Use casesAI in your product
Know what each of your customers costs you in AI.
Send your user's id with each request. INFRO records usage and estimated provider cost per end customer, refuses a request over that customer's cap before the call, and exports the rows for your own billing system.
Example cap. INFRO measures; you bill your own users. INFRO never charges your end customers.
The problem
Without a control plane
- One heavy customer can use more AI than they pay you for.
- Pricing an AI feature is a guess, because cost per customer is unknown.
- A free tier has no ceiling a script cannot pass.
With INFRO
- Usage and estimated cost per end customer, by day or month.
- One cap for every end customer, with overrides per customer.
- A 402 with the reset time, for your app to show its user.
How it works
Name the end customer
Send your user's opaque id as metadata.user_id or the X-INFRO-User-Id header. Use an id, never an email address.
Cap each one
One cap per organization or project for every end customer, with overrides your backend sets through the management API.
Bill from the rows
Requests, tokens and estimated provider cost per end customer, project and model, as CSV or JSON, for the billing system you already use.
What you get
Each one is documented, and each says which plan includes it. Where no plan is named, it is on every plan.
End-customer capsFrom Team
One spend cap for every end customer, per organization or project, with overrides set through the management API.
DocsUsage per end customerFrom Team
Requests, tokens and estimated provider cost per customer, by day or month, as CSV or JSON.
DocsAttribution by feature
Add X-INFRO-Feature to see which part of your product each customer's cost comes from.
DocsUnit economics
Cost per run, per request, per feature and per customer, with the unpriced share beside every figure.
DocsCost as a share of revenueFrom Team
Record each customer's monthly revenue to see AI cost as a share of it, flagged past your threshold. Display only.
DocsYour own spend limits
Organization, project and key limits still apply, independently of the end-customer cap.
Docs
Who it is for
- FoundersPrice AI features on what each customer actually uses, and keep a free tier from becoming the biggest line on the bill.
- Product managersSee which customers and features drive AI cost before deciding plan limits.
- FinanceUsage rows per customer that load into the billing system you already run.
FAQ
Does INFRO bill my customers?
No. INFRO measures usage and estimated provider cost per end customer; you bill your own users from your billing system, at your own prices.
What does my app see when a customer hits their cap?
A 402 with type budget_exceeded and code end_user_budget, carrying the scope, the end customer's id, the period and resets_at, so your app can tell its user when they can continue.
Which plan includes this?
The per-customer cost view is on every plan. Caps and the usage export are included from the Team plan.
The full contract is in the End-customer caps docs, and every other question is on the FAQ.
Field guides
- Field guideAttributing AI cost to customers, features and teamsThe provider's finest unit of cost is an account structure you created for its convenience. The dimensions your business runs on — customer, feature, team — only exist where the request passes through something you control.
- Field guideShowback and chargeback for AI spendProvider invoices arrive per account, not per team. Showback and chargeback for AI spend depend on tagging every request at the source, booking it with rules finance can audit, handling shared costs openly, and closing each month so it never moves.
Get started
Try it on your own provider accounts.
Connect a provider, create a gateway key and change one base URL. Your providers keep billing you directly; 0% markup on model spend.