Tokens
The pieces of text models read and write, and the unit you pay for.
A token is roughly a word piece; languages other than English often need more tokens for the same text. Input and output are priced separately, output usually several times higher. Reasoning a model does before answering is billed as output.
Related terms
- Context window: The maximum number of tokens the model can read and write in one request.
- Prompt caching: Reusing an identical prompt prefix across requests so it is cheaper and faster to process.
- Cost cap: A hard spending limit enforced by your code, per user, per day or per month.
