# Budget Forcing

> Budget forcing controls how long a reasoning model thinks at inference time, by forcibly ending its reasoning when a token budget is reached or by appending a word such as "Wait" when it tries to stop early, which makes it keep reasoning.

- Identifier: PTL-0157
- Category: Reasoning Models & Test-Time Compute
- Canonical URL: https://protologue.com/t/budget-forcing/
- Also known as: s1, wait token, thinking budget control
- Introduced: 2025

## Description

It was introduced with s1, a model fine-tuned on only about a thousand reasoning examples, where extending thinking with budget forcing improved accuracy on competition math. It is a simple way to trade compute for accuracy, though the gains flatten beyond a point.

## Broader terms

- [Test-Time Compute Scaling](https://protologue.com/t/test-time-compute-scaling/)

## Related terms

- [Reasoning Model](https://protologue.com/t/reasoning-model/)
- [Extended Thinking](https://protologue.com/t/extended-thinking/)
- [Overthinking](https://protologue.com/t/overthinking/)

## Sources

- Muennighoff et al. (2025). s1: Simple test-time scaling. https://arxiv.org/abs/2501.19393

## Cite this entry

Protologue. (2026). Budget Forcing. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0157). https://protologue.com/t/budget-forcing/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)