A token is a fragment of a word: in French, about 0.75 of a word or four characters. The model splits your text into tokens and reads them (input), then produces others (output), and every token generated uses energy. So it is the volume of tokens processed, especially output tokens, rather than the number of queries, that determines energy use.
Read the source article: Which AI uses the least energy? ChatGPT vs Claude vs Gemini