What it means
Models process and bill text as tokens; a rough rule is ~¾ of a word per token in English, but code and symbols can consume more.
Why designers should care
Design for limits: character counters, summarization steps, file chunking, and honest messaging when context is trimmed, not mysterious cut-off replies.
Example
A research copilot shows “Using 12 of 40 pages from your upload” and offers to focus on selected sections before running analysis, preventing silent truncation.
Common mistakes
- Unlimited paste areas with no feedback until the model errors.
- Equating “characters” with model capacity in user-facing help text.
- Ignoring token cost in agent loops that chain many automatic steps.
Frequently asked questions
What is Token?
A token is a small chunk of text (often a word fragment) that models use to read and write language. Input and output size, cost, and speed are measured in tokens.
Why should designers care about Token?
Design for limits: character counters, summarization steps, file chunking, and honest messaging when context is trimmed, not mysterious cut-off replies.
What are common mistakes with Token?
Unlimited paste areas with no feedback until the model errors; Equating “characters” with model capacity in user-facing help text; Ignoring token cost in agent loops that chain many automatic steps.