 Flash directly, removing the need for a Python, Java, Node.js, or Go backend service layer. Security is handled through Firebase App Check, which verifies that requests come from genuine apps and devices. daily.dev surfaces updates like this for developers deciding how to add AI features without standing up a backend."}},{"@type":"Question","name":"How do I prevent unauthorized use of my API key when calling generative AI models from a client app?","acceptedAnswer":{"@type":"Answer","text":"Vertex AI for Firebase SDKs integrate with Firebase App Check, which verifies the authenticity of each call to the Vertex AI Gemini API so only legitimate requests from genuine apps and devices get processed. This protects against malicious actors extracting client-side API keys, which could otherwise cause unexpected costs, data breaches, or quota overages. Developers securing client-side AI calls can track tooling like this on daily.dev."}},{"@type":"Question","name":"How can I update AI model versions and prompts in my app without shipping a new app release?","acceptedAnswer":{"@type":"Answer","text":"Firebase Remote Config lets you store default prompt text and model name values in your app, then change those defaults from the Firebase console for all users or specific test groups, without requiring an app update download. This supports A/B testing prompts and switching Gemini model versions as new ones are released. daily.dev helps developers keep up with tools for iterating on AI prompts and models in production."}}]} ```