Token

The unit of text processed by an LLM — roughly 4 characters or 0.75 words in English.

Tokens are the atomic units of large language model processing. Pricing, context windows and throughput are all measured in tokens. English averages ~0.75 words per token; code averages ~0.5 words per token due to syntax density.

Related terms

Context window

The maximum number of tokens a model can process in a single request.

Input tokens

Tokens consumed by the prompt, system message and retrieved context fed into the model.

Output tokens

Tokens generated by the model in response — typically 3–5x more expensive than input tokens.