What is an LLM?
An LLM (large language model) is an AI model trained on very large amounts of text to predict the next word, which lets it answer questions, summarise and write.
Also calledlarge language model
Why it matters for a business
Most AI features you might buy or build, from a support assistant to document search, run on an LLM.
More
GPT, Claude, Gemini and Llama are well-known families of LLMs.
The model you choose affects cost per request, speed, where data is processed and how well it handles your field. A good setup lets you switch models later without rebuilding the product.
How it works
It splits text into tokens and predicts the likely next token, one at a time, based on patterns learnt in training.
Inference
Inference means running the trained model to answer a request, usually paid per token through a provider’s API.
Not the law degree
At universities, LLM is a Master of Laws degree; in AI, it stands for large language model.
- InputA question, a message, a document
- ContextYour data, found by search
- LLMLanguage modelReads, reasons and writes
- ResultAn answer, or an action in your tools
What it costs
Starting prices of our services on this topic, in your currency.
LLM in practice
A large language model: an AI model trained on huge amounts of text to read and write language.
Example
- A recruitment agency in Leeds receives a large pile of CVs for each role.
- An LLM reads every CV against the job description, writes a short summary of each candidate and flags missing requirements.
- Recruiters still decide who to call, but they start from a shortlist instead of a pile.
Which term is it?
Software that uses a language model to plan the steps of a task and carry them out in your tools.

From the founder
I want AI that does a real job inside your tools, with a person checking what matters. We test it on your own data before you rely on it.
Anatoly MikhailovFounder of Pazl






