← Back to glossary Glossary

Token Budget

Reviewed 19 July 2026 Canonical definition Part of: AI Agent Cost & Token Terms →

A token budget is a hard or soft limit on the number of tokens an AI agent can consume in a single task, session, or time period. Hard budgets terminate execution when the limit is reached; soft budgets trigger alerts or require reauthorisation. Token budgets are a practical tool for controlling both cost and the scope of what an agent is permitted to do.

§01 / QUESTIONSterm: Token Budget
Questions

Common questions.

What is Token Budget?

A token budget is a hard or soft limit on the number of tokens an AI agent can consume in a single task, session, or time period.

How does Token Budget work?

Hard budgets terminate execution when the limit is reached; soft budgets trigger alerts or require reauthorisation. Token budgets are a practical tool for controlling both cost and the scope of what an agent is permitted to do.

Which terms are related to Token Budget?

Closely related concepts include Agent Budget, Agent Spend Controls, Inference Cost, Agent Quota. Each is defined in the Prefactor glossary.

§02 / RELATEDnext: where this fits
Keep reading

Where this fits.

See how every agent performs, and make it better

Prefactor helps teams observe, evaluate, and improve their AI agents in production, across every framework and provider.