# AI inference: what it is and how it works · Zorraquino
> Inference is the use of a trained model to produce an output from an input. It can generate a prediction, a classification or content.
URL: https://www.zorraquino.com/en/dictionary/ai-inference

# AI inference

Inference is the use of a trained model to produce an output from an input

What it means, how it is used and where it comes up, with its related concepts.

[The whole glossary](https://www.zorraquino.com/en/dictionary)

## What it is and how it works

It can generate a prediction, a classification or content. In an application, its design affects latency, cost and serving capacity. The result should be interpreted according to the task and the model's evaluation, without mistaking it for certainty.

Topics

[Artificial intelligence](https://www.zorraquino.com/en/dictionary/category/inteligencia-artificial)

## Related concepts

- [AI model evaluation](https://www.zorraquino.com/en/dictionary/ai-model-evaluation)
- [Foundation model](https://www.zorraquino.com/en/dictionary/foundation-model)
- [Multimodal model](https://www.zorraquino.com/en/dictionary/multimodal-model)