Pricing
Start free. Pay for usage, not seats.
Every plan includes the full product: trained agents, Knowledge OS, Slack and Teams, approvals, and audit. Plans differ in one thing — how much work your agents can do each month.
Plans
$0
One agent in one channel with limited monthly usage. Enough to train it on real context and see the work come back.
$20 /mo
Full product with standard monthly usage: agents, Knowledge OS sources, approvals, and audit. Bring your own model keys if you prefer.
$90 /mo
For teams whose agents answer all day. Five times the included usage of Starter, across multiple agents and channels.
$180 /mo
For companies running agents across departments. Twenty times the included usage of Starter, with room to keep growing.
Self-serve from day one: upgrade, downgrade, or cancel from your console. Need SSO/SCIM, a dedicated runtime, or invoice billing? Enterprise is available from your console.
What counts as usage.
Usage is the work your agents do: answers, drafts, summaries, and tool runs. Each plan includes a monthly amount — Pro plans include 5× or 20× the Starter amount. Prefer your own model keys? Bring them on any paid plan and provider spend stays on your invoice.
Questions buyers actually ask.
What counts as usage?
The work your agents do: answers, drafts, summaries, decision records, and tool runs. Reading and indexing your knowledge sources does not burn usage.
Can I bring my own model API keys?
Yes. Paid plans support BYOK routes for providers like Anthropic and OpenAI. Your provider spend stays on your own invoice and stays visible in the console.
What happens when I hit my included usage?
The console warns you at 80%. At the limit, agents pause until the next cycle or until you upgrade — nothing fails silently and nothing bills you by surprise.
How do I cancel or change plans?
From the billing page in your console, any time. Downgrades take effect at the next cycle.
Is my company data used to train models?
No. Your context is retrieved per-question, scoped by permissions, and sent only to the model providers you configure under your routing policy.