Skip to main content
Pricing for the Embedding & RAG section is broken down by feature. Search covers collection management, embedding, storage, and search events. Embedding covers document embedding and storage for use with RAG workflows.
Search pricing has three parts: embedding and persisting content when it is indexed for search, storage retention beyond 30 days, and search events when you query a collection.

​
Rates

​
How Billing Works

​
Embed and Persist

Content is billed once when it is indexed. A source is indexed when its content is first ingested for search; once indexed, the same source can be added to any number of collections at no additional cost. You are not billed for a source simply because it is part of a collection. Billing covers the input content characters and includes 30 days of retention. Storage after 30 days is billed at the extended retention rate only if extended retention is enabled.

​
Search Events

A search event is a single GET /v2/ai/collections/{slug}/documents request that includes a query parameter. Each ranked search counts as one billable event, regardless of the top_k value or the number of results returned. The first 10,000 searches per month are free.Requests without a query parameter (catalog listings) are free — they return documents sorted by date without ranking, and are not counted as search events.

​
Multi-Region Fan-Out

When a collection’s sources are stored across multiple regions, a search query fans out to all relevant regions in parallel. Each region retrieves its matching results independently, and the results are merged into a single ranked list by score. The user does not see or control which regions are searched — the fan-out and merge happen automatically.Despite querying multiple regions, the entire fan-out counts as one billable search event, not one per region. The multi-region behavior does not increase the cost of a search.Region selection is automatic — there is no region parameter on search requests.

​
Example

A collection with 10,000 characters of indexed content and one search within the free tier would be priced as: