大模型
developers.cloudflare.com ·
@Cloudflare Developers
Cloudflare AI Search 正式 GA：默认混合检索，支持多模态嵌入与 OCR
Cloudflare 宣布 AI Search 正式可用（GA），自2026年11月1日起按用量计费，涵盖每月包含的摄取、存储、语义查询与全文查询额度。新实例默认启用混合检索（语义向量检索结合全文匹配），创建实例时可另选索引方式。Workers AI 的嵌入与重排序调用纳入 AI Search 计费，不再出现在 Workers AI 账单或 AI Gateway 日志中。产品新增对 @cf/qwen/qwen3-vl-embedding-2b 与 google-ai-studio/gemini-embedding-2 多模态嵌入模型的支持，搜索与对话请求可通过 REST API 和公共端点传入图片。OCR 面向所有账户开放以处理扫描版 PDF，启用 OCR 的纯文本/代码文件及 PDF 上限提升至 10 MiB，未启用 OCR 的 PDF 及其他格式仍为 4 MiB。创建实例时 type 字段变为可选，系统可从 HTTP/HTTPS URL 推断网站源，或从已有存储桶名推断 R2 源。
AI推荐理由 Cloudflare官方开发者更新日志，属一手产品发布信息，事实明确、条目清晰。核心新信息包括：AI Search正式GA、11月1日起按用量计费、默认启用混合检索（语义向量+全文匹配）、Workers AI嵌入与重排序调用纳入AI Search计费、支持Qwen3-VL与Gemini多模态嵌入模型及图片检索、OCR全账户可用并将带OCR的PDF/文本文件上限提至10MiB、source type可自动推断。对构建RAG/搜索应用的开发者有直接落地参考价值；局限在于未提供性能基准或实际效果数据。
82
正文
AI Search is now generally available. Usage-based billing begins on November 1, 2026, with included monthly ingestion, storage, semantic query, and full-text query usage. Cloudflare will send a reminder email the week before billing begins.
Refer to [Limits & pricing](https://developers.cloudflare.com/ai-search/platform/limits-pricing/) for rates and included usage.
#### Hybrid search is on by default
New AI Search instances use hybrid search by default. Hybrid search combines semantic vector retrieval with full-text matching. You can choose a different index method when you create an instance.
Refer to [Hybrid search](https://developers.cloudflare.com/ai-search/configuration/indexing/hybrid-search/) for details.
#### Workers AI embeddings and reranking are included
Workers AI embedding and reranking calls made by AI Search are included in AI Search pricing. These calls no longer appear on your Workers AI bill or in your AI Gateway logs. Generation, query rewriting, and external providers continue to use your account and gateway.
Refer to [Limits & pricing](https://developers.cloudflare.com/ai-search/platform/limits-pricing/) for details.
#### Multimodal model and image support
AI Search supports the `@cf/qwen/qwen3-vl-embedding-2b` and `google-ai-studio/gemini-embedding-2` multimodal embedding models. Search and chat requests can include images through the REST API and public endpoint.
Refer to [Supported models](https://developers.cloudflare.com/ai-search/configuration/models/supported-models/) for the full list of embedding models.
#### OCR availability and increased file limits
Optical character recognition (OCR) is available on every account for scanned PDFs. Plain-text or code files and PDFs with OCR enabled can be up to 10 MiB. PDFs without OCR and other supported formats remain limited to 4 MiB.
Refer to [Data source](https://developers.cloudflare.com/ai-search/configuration/data-source/#file-limits) for file limits and [Limits & pricing](https://developers.cloudflare.com/ai-search/platform/limits-pricing/) for OCR pricing.
#### Source type inference
When you create an AI Search instance, the `type` field is optional. AI Search infers a website source from an HTTP or HTTPS URL, or an R2 source from an existing bucket name.
Refer to [Data source](https://developers.cloudflare.com/ai-search/configuration/data-source/) for details.