# Large language model (LLM)

> A large language model is a neural network trained on huge volumes of text to predict the next token, which lets it write, summarize, classify and answer questions.

- Page: https://methodcrew.com/glossary/large-language-model
- Last updated: 2026-10-28
- Publisher: [The Method Crew](https://methodcrew.com/)

## How it works

An LLM reads text as tokens, which are pieces of words (in English, 1,000 tokens is roughly 750 words, per [OpenAI's rule of thumb](https://developers.openai.com/api/docs/concepts)), and predicts the most likely next token, one at a time. Trained on huge volumes of text and code, then tuned to follow instructions, that single skill turns into drafting, extraction, classification, translation and multi-step reasoning. The instruction-tuning step, described by [Ouyang and colleagues (2022)](https://arxiv.org/abs/2203.02155), is what turns a text predictor into an assistant that does what a request asks.

The models most businesses use come from OpenAI (GPT), Anthropic (Claude) and Google (Gemini), reached through an API and billed per token. Open-weight models, such as Meta's Llama family or Mistral's models, can run on your own servers when data cannot leave your network.

A model only knows what was in its training data, up to a cutoff date, plus whatever you put in the [context window](https://methodcrew.com/glossary/context-window) for that request. It knows nothing about your company unless you give it that information.

## How businesses use it

An LLM is rarely useful on its own. It becomes useful as one part of a larger system:

- An automation that reads inbound email and extracts order details into your ERP
- A [RAG system](https://methodcrew.com/glossary/retrieval-augmented-generation) that answers questions from your policies
- An [agent](https://methodcrew.com/glossary/ai-agent) that calls tools to finish a task
- A voice line that books appointments

Choosing a model is a cost and quality trade. A small, cheap model often handles classification well. A larger model is worth the extra cost on long documents and judgment calls. On our builds, model usage is billed at cost, so you see the real per-token bill.

## Where it goes wrong

LLMs produce fluent text whether or not it is true; see [AI hallucination](https://methodcrew.com/glossary/ai-hallucination). They are unreliable at exact arithmetic without a calculator tool, and the same prompt can return different answers on different runs. Providers also retire model versions, so a prompt tuned for one model can behave differently after an upgrade. Pin model versions and rerun a fixed test set before every switch.

Where a rule or a lookup table gives the right answer every time, use that and skip the model. It is cheaper and it does not drift.

## Example (hypothetical)

Hypothetical: a 70-person distributor receives purchase orders as PDFs in 30 different layouts. An LLM extracts the customer, SKUs, quantities and ship date into a fixed JSON format, and a validation step checks every SKU against the product catalog before the order reaches the ERP.

## Related terms

- [Context window](https://methodcrew.com/glossary/context-window): A context window is the maximum amount of text, measured in tokens, that a language model can read and write in one request, counting instructions, documents and its reply.
- [AI hallucination](https://methodcrew.com/glossary/ai-hallucination): An AI hallucination is output from a language model that is fluent and confident but false, such as an invented citation, policy, figure or product detail.
- [Fine-tuning](https://methodcrew.com/glossary/fine-tuning): Fine-tuning is further training of an existing language model on your own examples, so it learns a specific format or task without long instructions every time.
- [Prompt engineering](https://methodcrew.com/glossary/prompt-engineering): Prompt engineering is writing and testing the instructions, examples and context given to a language model so it produces the output a task needs, consistently.
- [Retrieval-augmented generation (RAG)](https://methodcrew.com/glossary/retrieval-augmented-generation): Retrieval-augmented generation is a method where a system first searches your own documents for relevant passages, then gives them to a language model to answer from.

## Services where this matters

- [Corporate AI consulting](https://methodcrew.com/services/corporate-ai-consulting): Use cases ranked by return, the best 1 or 2 piloted on your data, then a costed roadmap. $12,000 to $40,000 per project.
- [AI workshops and team training](https://methodcrew.com/services/ai-workshops): Sessions where staff practice on their own emails, documents and spreadsheets. $3,000 to $12,000 per session.
- [Custom AI agents and copilots](https://methodcrew.com/services/custom-ai-agents): Agents that look things up in your CRM or helpdesk and take the next step, with approvals. $15,000 to $90,000 per project.

## Articles that use this term

- [What AI consulting costs in 2026: rates, packages and price drivers](https://methodcrew.com/insights/ai-consulting-cost)
- [AI readiness assessment: the checklist we use and how to score it](https://methodcrew.com/insights/ai-readiness-assessment-checklist)

Full glossary: https://methodcrew.com/glossary