Small Talk, Big Impact: The Energy Cost of Thanking AI

TL;DR

This paper investigates the energy costs associated with polite interactions with large language models, revealing how factors like message length and model size influence energy consumption, and offering insights for more sustainable AI use.

Contribution

It provides a detailed quantification of the energy impact of polite language in LLM interactions, using real-world data and fine-grained measurements.

Findings

Longer inputs and outputs increase energy use

Model size correlates with higher energy consumption

Politeness adds measurable energy costs

Abstract

Being polite is free - or is it? In this paper, we quantify the energy cost of seemingly innocuous messages such as ``thank you'' when interacting with large language models, often used by users to convey politeness. Using real-world conversation traces and fine-grained energy measurements, we quantify how input length, output length and model size affect energy use. While politeness is our motivating example, it also serves as a controlled and reproducible proxy for measuring the energy footprint of a typical LLM interaction. Our findings provide actionable insights for building more sustainable and efficient LLM applications, especially in increasingly widespread real-world contexts like chat. As user adoption grows and billions of prompts are processed daily, understanding and mitigating this cost becomes crucial - not just for efficiency, but for sustainable AI deployment.