Concept最大输出token
max_output_tokens
An API request parameter that sets the maximum number of output tokens allowed for a single call. Setting it too low may result in an empty answer being returned while billing proceeds as usual. Exceeding the synchronous limit requires enabling long decoding.
Timeline (last 90 days)
Oct 17
The OpenAI Responses API triggers a response.incomplete event when a response ends early (such as hitting the max_output_tokens limit), and that event also carries response.usage; listening only for response.completed will miss the usage of truncated answers.
Unverified50%