Retrieve weekly AI allowance usage
How much of the plan’s weekly AI allowance the two in-product AI assistants have used: the
dashboard copilot (ask_ai) and the prompt generator (prompt_gen). The allowance is
measured in what the AI model calls cost, so a model that reasons more uses more of it; it is
reported as a PERCENTAGE of the allowance (limit is 100). Weeks run Monday 00:00 UTC to
the next Monday. weekStart and resetsAt give the boundaries.
Growth’s weekly allowance is five times Starter’s and Business’s twenty-five times.
Enterprise is unlimited (limit and remaining are -1, percent is null). With no
subscription limit and remaining are 0. When an allowance runs out, the assistant
itself answers 429 AI_WEEKLY_CAP_REACHED until resetsAt. This allowance is separate
from the AI replies your agents send to customers (see GET /api/billing/usage).
Consistency. Never cached (Cache-Control: no-store); used is percent rounded up
to a whole point and can pass 100 by the last request of the week.
Access
- Required scope:
read. Available to every workspace role. - Rate limit: Billing — 15 requests/min per workspace, shared by every
/api/billingroute. See Rate limits. - Plan: Available on every plan.
Authentication
Workspace API key: jl_ followed by 64 lowercase hex characters, created by the workspace owner in the
dashboard (Settings → API Keys) and sent as Authorization: Bearer jl_.... The plaintext is shown once,
at creation; Jelliu stores only a SHA-256 hash. A workspace can hold up to 25 active keys.
Operations restricted to admins or owners reject keys without the full scope with 403, and say so in
their description. No key, whatever its scope, can mint or revoke API keys or rotate a webhook secret —
that requires a signed-in owner session. A revoked key stops authenticating within about 10 seconds.
See Authentication.
Response headers
Always no-store.