← All features
AI Controls & Guardrails

Cost transparency

Live

Per-request token + cost log. Export to CSV for chargeback.

What you get
  • Per-request logging — tokens, cost, latency, model
  • Filter by user, workspace, feature, document
  • CSV export
  • Webhook export to external usage systems (enterprise)
Overview

What it is.

Every LLM call is logged with input tokens, output tokens, cached tokens, model used, latency, and cost. Admins can filter the log by user, workspace, feature, or document.

CSV export means you can roll these up into your own chargeback or budgeting systems.

How it works

Three steps.
End to end.

01
1. Action happens

Any LLM call is logged automatically.

02
2. Admin sees the log

Admin → Usage. Filter by date, user, workspace, feature, model.

03
3. Export

CSV export for chargeback, budget reconciliation, or external dashboards.

Capabilities

What you get.

  • Per-request logging — tokens, cost, latency, model
  • Filter by user, workspace, feature, document
  • CSV export
  • Webhook export to external usage systems (enterprise)
FAQ

Quick answers.

Is there a usage API?

Yes — the Intelligence API has a /usage endpoint that returns the same data programmatically.

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.

Per-org cost guardrails
Live

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

Prompt caching
Live

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

Want to try Cost transparency?
Get started in 60 seconds.

Sign up →All features