Chapter 09 · Sustainability & AISustainability & AI

Inference

Meaning statusEstablishedSource recordDirect document linkedWhy these are different

Definition

Using a trained model to produce outputs for new inputs — each query, prediction or generation — as distinct from the training phase.

References

FAccT 2024 / arXivLuccioni et al. — Power Hungry Processing: Watts Driving the Cost of AI Deployment

This source provides part of the technical or institutional basis for the definition.

arXivLuccioni et al. — Estimating the Carbon Footprint of BLOOM

This source supports the explanation of how the term is applied, measured or governed in practice.

IEAEnergy and AI — energy demand from AI (2025)

This source supports the wider sustainability significance and context described in the entry.

Overview

What it means

Individually cheap, inference aggregates: a model serving millions of users consumes energy with every request. Research such as 'Power Hungry Processing' shows inference can dominate a popular model's lifetime footprint, shifting attention from one-off training costs to continuous operating costs.

How it is used

Inference is the phase sustainability teams encounter as users: every automated classification, summary or forecast has a marginal energy cost. Efficient architectures, smaller models and batching reduce it; so does simply not using a large model where a small one suffices.

Why it matters

As AI embeds into daily operations, inference turns its environmental cost into a running metre. Accounting regimes and procurement criteria increasingly need to cover deployment, not just development.

Have evidence, context, or a correction to share? Every suggestion is considered by an editor before publication.

Meaning status
Established
Verification date
Not recorded
Last updated
21 Aug 2026
What the classifications mean

Meaning status: Established

EstablishedCurrentMultiple definitionsContestedEmergingIndexed