How Usage is Calculated

Adds: one unit per memory created

A single POST /memory/add costs one unit; when the extractor distils that text into more than one atomic fact, the request still costs one unit. A bulk add, file upload, import or connector sync is charged for every memory it stores — a document that becomes fifteen memories costs fifteen. A synchronous write that stores nothing (a deduplicated add, a skipped upload) still consumes the single unit taken when the request was accepted; an import or connector sync that creates nothing costs nothing.

Retrievals: one unit per request

A query, recall, compose, search or list is one unit however many memories it returns.

Checked before the work

The check and the first increment happen together, before your request runs, so two concurrent requests cannot both take the last unit. Memories a request fans out into are charged once they are stored.

External traffic only

Requests authenticated with an API key or OAuth token are billable. Dashboard sessions are exempt.

Over-limit requests

Do not increment the counter, so usage never exceeds the plan limit.

Both counters reset to zero when your billing cycle rolls over. The next cycle is anchored to the end of the previous one, so the reset date does not drift month to month. The dashboard shows the current period and the days remaining until the reset.