Optional
apiOptional
dimensionsOptional
frequencyThe frequency penalty of the model
Optional
inputthe maximum input tokens that the model should accept (Context window size)
Optional
maxThe maximum number of tokens to think
Optional
maxThe maximum number of tokens to generate
Optional
modelOptional
outputthe maximum output tokens that the model should generate
Optional
presenceThe presence penalty of the model
Optional
providerOptional
stopThe stop sequences of the model
Optional
temperatureThe temperature of the model
Optional
topThe top K of the model
Optional
topThe top P of the model
The dimensions parameter for text embeddings models