AI glossary

LLM

Summary

An LLM (Large Language Model) is a model trained on huge amounts of text that predicts and generates language, the brain behind ChatGPT, Claude or Gemini.

Updated

What it is

An LLM learns language patterns from a very large amount of text and, given an input, predicts the most likely continuation. That is where answers, summaries, code and translations come from.

Why it matters to an agency

The LLM is the engine behind your prompts and agents. Choosing the right model (by capability, speed and cost) affects the quality and the budget of your automations.

Example

When you paste a prompt into ChatGPT or Claude, the LLM is the one that reasons and produces the answer.

FAQ

Frequently asked questions

Are all LLMs the same?+

No. They vary in capability, speed, context size and price. It pays to test which one performs best for your task.