{"slug": "vertex-ai-in-firebase-is-now-firebase-ai-logic-what-actually-changed", "title": "Vertex AI in Firebase is Now Firebase AI Logic: What Actually Changed", "summary": "Google rebranded Vertex AI in Firebase to Firebase AI Logic in May 2025, expanding the client-side SDK to support both the Gemini Developer API and the enterprise Agent Platform backend. The change introduces a new firebase/ai package replacing firebase/vertexai, with getAI() and backend selection replacing getVertexAI(), plus App Check protection, multimodal chat responses, and Gemini Nano on-device support in Chrome. A developer migrating a real Angular + Gemini project documented the SDK import changes and provider-switching code required to move off the deprecated Vertex-only path.", "body_md": "If you learned Vertex AI in Firebase last year and came back in 2026 to find Firebase AI Logic, you’re not alone as I went through the same reset. I’d already shipped an [Angular + Gemini demo](https://bytewiseshop.web.app/), then spent days reconciling old blog posts, renamed Console menus, and SDK imports that no longer compiled. This article is the companion to my setup tutorial: not *how to wire Angular*, but *what the rebrand actually means* and what’s new compared to the original Vertex-only path. This is documented from the mistakes and migration work I did on a real project.\n\nIn **May 2025**, Firebase renamed and expanded it to **Firebase AI Logic**. The rename reflects a wider scope, not a different product category. Same client-side idea; more backends and features.\n\n| Era | Name | What it meant | \n|---|---|---|\n| May 2024 | Vertex AI in Firebase (preview) | Client SDKs → Vertex AI Gemini API only | \n| Oct 2024 | Vertex AI in Firebase (GA) | Production-ready Vertex path | \n| May 2025+ | **Firebase AI Logic** | Agent Platform Gemini API **or** Gemini Developer API, new SDK, expanded platform support | \n\n`GoogleAIBackend`)\nThe biggest addition. Prototype on the **Spark (free) plan**, then scale. Console: **Build → AI Logic → Get started → Gemini Developer API**. The original product only offered the enterprise Vertex/Agent Platform path.\n\nSwitch providers by changing initialization:\n\n``` js\nimport { getAI, GoogleAIBackend, AgentPlatformBackend } from 'firebase/ai';\n\n// Gemini Developer API — easiest way to get started (this guide uses this)\ngetAI(app, { backend: new GoogleAIBackend() });\n\n// Agent Platform / enterprise (what Vertex AI in Firebase was built around)\ngetAI(app, { backend: new AgentPlatformBackend('global') });\n```\n\nYou can enable both APIs in one Firebase project.\n\nApp Check can protect Developer API traffic, not just the enterprise backend. Required for production AI Logic on web; this guide wires it in Part 2.\n\nMigrate from the deprecated path:\n\n| Vertex AI in Firebase | Firebase AI Logic | \n|---|---|\n| `firebase/vertexai` | `firebase/ai` | \n| `getVertexAI()` | `getAI()` + backend | \n\nFirebase Console dashboards now cover client-side AI Logic requests (not only server-side Genkit).\n\nClient-side AI Logic for games and Android XR.\n\nMultimodal chat responses (text + image), beyond Imagen-only client access.\n\nGemini Nano on Chrome with `prefer_on_device`, falling back to cloud automatically.\n\nFirebase AI Logic authorizes Developer API calls via a **Google-managed service account**, not a Gemini API key embedded in your app. Use your normal Firebase web `apiKey` + App Check; do not add Generative Language API to that key's allowlist (if it's still available as an option).\n\n``` js\n// BEFORE — Vertex AI in Firebase\nimport { getVertexAI, getGenerativeModel } from 'firebase/vertexai';\nconst vertexAI = getVertexAI(app);\nconst model = getGenerativeModel(vertexAI, { model: 'gemini-2.0-flash' });\n\n// AFTER — Firebase AI Logic\nimport { getAI, getGenerativeModel, GoogleAIBackend } from 'firebase/ai';\nconst ai = getAI(app, { backend: new GoogleAIBackend() });\nconst model = getGenerativeModel(ai, { model: 'gemini-2.5-flash' });\n```\n\nOfficial references: [May 2025 announcement](https://firebase.blog/posts/2025/05/building-ai-apps/), [FAQ — why the name changed](https://firebase.google.com/docs/ai-logic/faq-and-troubleshooting).", "url": "https://wpnews.pro/news/vertex-ai-in-firebase-is-now-firebase-ai-logic-what-actually-changed", "canonical_source": "https://dev.to/wayne_gakuo/vertex-ai-in-firebase-is-now-firebase-ai-logic-what-actually-changed-fbb", "published_at": "2026-09-16 11:27:18+00:00", "updated_at": "2026-09-16 11:42:32.018112+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "generative-ai", "large-language-models", "developer-tools"], "entities": ["Google", "Firebase", "Firebase AI Logic", "Vertex AI in Firebase", "Gemini Developer API", "Agent Platform", "Gemini Nano", "Angular"], "alternates": {"html": "https://wpnews.pro/news/vertex-ai-in-firebase-is-now-firebase-ai-logic-what-actually-changed", "markdown": "https://wpnews.pro/news/vertex-ai-in-firebase-is-now-firebase-ai-logic-what-actually-changed.md", "text": "https://wpnews.pro/news/vertex-ai-in-firebase-is-now-firebase-ai-logic-what-actually-changed.txt", "jsonld": "https://wpnews.pro/news/vertex-ai-in-firebase-is-now-firebase-ai-logic-what-actually-changed.jsonld"}}