AI Cost Management
Budgets, alerts and hard limits for every team, router, person and model.
Budgets by organization, router or tag
Total, per-router and per-model caps, each with its own alert and block rules.
Per-team, per-person and per-model caps
Policies apply the same budget to every team or person they match.
Soft and hard limits
Soft limits alert by email or webhook. Hard limits block with HTTP 429 until the period resets.
HTTP/1.1 429 Too Many Requests
Retry-After: 259200
{
"error": {
"message": "budget bdg_7Hq2Lm4NwQ is exhausted for this period; it resets at 2026-11-01T00:00:00Z",
"type": "budget_exhausted",
"code": "budget_exhausted"
}
} Budget overrides and approvals
People request more in the portal. Approvers raise the limit for the rest of the period.
Emailed when an employee asks for a higher limit in the Portal.
Exact pricing with your negotiated rates
Each request is priced at the exact rate that served it, or at your negotiated rate.
Set your negotiated rates once. Every request is priced at them, so budgets, caps, alerts, Traffic and Detailed usage count what you actually pay.
Cost per customer and feature
Tag routers and requests, and see spend by customer, feature and workflow run.
Start controlling AI spend
Create a budget, set its caps and see spend against it on every request.