Concepts Fondamentaux
Token
The basic unit of text that language models process and are billed by.
A token is a chunk of text — roughly 4 characters or ¾ of a word in English. Language models split all input and output into tokens before processing. API pricing is expressed in cost per million tokens ($/1M), making token count the single most important factor in your AI infrastructure bill.
Termes Associés
Tokenizer
The algorithm that converts raw text into a sequence of tokens for a language model.
Input Price
The per-million-token cost charged for tokens in your prompt.
Output Price
The per-million-token cost charged for tokens the model generates.
Context Window
The maximum number of tokens a model can process in a single request.