What a run costs, and where to see it
Every model call is metered: tokens in, tokens out and cost. See them per run, per day and per agent under Usage.
Updated 1 min read
A run’s cost is its model calls. Each call goes through our AI gateway on your account’s own key, which records its model, tokens and cost.
- On a run: its model calls, tokens in and out, and cost.
- Usage: model cost, tokens in, tokens out and model calls for the period, a chart of Model cost per day, and a table per agent.
- The record: each model call as an entry, with its tokens and cost.
Billing
Plans, allowances and invoices arrive with billing. Until then nothing is charged.