AI Search is now generally available

Summary

Cloudflare’s AI Search, a managed pipeline combining Workers AI, Vectorize, R2, and Browser Run, is now generally available after a year of preview. The update adds native image embeddings via the Qwen3-VL-Embedding model with Matryoshka Representation Learning, enabling visual search by texture and composition alongside caption-based text search. AI Search now supports files up to 10 MiB and optical character recognition for scanned PDFs; queries undergo optional rewriting, parallel vector and keyword search, fusion, and optional reranking. Previously reliant on caption generation only, image retrieval now embeds query images directly using multimodal models, while text-only models convert images to text via ToMarkdown. Billing starts November 1, 2026, with a free monthly allotment of 5 million ingestion tokens, 10 GB storage, 1,000 semantic queries, and 1,000 full-text queries, with no capacity units or monthly minimums.

Takeaways

1. 1

   AI Search now supports native image embeddings via the Qwen3-VL-Embedding model with Matryoshka Representation Learning, preserving visual attributes (texture, composition, spatial relationships) alongside text captions for more expressive search.

2. 2

   Optical character recognition is available for scanned PDFs, extracting text before chunking and embedding; file size limit increased from 4 MiB to 10 MiB.

3. 3

   Pricing is based on ingestion tokens (uniform across embedding models), storage ( 2.00/GB-month), and query type ( 0.75/1k semantic, $0.10/1k full-text), with a free tier of 5M tokens, 10 GB storage, and 1,000 each of semantic and full-text queries per month.

FAQ