Cloudflare Introduces AI Search Developer Improvements and Pricing Preview

Cloudflare Introduces AI Search Developer Improvements and Pricing Preview Cloudflare has introduced developer experience updates for Cloudflare AI Search, turning it into an automated solution for crawling, indexing, and querying data. The system allows AI agents to access fresh site data through Model Context Protocol endpoints or Worker bindings, backed by an upcoming predictable pricing structure. AI Search automates crawling, embedding, and retrieval across multiple sites, replacing the manual stitching of primitives like Vectorize, R2, and Workers AI. Developers can expose search via a Cloudflare Worker binding or through public, zero-code /search and /mcp endpoints secured with custom domains and Cloudflare Access. Internal platforms including Developer Docs, the Cloudflare Blog, and the Cloudflare Dev Stack MCP run on the service using hybrid semantic and keyword search. AI Search is currently free in beta, with an upcoming pricing model that keeps default embedding and reranking free while billing for ingestion, storage, queries, and optional model generation. Automated Ingestion and Flexible Query Endpoints Cloudflare AI Search replaces the manual orchestration of Workers AI, Vectorize, AI Gateway, R2, and Browser Run with an automated workflow. It ingests single sites or multi-domain sets using a crawler that identifies itself as Cloudflare-AI-Search while honoring robots.txt. Queries across instances can be handled inside a Cloudflare Worker to fan out requests within remote MCP servers, or exposed through zero-code public /search and /mcp endpoints. These endpoints support custom domains and can be protected with Cloudflare Access for authenticated agent or user querying. Dev Stack MCP and Internal Implementations Cloudflare uses AI Search to power search across its own developer documentation, Cloudflare.com, and its official blog via an EmDash integration. It also drives the Cloudflare Dev Stack MCP, which queries 10 Cloudflare-owned surfaces to provide coding agents with up-to-date, cited documentation directly inside agentic workflows. All internal deployments utilize hybrid search, combining semantic understanding with keyword matching to support both natural-language queries and exact identifier lookups. Pricing Structure and Beta Availability Currently free while in beta, AI Search will transition to a predictable pricing model designed around usage pools. Default embedding and reranking models remain free of charge, removing token predictability concerns for core indexing and ranking. Ingestion includes an initial pool of 5 million tokens per month, query tiers provide a base pool of 2,000 monthly queries, and additional costs apply to image processing, storage, and optional Workers AI generation or query rewriting tasks.

Cloudflare 推出 AI Search 开发者体验更新及定价预览 Cloudflare 宣布对 AI Search 进行体验改进，将抓取、摄取与检索等分散组件自动化整合为开箱即用的方案，并引入模型上下文协议（MCP）支持与多站点联合搜索能力。 AI Search 实现了端到端自动化抓取、向量化与混合检索，支持跨多个实例和站点发起联合查询。 提供 Worker 绑定与免部署公共端点两种接入方式，原生支持 `/search` 与 `/mcp` 接口及安全访问控制。 服务在 Beta 阶段免费，未来定价中默认的嵌入与重排序模型将保持免费，并提供每月 500 万摄取 Token 的免费池。 端到端自动化与多源联合检索 以往开发者需要手动组装 Workers AI、Vectorize、R2 和 Browser Run 等组件，更新后的 AI Search 能自动处理爬取、解析、向量嵌入和检索全流程。爬虫采用公开的专用标识符并遵循 robots.txt 规则。针对跨域资产，系统可将多个独立实例视作统一集合，单次调用即可扇出查询所有实例，官方已借此构建了覆盖十个生态站点的 Dev Stack MCP。 接入方式与 Agent 工具化支持 开发者可以通过两种路径调用搜索：一是将命名空间绑定至 Worker 构建远程 MCP 服务器，作为代码智能体（Agent）的扩展工具直接返回具名引用的最新文档；二是直接启用公共端点，免代码生成公开的 `/search` 与 `/mcp` URL。公共端点支持绑定自定义域名，且可在前端挂载 Cloudflare Access 实现权限认证与私有化访问。 内部应用落地与可预测定价机制 AI Search 结合了语义与关键词的混合搜索能力，已被部署在 Cloudflare 官网、开发者文档以及基于 EmDash CMS 的官方博客中。该服务目前处于免费公测期，未来计费模型侧重可预测性：使用默认模型进行向量化和重排序不计费，答案生成和查询重写作为可选步骤计费，同时每月提供 500 万摄取 Token 与 2000 次查询的通用免费额度。

Today, we’re excited to announce a few developer experience improvements to [Cloudflare AI Search](https://developers.cloudflare.com/ai-search/) to make it easy to manage a search solution out of the box. Previously, you had to stitch together components of the Cloudflare primitives (Workers AI, AI Gateway, Vectorize, R2, Browser Run) but now, AI Search can do this automatically, and better. Our goal is to give your agents their own search engine, where they can easily find data to provide better answers for themselves and their humans. We’re also sharing an early preview of pricing for customers of AI Search so you can learn how this scales. We modeled pricing in a way that makes it predictable and scalable: embedding and reranking are free when you use the default models, so no need to worry about predicting token count. In AI Search, users can now: `/search` and `/mcp` endpoint that can search through multiple instances or websites at once without authentication, so you can share easily with your customers.`search.example.com/mcp`). You can also add Finally, we will also share examples of how AI Search is used across our own platform including [Cloudflare.com](http://Cloudflare.com), our Developer Docs, with EmDash, in Cloudflare Dev Stack MCP — and even the blog post you’re reading right now (try cmd+K). One of the ways we use AI Search is in our new **Cloudflare Dev Stack MCP**, which you can try today in our [AI Playground](https://playground.ai.cloudflare.com). It gives coding agents current, cited docs from across the Cloudflare developer ecosystem, so they build on the latest features and fixes instead of stale training data. Here's how we built it using the features available today in AI Search: We created one AI Search instance per Cloudflare-owned surface: Docs, Blog, API Docs, Community, Astro, Vite, Vitest, Hono, Replicate, OpenNext. (Each of these is Cloudflare-owned.) They span different domains, but, because Cloudflare owns the website data, AI Search is able to treat them as a single set and ingest them all the same way. Point AI Search at a site, or set of sites, and it handles crawling, ingestion, embedding, and retrieval. Creating an instance is a single command, and for a site without a sitemap you add --parse-type discover to find pages by following links (powered by /crawl from Browser Run): Now the interesting part: answering a single query across all 10 instances. There are two ways to do it. **Option A: in a Worker (what we did for Cloudflare Stack MCP)** We bound the namespace to a Worker to create a [remote MCP server](https://developers.cloudflare.com/agents/model-context-protocol/guides/remote-mcp-server/) and made one multi-instance call across all 10 instances. We took this path because we're adding the stack search into [Cloudflare's MCP server](https://github.com/cloudflare/mcp-server-cloudflare), so it ships as a tool alongside the Cloudflare tools agents already connect to. The binding, in `wrangler.jsonc:` Then a single tool makes one call that fans out across the instances you name: **Option B: flip on public endpoints (no code)** If you'd rather not write a Worker at all, enable public URLs on the namespace. You immediately get /search and /mcp endpoints that query every instance, with no auth and nothing to deploy. Reach for the Worker when you're folding search into an existing app or MCP server, as we are. Or reach for the public endpoint when you just want a shareable search endpoint in one click. Public endpoints come with a default public URL, but you can put your own **custom domain** over them to brand the endpoint (e.g., `search.example.com/mcp`). If the search should be private, add **Cloudflare Access** in front of the domain. The endpoint now requires a login, so only authorized people (or agents) can query it. With the Cloudflare Dev Stack MCP Server, you can ask about any tool, or describe an app you want to build, and you'll get back current, cited answers on how best to build it on the Cloudflare stack. The [AI Playground](https://playground.ai.cloudflare.com) is worth checking out, but the real magic is wiring the MCP into your coding agent, so the stack's current docs are one tool call away. That replaces the usual fallback (web search then fetching full pages), which is slow, token-heavy, and often lands on the wrong or stale source. To use with your agent of choice, drop the Dev Stack MCP URL into your MCP configuration. For example: We build with AI Search the same way our customers would: Cloudflare Blog's search already runs on it, and today Developer Docs and [Cloudflare.com](http://Cloudflare.com) join it. All of it uses hybrid search, semantic and keyword together in one query, so it handles both open-ended "what does this do" questions and exact lookups of names or keywords. We recently rebuilt the Blog on EmDash, our new open-source CMS, and our new [EmDash AI Search integration](https://docs.emdashcms.com/deployment/cloudflare/#cloudflare-ai-search) is what powers that search now. You can also add it to your own EmDash site and get the same search over your content out of the box. AI Search is powered by Browser Run `/crawl` in the background, but goes a step further to identify itself with its own bot identity: `Cloudflare-AI-Search`. Just like Browser Run, it follows robots.txt, identifies itself with an immutable, public user agent, and will respect whatever bot controls a site has in place. AI Search is currently free while in beta, and billing is not yet enabled; we'll email you with plenty of notice before it starts. As we move toward general availability, here's a preview of pricing across ingestion, storage, and queries, plus embedding and reranking (*preview prices are subject to change before billing begins)*: *† A single pool of 5M ingestion tokens per month, covering any file type currently supported (e.g., text, images). ‡ A single pool of 2,000 queries per month, shared across both query types.*  Our goal is to provide pricing you can predict, starting with the models your search leans on. Embedding turns your text into the vectors that search matches on, and reranking reorders results so the most relevant come first. Both run free with AI Search defaults or when using select models from the Workers AI catalog, so the models behind indexing and every search are not a cost you have to worry about. Answer generation and query rewriting are optional steps that run on a model you choose, billed as Workers AI usage, or you can use AI Gateway credits with any model/provider. Here's a sample monthly bill on the Workers Paid plan for creating a new AI Search instance for a 20,000-document data source (about 20M tokens of text) plus 1,000 images (assume about 1,000 tokens each), with 30,000 semantic queries a month using the default AI Search embedding and reranking model. Ingestion is chunked with roughly 10% overlap, which shows up as the × 1.1 below: Images count toward base ingestion and also incur the image add-on cost. Storage assumes about 10 KB per document and 1 MB per image. Indexing is largely a one-time cost, so later months are mostly queries, closer to $21. AI Search is available to enable and use today. Point it at your site, turn on hybrid search for both semantic and keyword matching, and you have a search engine for your own data, ready for your agents. Spin one up with one command: From there, query it, wire it into an agent over `/mcp`, or put a custom domain on a public `/search` endpoint to share it with your users. Check out the [AI Search docs](https://developers.cloudflare.com/ai-search/) for more information.