Shows why the model's most likely tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → can violate a schema, and how structured outputForcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.Full definition → fixes it. You can try it locally in the browser with WebGPU, which helps when explaining structured output to a team.
Terms in this piece · Glossary
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
structured output — Forcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.
