Core Concepts
Token
Tokenization splits text into tokens—sub-word units that balance vocabulary size with linguistic coverage. GPT-4 uses roughly 1 token per 4 characters of English text, so 1,000 words ≈ 750 tokens.
Token counts determine API costs, context window usage, and generation speed. Concise, well-structured content is processed more efficiently and fits more meaning into limited context windows.
Authority Links
Related Terms
Model Components
Context Window
The maximum number of tokens a language model can process in a single inference pass — everything the model "sees" at once, including system prompt, conversation history, retrieved documents, and the response being generated.
Model Components
Large Language Model (LLM)
A transformer-based neural network with billions to trillions of parameters, trained on broad text corpora to predict the next token and able to generate, summarize, classify, and reason over natural language.