GPT-4o mini

This setting affects the diversity of the model's responses. Lower values lead to more predictable and typical responses, while higher values encourage more diverse and uncommon responses. When set to 0, the model always gives the same response to a given input. View Documentation

This setting limits the model's selection to a certain proportion of the most likely words: only selecting those top words whose cumulative probability reaches P. Lower values make the model's responses more predictable, while the default setting allows the model to choose from the entire range of vocabulary. View Documentation

This setting aims to control the repetition of words based on their frequency in the input. It attempts to use less frequently used words that appear more in the input, with usage frequency proportional to appearance frequency. Word penalties increase with frequency. Negative values encourage word repetition. View Documentation

This setting adjusts the frequency of specific words that have already appeared in the input. Higher values reduce the likelihood of such repetitions, while negative values have the opposite effect. Word penalties do not increase with frequency. Negative values encourage word repetition. View Documentation

This setting defines the maximum length the model can generate in a single response. Higher values allow the model to generate longer responses, while lower values limit the length, making it more concise. Adjusting this value appropriately can help achieve the desired response length and detail based on different application scenarios. View Documentation

This setting controls the intensity of reasoning the model performs before generating an answer. Low intensity prioritizes response speed and saves tokens, while high intensity provides more complete reasoning but consumes more tokens and slows down response speed. The default value is medium, balancing reasoning accuracy and response speed. View Documentation