Cloudflare AI Search Reaches General Availability with Multimodal Embeddings, PDF OCR, and Usage-Based Pricing

Cloudflare AI Search Reaches General Availability with Multimodal Embeddings, PDF OCR, and Usage-Based Pricing Cloudflare has made AI Search generally available, introducing native multimodal image embeddings via Qwen3-VL-Embedding, optical character recognition for PDFs, larger file limits, and a structured pricing model effective November 1, 2026. AI Search combines Workers AI, Vectorize, R2, and Browser Run into an end-to-end index and retrieval service. Native visual retrieval embeds image pixels directly alongside captions using Matryoshka Representation Learning (MRL), supported by Qwen3-VL-Embedding. File size limits increased to 10 MiB, with OCR available to process scanned PDF documents. Billing begins November 1, 2026, across three dimensions: ingestion tokens, stored index data, and queries, accompanied by a free tier for all Workers plans. Multimodal Retrieval Architecture Moving beyond naive caption generation, AI Search preserves both pixel data and captions by utilizing Matryoshka Representation Learning to keep storage efficient. Native multimodal search is supported through the Qwen3-VL-Embedding model, which places images and text in the same vector space. For text-only embedding models, AI Search provides a fallback by converting query images into text using ToMarkdown. Data Processing and Document Ingestion Maximum file size limits for PDFs and text formats (such as Markdown, HTML, CSV, and JSON) have increased from 4 MiB to 10 MiB. For PDFs consisting of scanned images without raw text, users can enable OCR to extract page text before chunking and embedding. Queries undergo parallel vector and keyword lookups before fusion and optional reranking. Pricing Structure and Roadmap Billing goes live on November 1, 2026, charging $0.75 per million base ingestion tokens, an additional $0.50 per million tokens for image processing, $2.00 per GB-month for storage, $0.75 per 1,000 semantic queries, and $0.10 per 1,000 full-text queries. The free allotment includes 5 million ingestion tokens, 10 GB of storage, 1,000 semantic queries, and 1,000 full-text queries. Cloudflare also outlined plans to support video and audio ingestion, enhance keyword search scalability, and simplify indexing for existing Cloudflare sites.

Cloudflare 宣布 AI Search 正式上线并升级多模态检索与计费体系 Cloudflare 宣布其完全托管的索引与检索服务 AI Search 正式进入全面商用（GA）阶段，引入了原生图像嵌入、针对 PDF 的 OCR 识别及更大的文件上限，并公布了定于 2026 年 11 月 1 日生效的计费规则与免费额度。 AI Search 正式商用，通过 Qwen3-VL-Embedding 模型和 MRL 技术实现像素级原生图像嵌入与文本标注双重检索。 单文件限制由 4 MiB 提升至 10 MiB，并对扫描件类 PDF 提供全账户可用的 OCR 识别支持。 计费将于 2026 年 11 月 1 日启动，按内容摄入、数据存储和查询量收费，全系 Workers 提供包含 5M 摄入 Token 与各 1000 次查询的免费额度。 后续路线图包括扩展视频与音频摄入管线、重构关键词搜索引擎以支持更大规模数据，并简化站内索引构建。 原生多模态与图像检索增强 此前 AI Search 采用生成图片标注后再嵌入文本的方式，难以保留纹理、布局和色彩细节。新版本采用 Qwen3-VL-Embedding 模型直接嵌入图像像素，使图像与文本进入同一向量空间，同时保留文本标注以兼顾语义理解。为了控制存储与速度，系统应用了俄罗斯套娃表示学习（MRL）技术；若使用纯文本模型，系统会借助 ToMarkdown 将查询图像转为标注后再执行检索。 文件容量与 OCR 支持 系统支持的文本文件（Markdown、HTML、CSV、JSON 等）与 PDF 大小上限从 4 MiB 提高到 10 MiB。针对缺乏可提取文本的扫描版 PDF，各账户均可开启 OCR 功能先提取文字再分块和嵌入，该部分按图像处理摄入 Token 计费。 计费方案与免费额度明细 正式计费定于 2026 年 11 月 1 日生效。基础摄入费用为每百万 Token 0.75 美元（图像处理附加每百万 Token 0.50 美元），存储为每月每 GB 2.00 美元，语义查询与全文查询分别为每千次 0.75 美元和 0.10 美元；使用部分 Workers AI 模型时嵌入与重排序免费。免费额度涵盖每月 500 万摄入 Token、10 GB 存储，以及各 1,000 次语义与全文查询。 未来演进方向 团队正在构建支持完整视频与音频处理的摄入管线，以实现富媒体资产检索。同时正在重构关键词搜索引擎以克服当前大数据集的规模限制，并计划为部署在 Cloudflare 上的站点提供更便捷的 AI 索引创建方式，便于 AI Agent 发现和消费内容。

Cloudflare’s AI Search combines Workers AI, Vectorize, R2, and Browser Run into a fully managed index and retrieval pipeline. Since we launched AI Search over a year ago, we’ve seen developers use it to power a wide range of search use cases, from searching internal documentation to powering search for their websites. We use AI Search ourselves to power search on our own blog and developer docs. Starting today, AI Search is generally available. And as part of it, we've expanded and improved our support for multimodal formats beyond text, adding native [image embeddings](https://developers.cloudflare.com/ai-search/configuration/models/supported-models/#embedding), [optical character recognition (OCR) for PDFs](https://developers.cloudflare.com/ai-search/configuration/data-source/#images-and-optical-character-recognition), and [support for larger files](https://developers.cloudflare.com/ai-search/configuration/data-source/#file-limits). As part of general availability, we’ll start billing for AI Search on **November 1, 2026**, and continue to offer [a generous free tier](https://developers.cloudflare.com/ai-search/platform/limits-pricing/) on all Workers plans. An image is more than the sentence used to describe it. Product texture, screenshot state, chart relationships, document layout, and fine visual detail can all disappear when pixels are compressed into a caption. AI Search now preserves both signals: it embeds image pixels directly for visual retrieval while retaining captions for textual understanding. To keep these richer representations efficient, AI Search leverages [Matryoshka Representation Learning](https://arxiv.org/abs/2205.13147) (MRL), allowing smaller embeddings to retain useful information while keeping storage manageable and search fast. Although we originally supported retrieval over images, the implementation was naive: we would perform object detection, generate a caption, and then embed that text. This made images searchable, but only through the details captured in the caption. **Now, we do both — caption-based understanding and native image retrieval.** Native multimodal retrieval is available today with the [Qwen3-VL-Embedding](https://github.com/QwenLM/Qwen3-VL-Embedding) model. At query time, AI Search checks whether your instance’s embedding model supports images. If it does, a query image is embedded directly by that model, landing in the same vector space as your indexed images and text. If your embedding model is text-only, you can still query with an image. AI Search converts the query image to text with ToMarkdown and searches using the resulting caption. This gives every model basic multimodal support, while models with native image support get the full visual signal. | Caption-based understanding | A small bird with black-and-white markings perched among golden fruit and green leaves | | Native Image Retrieval | Can match details omitted from the caption: the geometry of the bird’s white eyebrow stripe, its yellow-green plumage, the mixture of smooth and weathered fruit, the leaves’ deeply ribbed texture, and the image’s warm palette and shallow-focus composition. | The caption is a compressed interpretation of the image. Capturing every potentially useful detail requires long or specialized captions, written with the eventual search query in mind. Native image embeddings preserve visual characteristics without requiring the caption to anticipate which details matter. This enables searches that are difficult to express precisely with words. You can describe an image you want to find, provide another image to locate visually similar results, or combine both, such as “a bird with similar markings” or “a bird perched on a leafy branch with plums.” It is useful for product discovery, screenshot matching, charts, diagrams, scanned documents, and other collections where color, texture, composition, or spatial relationships matter. Here’s how a query moves through AI Search. First, the query is optionally rewritten, then embedded (image queries are embedded directly by multimodal models, or captioned first by text-only models). Vector and keyword search run in parallel, and results are fused and optionally reranked. The top chunks are returned, or passed to a generation model to write an answer. AI Search now accepts your text files (Markdown, HTML, CSV, JSON and similar) and PDFs up to 10 MiB, up from 4 MiB. Many PDFs are really scanned images with no extractable text. For those, [turn on OCR](https://developers.cloudflare.com/ai-search/configuration/data-source/#images-and-optical-character-recognition) and AI Search reads the text from each page before chunking and embedding it. OCR is available to every account and is billed under the new [AI Search pricing](https://developers.cloudflare.com/ai-search/platform/limits-pricing) as image processing ingestion tokens. During our August 2026 Agents Week, we [announced preview pricing for AI Search](https://blog.cloudflare.com/ai-search-easier/#preview-pricing-pricing-you-can-predict). With the product going GA today, we’re announcing billing for AI Search that is going live on November 1, 2026. We’ll send a reminder email before billing is enabled. AI Search pricing is designed, so you can estimate your bill before you index a single file. You pay for three things: the content you ingest, the data you store, and the queries you run. The work in between (parsing, chunking, embedding with Workers AI models, keyword indexing, and reranking) is included. There are no instance hours, capacity units, or monthly minimums to size up front, and small projects fit inside the free monthly allotment. Ingestion pricing is based on one rate per token with whichever Workers AI embedding model you pick, and tokens are counted the same way for every model. Switching from a text-only embedding model to a multimodal one doesn't change what you pay to ingest, unless you are also processing images (add-on fee). Storage is priced on the size of data in your indices. Querying is priced based on the type of query (semantic vs. full-text) and how many queries you send. Estimating your cost comes down to how much content you index, how much you store, and how many queries you expect. Here's the pricing we announced in preview, with one tweak that we’re making: on the free monthly allotment, you will receive 1,000 semantic queries and 1,000 full-text queries (instead of a shared pool of 2,000 queries). | | Pricing | Free monthly allotment (all Workers plans) | | Ingestion | | | | Base Ingestion | $0.75 / 1M tokens | 5M tokens † | | Image processing (add-on) | +$0.50 / 1M tokens | 5M tokens † | | Storage | | | | Stored data | $2.00 / GB-month | 10 GB | | Query | | | | Semantic (hybrid and vector search) | $0.75 / 1k queries | 1,000 queries | | Full-text | $0.10 / 1k queries | 1,000 queries | | Embedding and Reranking | | | | Ingestion and query | Free with select Workers AI models; third-party billed separately | N/A | *† A single pool of 5M ingestion tokens per month, covering any file type currently supported (e.g., text, images).* Multimodal embedding support is just the first step; we’re building an ingestion pipeline to support full video and audio processing to allow our customers to search their rich media assets. We’re also refactoring the keyword search engine so that it scales better with your content requirements, particularly for when you have big data stores where the current implementation has limits. Finally, we’re developing better and simpler ways to enable AI Search and create indexes for websites already running on Cloudflare. This ensures AI agents can discover, explore, and consume content more easily and efficiently. Stay tuned for these follow-up announcements and more. AI Search is now generally available to enable and use today. Get started with our new multimodal embeddings, bigger files, OCR features, and our new managed instance pricing. Check out the [AI Search developer docs](https://developers.cloudflare.com/ai-search/) for more information.