AI glossary · Prompts and settings
Max tokens
Max tokens is a setting that caps how long an AI’s reply can be, measured in tokens. When the limit is reached, the answer stops, even mid-sentence.
Also called maximum output length, output token limit
In more detail
Developers use it to control cost and keep answers short. If replies are being cut off, the limit is probably too low.
It is separate from the context window, which covers the whole conversation, not just the reply.
Related terms
TokenA token is a small chunk of text, often a word or part of a word, that a language model reads and writes. Usage limits and prices are counted in tokens.Context windowThe context window is how much text an AI model can consider at once, including your messages, files and its own replies, measured in tokens.CompletionA completion is the text an AI model writes in response to a prompt. The term comes from models “completing” the text they are given.
Browse related tools
AI tools listed on BroUseAI in these categories.
