← All features
AI Controls & Guardrails

Per-org cost guardrails

Live

Daily and monthly cost ceilings per organisation. Soft warnings, hard cutoffs.

What you get
  • Daily + monthly cost ceilings per org
  • Soft warnings at 80%
  • Hard cap or overage mode
  • Per-feature, per-user, per-document usage dashboard
+1 more capabilities below
Overview

What it is.

Set a daily and monthly LLM cost ceiling per organisation. Soft warnings fire at 80% utilisation; hard cutoffs kick in at 100% (configurable to soft-cap-only if you'd rather pay overage than hit a wall).

Per-organisation usage dashboard with breakdown by feature, user, and document type.

How it works

Three steps.
End to end.

01
1. Set the ceilings

Admin → Usage. Set daily + monthly caps. Defaults are conservative.

02
2. Watch the warnings

Slack / email / in-app warning at 80% utilisation.

03
3. Hard cap (optional)

At 100%, hard cap stops new AI runs until ceiling resets or you raise it.

Capabilities

What you get.

  • Daily + monthly cost ceilings per org
  • Soft warnings at 80%
  • Hard cap or overage mode
  • Per-feature, per-user, per-document usage dashboard
  • Slack / email warning channels
FAQ

Quick answers.

Can I cap per workspace too?

Enterprise plans support per-workspace caps in addition to org-level. Other plans cap at the org level.

Related

More in AI Controls & Guardrails.

No model training on your data
Live

We do not train models on customer content without explicit opt-in. Default is off.

Prompt injection defence
Live

User-pasted text is sanitised before reaching the LLM.

Prompt caching
Live

Stable prompt prefixes are cached. Faster responses, lower bill, passed to you.

Token cap per request
Live

200K input / 8K output limits with graceful truncation and a clear notice.

Want to try Per-org cost guardrails?
Get started in 60 seconds.

Sign up →All features