Vector RAG · Pricing
Docs / Vector RAG

Pricing

Vector RAG is billed from credits — embeddings for documents you add and searches you run.

Vector RAG has no separate subscription. Usage is billed from your credits — the same balance used across Inference.

What you pay for

ActivityBilled as
Adding documentsEmbedding tokens for every chunk that is embedded
Running a searchEmbedding tokens to embed the question
Syncing a connected sourceEmbedding tokens for every chunk fetched and embedded

Storage of embedded documents is included; you are charged for the embedding work itself, priced per token at the same rates as inference. See Inference pricing for the per-model token rates.

Note
Top up and track your balance under credits. Each collection shows the tokens it has consumed so you can attribute cost.