A token budget caps how much a specific API token may spend, with daily, weekly, or monthly windows and a warning threshold. A hard limit blocks requests when reached; a soft limit only flags the token. Budgets stop a single runaway integration from spending the whole workspace balance.

Why it matters

A single runaway integration can drain a shared workspace balance. Budgets put a ceiling on one token without affecting the others.

How it works

Each token gets a spend limit with a daily, weekly, or monthly window and a warning threshold. A hard limit blocks requests at the cap; a soft limit only flags the token. Changing the period starts a new window immediately.

Example

Cap a development token at $50/month with a warning at 80% so experiments cannot touch production budget.

← Back to the full glossary

Put the platform behind the terms

Route, evaluate, and monitor every AI request from one OpenAI-compatible platform.

Start Free → Explore the Features