Built-in storage
Every new AI Search instance comes with built-in storage and a built-in vector index, powered by R2 and Vectorize. You can upload files directly to an instance without setting up either service yourself.
Instances created after April 16, 2026 include built-in storage. You can upload files directly using the Items API or the dashboard.
Instances created before this date do not include built-in storage and do not support the Items API. You can see which of your instances have built-in storage on the dashboard under AI > AI Search. Select your instance and check the Overview tab to see if it includes built-in storage.
Go to AI SearchAll instances will be migrated to managed infrastructure. Migration details are coming soon.
Upload files to an instance using the Items API (Workers binding or REST API) or the Items tab in the dashboard (AI > AI Search > your instance > Items). You can also list, view, and delete uploaded files through the Items API or the dashboard.
For supported file types, refer to Supported file types.
Files uploaded to built-in storage are indexed immediately. External data sources like websites and R2 buckets are indexed on a sync schedule.
An instance can use built-in storage alongside an external data source. The available external data sources are:
- Website: crawl and index a website that you own
- R2 Bucket: index documents stored in a Cloudflare R2 bucket
For example, an instance can be backed by a website for shared documentation while also accepting file uploads through the Items API for additional content.
For instances with built-in storage, R2 storage, Vectorize, and Browser Run are included. Workers AI and AI Gateway usage is billed separately. For full details, refer to Limits and pricing.