What is Token?
A token is the unit of text a language model reads and writes — roughly three-quarters of a word in English — and the unit you're billed and limited by.
Models don't process characters or words; they process tokens — chunks produced by a tokenizer. Common words are one token; rarer words, numbers, code and other languages split into several. As a rule of thumb, 1,000 tokens ≈ 750 English words.
Tokens matter for three things: the context window (how much fits), cost (APIs charge per token in and out), and speed (output is generated one token at a time). Asking for a shorter answer is the cheapest way to get a faster, cheaper one.
- Estimate: characters ÷ 4 ≈ tokens for English.
- Set a max length in the prompt ("under 150 words") rather than relying on defaults.
Use it right now
Ask our brain anything on the homepage — it remembers the whole conversation — or write a brief in the Studio and see the prompt it compiles to.