A concrete example
A short email uses very little. An 80-page PDF sent to an advanced model can add up to tens of thousands of tokens.
Why it matters
The token explains three things at once: cost, maximum length, and response speed.
You'll see it in the pricing tables of AI APIs, in context limits, and in usage counters.
Don't mix it up with
Context window: The context window is how much text a model can take into account in a single conversation or request.
TTFT: TTFT measures the time between sending your request and the first token showing up.
Common mistakes
- Confusing the number of words with the exact number of tokens.
- Forgetting that the output often costs more than the input.
- Running a loop over big documents with no limit.
Quick checklist
- First I check whether the word names a concept, a tool, a risk, or a metric.
- I tie it to a concrete case: A short email uses very little. An 80-page PDF sent to an advanced model can add up to tens of thousands of tokens.
- I keep the main trap in mind: Confusing the number of words with the exact number of tokens.
Quick questions
What is Token in AI?
A token is a small chunk of text the AI counts to measure what it reads, writes, and bills.
Where will I run into Token?
You'll see it in the pricing tables of AI APIs, in context limits, and in usage counters.
Which word should I read next?
Start with Context window, TTFT, TPS.