Language model (AI model, LLM)

Definition

Language models, or large language models (LLM), sit behind programs such as ChatGPT or Claude. They receive a text, such as a question and a document, and write an answer from it. Most run in their provider’s cloud (The cloud means computers in a provider’s data centres on which programs run and data is kept, instead of on your own device.); some can also run on your own hardware.

A language model can be wrong. That is why, in everything we build, a person decides before a message goes outside your firm or money is spent.

What it means for you

The AI harness (An AI harness is the workspace on your computer in which AI reads files and carries out agreed steps.), model and provider remain your choice. Using a model costs, depending on the plan, a fee per person and month or a charge for what you use, and it is not included in the setup price.

Where the term comes up

• Where your data is processed
• FAQ: Must we use Claude Code or a particular provider?

More terms

• Model usageModel usage means accessing an AI provider’s language model. The cost is not included in the setup price.
• AI providerAn AI provider runs language models and sells access to them, for example OpenAI (ChatGPT), Anthropic (Claude) or Google (Gemini).
• TokenFor language models, a token is a piece of text, such as part of a word, by which usage is measured; for logins, a token is a digital key.
• PromptA prompt is the input to a language model: the question, instruction or template the AI responds to.

All terms