Token
A token is the unit of text a language model reads and writes: a whole word, part of a word, a number or a punctuation mark. In English, one token averages about three-quarters of a word. AI providers measure context windows, speed and usage-based prices in tokens.
Example
The sentence "Do you ship to Canada?" is about six tokens; a 1,000-word help article is roughly 1,300 tokens.
Why it matters for a website chatbot
Every chatbot reply costs tokens: the question, the retrieved content and the answer. Vendors pass that cost on as credits, per-resolution fees or message limits. ChatBento plans count AI replies instead of tokens, so the price doesn't change with how long an answer is.
See it in practice: Docs and help-center search
Related terms
- Context windowA context window is the maximum amount of text, measured in tokens, that a language model can take into account at once. It covers the instructions, the conversation so far, any retrieved documents and the reply being written. Anything outside the window is invisible to the model when it generates its answer.
- Large language model (LLM)A large language model (LLM) is an AI model trained on very large amounts of text to predict and generate language. It can answer questions, summarize, translate and write. Its general knowledge comes from training data with a cutoff date, so it needs supplied documents to answer accurately about a specific business.
- Per-resolution pricingPer-resolution pricing is a billing model in which an AI support vendor charges a fee for each conversation its AI resolves, rather than a flat monthly price or a charge per message. What counts as a resolution varies by vendor, so the same traffic can cost very different amounts.