Tenant caps
If you have multiple tenants under your account on Embed Core, Embed Automate, or Embed Partner, each tenant gets a per-tenant cap on AI usage so no single tenant can drain your whole pool. Every new tenant starts with Hub-equivalent caps of 250,000 narration tokens and 150 AI image generation events per month, and you can change a tenant's cap through the Coassemble API.
Why per-tenant caps exist
Tenants under your account share your total monthly allowance for narration tokens and AI image generation events. The per-tenant cap stops any one tenant from consuming the whole pool. When a tenant reaches its cap, AI usage is blocked for that tenant only until you raise the cap or it resets at the start of the next calendar month. Your other tenants and your parent account keep working.
What the default caps are
Every new tenant starts with Hub-equivalent caps:
- 250,000 narration tokens per month
- 150 AI image generation events per month
These defaults apply even if your account-level AI allowance is set to unlimited.
How tenant caps interact with your account allowance
The two layers run independently:
- Account-level AI caps on Embed plans are soft. If your account goes over its overall allowance, generation keeps working and the overage is surfaced to your account manager as a commercial conversation.
- Tenant-level caps are hard. A tenant that hits its monthly cap is blocked from generating AI content until you raise the cap or the month rolls over.
Hitting one cap doesn't affect the other.
How to set or change a tenant's cap
You manage tenant caps through the Coassemble API. You can set a different numeric cap, or set a tenant's cap to "unlimited" so it draws freely from your account-level allowance. Only the parent account can change caps; tenants can't change their own. For the endpoint and request shape, see the developer documentation.
Seeing per-tenant usage
The Per-Tenant Usage Reporting API returns consumption broken down by tenant for any time window, so you can build your own dashboards or alerts on top of it. The endpoint shape is in the developer documentation.
Common questions
Do Identified Recipients and Anonymous Recipients have tenant-level caps?
No. Recipient counts are enforced at the account level only. Per-tenant caps apply to AI usage (narration tokens and image generation events).
What happens when a tenant reaches its cap?
AI generation pauses for that tenant while your other tenants keep working. It resumes at the start of the next calendar month, or as soon as you raise the cap.
Can I set caps for all my tenants in one call?
There's no bulk-set option, so you set each tenant's cap with its own API call.
This article is maintained in our help centre. View the original ↗