---
title: "LLM (Large Language Model): Definition and Examples"
description: "A large language model (LLM) is an AI model trained on very large amounts of text to predict the next token, which lets it process and generate language..."
path: /glossary/large-language-model
family: glossary
updated: 2026-10-17
html: /glossary/large-language-model
sources:
  - "https://www.ibm.com/think/topics/large-language-models"
  - "https://arxiv.org/abs/1706.03762"
  - "https://developers.google.com/machine-learning/resources/intro-llms"
facts:
  term: "LLM (large language model)"
  also_called: "large language model, LLM, LLMs, foundation model"
  category: "AI and Agents"
---

# LLM (large language model)

A large language model (LLM) is an AI model trained on very large amounts of text to predict the next token, which lets it process and generate language: answering questions, summarizing, translating, writing and following instructions.

## What Is LLM (Large Language Model)?

**In short:** LLMs are neural networks built on the transformer architecture, introduced in the 2017 paper Attention Is All You Need.

They learn from billions or trillions of words to estimate the probability of the next token, a word or part of a word. In English, a token is about 4 characters, so 400 tokens is roughly 300 words. Further tuning teaches them to follow instructions.

Every LLM has a context window, the maximum number of tokens it can work with at once, and a training cutoff after which it knows nothing unless you supply it. LLMs can also state wrong facts with confidence, often called hallucinations. That is why teams pair them with retrieval, tools and checks before output reaches a customer.

## LLM Example

For example, a team uses an LLM to sort 5,000 cold email replies a month into interested, objection, out of office and unsubscribe. On a check set of 200 replies labeled by a person, the model agrees on 188 (94%), so the team lets it label replies automatically and sends only low-confidence cases to a rep.

## LLM in Practice

In B2B sales, LLMs power email personalization, account research summaries, reply classification, call summaries and the agents that chain those steps. Choosing a model is a trade-off between quality, speed and cost per token. Many teams use a cheaper model for high-volume classification and a stronger one for writing.

## FAQ

### What does LLM stand for?

Large language model: a deep learning model trained on very large amounts of text that can process and generate language.

### How do LLMs work?

They split text into tokens, use the transformer's self-attention to weigh how tokens relate to each other, and predict the most likely next token, one at a time, to build an answer.

### What is a token in an LLM?

A unit of text the model reads and writes, such as a word or part of a word. Google's rule of thumb for English is about 4 characters per token, so 400 tokens is roughly 300 words.

### What are examples of large language models?

Well-known model families include OpenAI's GPT, Anthropic's Claude, Google's Gemini and Meta's Llama. GPT-3, released in 2020, had 175 billion parameters.

### What is the difference between an LLM and generative AI?

Generative AI is the broad category of models that create content, including images, audio and video. LLMs are the generative models that work with text.

## Do this in Ken

### Do This in Ken

Operate Ken from the model you already use: connect Claude, ChatGPT or another MCP client to the Ken MCP server.

- Link: [Do This in Ken](/mcp)

## Related

- [GTM Glossary](/glossary): Every GTM term, grouped by topic.
- [Prompt engineering](/glossary/prompt-engineering)
- [RAG (retrieval-augmented generation)](/glossary/retrieval-augmented-generation)
- [Agentic AI](/glossary/agentic-ai)
- [AI agent](/glossary/ai-agent)
- [BYOK (bring your own key)](/glossary/byok)
- [Ken MCP server](/mcp)

## Sources

| Source | URL | Checked |
| --- | --- | --- |
| IBM: What are large language models? | https://www.ibm.com/think/topics/large-language-models | 2026-10-17 |
| arXiv: Attention Is All You Need (2017) | https://arxiv.org/abs/1706.03762 | 2026-10-17 |
| Google for Developers: Introduction to large language models | https://developers.google.com/machine-learning/resources/intro-llms | 2026-10-17 |

## Changelog

- 2026-10-17: Page published.