Infrastructure
Max Tokens
A commonly used name for a token ceiling, usually limiting how much a model may generate in one response. The exact parameter and accounting depend on the API. OpenAI’s Responses API uses max_output_tokens, which can include reasoning, visible output and non-visible formatting tokens. It is a ceiling, not a requested word count or a guarantee of a complete answer.
Reviewed
Sources
Member lesson
The definition and sources are public. The complete practical lesson is for members.