The AI-specific pieces of Cloudflare’s platform, read on their own: Workers AI, Vectorize, AI Gateway, and the trade-offs of building on these bindings.
The Cloudflare AI Stack series covers the infrastructure around AI apps: where models run, how gateway control works, how RAG is built, how agents keep running, how memory is governed, and how browser, sandbox, secrets, data, and observability fit into a product.
env.AI is not just run(). It also exposes toMarkdown (document-to-Markdown conversion), autorag (managed RAG), gateway (external provider proxy), and models (metadata lookup). Understanding these four method groups is what unlocks Cloudflare as a full AI platform inside Workers.
For running Traditional Chinese LLM workloads on Cloudflare Workers AI, the Gemma family follows instructions more reliably than same-tier Llama models. gemma-3-12b-it was marked deprecated on 2026-05-30; the current equivalent is gemma-4-26b-a4b-it: 256K context, Vision, Function calling, at $0.10 / $0.30 per M tokens.
AI Gateway is the control plane for AI calls: one layer for logs, analytics, cache, rate limits, retry/fallback, BYOK, and Unified Billing. In Workers, use env.AI.run(..., { gateway }); with external SDKs, change the baseURL or provider-native endpoint.
Formerly AutoRAG, the managed search primitive: drop files into built-in storage or attach R2 and websites, auto-index with Markdown conversion plus vector and BM25, retrieve with hybrid, RRF, and reranking, and query from Workers via namespace or instance bindings, REST, or MCP.
Vectorize is Cloudflare's vector database. AI Search is the right starting point for a managed RAG pipeline; Vectorize is the better fit when you need control over chunking, embeddings, metadata filters, hybrid retrieval, reindexing, and fallback behavior.
Cloudflare Agents turns an agent session into a durable runtime: each agent instance has stable identity, local SQLite, WebSockets, scheduled work, recoverable execution, and tools. It is not just a chat example; it composes Workers, Durable Objects, AI models, Browser, Sandbox, AI Search, and MCP into a deployable agent app.
Agent Memory is a Cloudflare private beta service for letting agents remember users, teams, projects, and task context across conversations. It fits facts, events, instructions, and tasks; RAG documents, product data, files, and audit logs should still live in AI Search, Vectorize, D1, or R2.
Browser Run gives Workers access to Cloudflare-managed headless Chrome. Quick Actions fit one-shot tasks such as screenshots, PDFs, HTML, JSON, and crawls; Browser Sessions fit Puppeteer, Playwright, CDP, and Stagehand automation where you need full control.
Cloudflare Sandboxes uses a Worker as the entry point, a named Durable Object as the control plane, and a Container inside an isolated VM as the execution plane. It fits Cloudflare-native fleets of ephemeral Linux workspaces, but persistence, security boundaries, and three layers of billing remain your responsibility.
Secrets Store is Cloudflare's open beta account-level secret store, currently integrated with Workers and AI Gateway. It fits provider API keys, BYOK keys, and secrets reused across Workers; per-Worker secrets still work, but the governance scope is different.
An AI app should not put conversations, artifacts, memory, retrieval documents, locks, and eval traces into one store. D1 fits queryable product data, R2 fits large files and artifacts, Durable Objects fit named coordination and per-session state, and Agent Memory / AI Search / Vectorize handle memory and retrieval.
Workers Observability is for debugging and request tracing; Workers Analytics Engine is for high-cardinality product events and custom metrics; GraphQL Analytics API is for querying existing Cloudflare product data. Keeping those roles separate prevents logs from becoming a database and keeps billing, monitoring, and product analytics from blending together.
Durable Objects map a name or ID to a globally unique, single-threaded actor with private SQLite storage. They fit per-room, per-user, per-tenant, and per-run coordination boundaries; the real design question is where the object key belongs.