Pricing & billing
What does $19.99 a month include?
Everything. Twenty hours of active work a month with the AI on us, every employee role — Front Desk, Outreach, Content, Bookkeeper and the rest of the roster — and the Bot download, so you can run the whole thing on your own machine: on the same twenty hours, one pool with our cloud, or on your own AI key, which leaves the hours untouched. There is no tier above it and nothing held back below it.
Do I need my own API key?
No — not for the employees, and not for the Bot download. The phone line, the sending and the AI they think with are ours to run and ours to pay for; there is nothing to paste. On your own machine the Bot thinks on the same included hours, one pool with our cloud. Your own key is optional: bring one, a local model or a coding subscription, and the Bot thinks on that instead, without touching the hours.
What happens when the twenty hours run out?
Work pauses unless you have bought more. Hours are metered by active work — the time the team spends thinking and doing, not the clock while it waits. More hours are $0.69 each at every pack size (10, 50 or 100), and a switch in Billing decides whether work continues onto hours you bought or waits for you.
Can I cancel anytime?
Yes. Cancellation is one click in the Stripe Customer Portal from your dashboard. You keep access for the remainder of the billing month. No prorated refunds, but no lock-in either.
Can I try it before I pay?
No free trial. The console on the home page runs real tasks free, with no account; the plan is $19.99/mo and you can cancel anytime.
On your own machine
Which AI can the Bot download use?
On the plan, the AI that comes with it: the setup wizard offers your included hours first — one pool with our cloud, nothing to paste. Or any of the major providers, an aggregator that puts them all behind one key, or a model running locally on your own machine at nothing per thought. If you bring a key, one is enough, and the aggregator is what we recommend to start with. The setup wizard makes one real call with the key before it saves it. The list of providers, and which key to get, is on the BYOK page: /docs/byok.
How much does the Bot cost to run on my keys?
It depends on the model you point it at. Our own Bot runs busy all day on a low-cost model for about $5 a day. A top-tier model as the brain came in at $6 to $11 an hour in our burn tests; a cheap tier alone runs at pennies an hour. The Bot keeps a ledger of what it spent, by day, on its own dashboard.
Can I cap spend?
Yes. On the plan, the hours are the cap, and the hard-cap switch in Billing stops work when they run out. On your own machine the Bot's config carries a cost control that stops the heartbeat at the daily amount you set, and every call it makes lands in its ledger.
Enterprise & integration
What about enterprise / on-prem?
Email hello@ai158z.com. We'll work out a fit — on-prem deploys, custom integrations, SLA, dedicated support, air-gapped install options.
Can I integrate this into my product?
Yes — the hosted platform exposes a REST API at api.repryntt.com: Bearer token auth, every role on the bench available via /v1/agents/run, all workbenches scriptable. See /docs/api for the surface. For embedding the engine itself in your product, email us — licensing options are being reworked at the moment.
Do you support webhooks / inbound tasks?
Yes — /v1/inbox is the universal inbound channel. Any external system POSTs a task; the worker picks it up, runs the agent, and delivers results via callback URL or polling. Native Slack adapter included; webhooks for Zapier / n8n / etc. work out of the box.
Still have questions? hello@ai158z.com — direct reply, usually within a business day.