A model trained on huge text corpora that predicts the next token to produce human-like language.
2 min readupdated 2026-06-22
/ quick answer
A Large Language Model is a neural network — usually a Transformer — trained to predict the next token given a context. Modern LLMs (GPT, Claude, Gemini, Llama) can reason, write code, follow instructions and call tools when wrapped in the right runtime.
A model trained on huge text corpora that predicts the next token to produce human-like language. A Large Language Model is a neural network — usually a Transformer — trained to predict the next token given a context. Modern LLMs (GPT, Claude, Gemini, Llama) can reason, write code, follow instructions and call tools when wrapped in the right runtime. In practice: You send a prompt like 'summarize this contract in 5 bullets'. The LLM tokenizes the input, runs it through billions of parameters and streams tokens back until a stop condition. This dictionary node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Definition
A Large Language Model is a neural network — usually a Transformer — trained to predict the next token given a context. Modern LLMs (GPT, Claude, Gemini, Llama) can reason, write code, follow instructions and call tools when wrapped in the right runtime.
Example
You send a prompt like 'summarize this contract in 5 bullets'. The LLM tokenizes the input, runs it through billions of parameters and streams tokens back until a stop condition.
A Large Language Model is a neural network — usually a Transformer — trained to predict the next token given a context. Modern LLMs (GPT, Claude, Gemini, Llama) can reason, write code, follow instructions and call tools when wrapped in the right runtime.
What is an example of LLM (Large Language Model)?
You send a prompt like 'summarize this contract in 5 bullets'. The LLM tokenizes the input, runs it through billions of parameters and streams tokens back until a stop condition.
Why does LLM (Large Language Model) matter for AI and automation?
A model trained on huge text corpora that predicts the next token to produce human-like language. It connects to the workflows, prompts and tool stacks linked on this page, so you can move from definition to execution without leaving Onexial.