Skip to content

Knowledge index embedding spend is metered and ledgered

Embedding calls are now part of usage reporting. Each query embedding the search_index tool makes emits an llm.generation event, so it reaches the session and agent totals and is debited from budgets like chat generations. Usage is recorded even when a search matches nothing.

Knowledge index sync, which embeds every indexed chunk in the background, now writes its spend to the usage ledger against the organization. Sync spend is not debited from any user’s budget, because no session triggered it.

See Knowledge Index, Budgets, #3149 and #3163.