AI & Technical
Token
The basic unit of text that AI language models process and are priced by.
A token is roughly equivalent to three to four characters or about three-quarters of a word in English. LLMs process text as a sequence of tokens rather than characters or words. Token count matters for two reasons: it determines the cost of each API call (most LLMs charge per input and output token), and it determines whether a conversation fits within the model's context window. For businesses running high-volume chat agents, token efficiency directly impacts infrastructure cost.