What is Token?
The basic unit of text that AI models process — roughly a word fragment — that determines both input length limits and output billing.
Full Definition
Tokens are the atomic units that language models read and write. A tokenizer splits raw text into tokens before feeding it to the model; common tokenization schemes (like BPE — Byte Pair Encoding) produce tokens that are roughly 3-4 characters on average in English, meaning one word is often 1-2 tokens. A model's context window is measured in tokens: GPT-4o supports 128k tokens, while some models support up to 1 million. Pricing for API access is denominated in tokens (e.g., per million input or output tokens). Understanding tokens is important for managing costs, staying within context limits, and interpreting rate-limit messages.
Tools that use Token
ChatGPT
The most widely used AI assistant with 900M+ weekly users
Claude
Best-in-class reasoning with 1M token context window
Gemini
NewGoogle's AI assistant with deep Workspace integration and 1M token context
GitHub Copilot
AI coding assistant with 4.7M+ paying subscribers