New research shows AI model usage costs vary by language, with token consumption differing by as much as 17 times.
Even among the top 20 most widely spoken languages online, token consumption varies significantly—ranging from 1.5 to 5 times higher at the high end. When expanding the scope to 200 languages, the gap widens further. In one AI model, token usage for different languages can differ by as much as 17 times.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open the original article on ITHome