Platform guide

💳 Costs, caps, and what uses credits

5 min read

Three separate meters, no overlaps:

Model usage

Bills to your own AI subscriptions (see AI tokens). We never mark it up. Every run shows its token usage in Runs.

Credits

Pay for research tools only: web searches, page scrapes, profile lookups, lead search with contact enrichment, local business and review pulls (Google, Trustpilot, Tripadvisor, App Store, Google Play), SEO data (keywords, backlinks, live rank checks, Google Trends), single-page site audits (including Google Lighthouse), and competitor ad lookups. 1,000 included monthly - a fresh allowance lands on the 1st (the free allowance doesn't accumulate month to month). Credits you PURCHASE are different: packs of 5,000 for $5 never expire and carry over until spent. Optional auto-recharge with a monthly cap you set. The per-tool menu lives in Billing → Credit cost per usage. Cache hits and failed calls cost zero. When an agent needs data fresher than the cache, scrape tools take a freshness setting that forces a live pull - that one costs normal credits, repeats stay free. Only the first 1,000 each month come with the plan - past that, credit packs are a separate purchase ($5 per 5,000). The agent email inbox is different again: a flat $10/month per inbox, never credits - pro-rated when you add it, removed from the subscription when you delete the inbox.

Email

A flat monthly add-on per agent inbox. Sends and receives never touch credits.

Where to watch it: Home shows the week’s credit usage at a glance; Billing breaks it down by tool, agent, and mission; each run’s detail itemizes its own spend. Nothing spends silently.

The caps that protect you: email daily send caps per inbox, the auto-recharge monthly maximum, and schedule timeouts. Each is a hard stop, not a warning.

💳 Cost note: Rough anchors from real playbooks: a weekly content-research run ≈ tens of credits; watching 4 competitors twice weekly ≈ a few dozen per week; email ≈ zero credits ever. If a month looks weird, Billing → usage-by-mission usually names the culprit in one glance.