Optional frequencyfrequencyPenalty represents a value between -2.0 and 2.0 to penalize tokens based on frequency.
Optional inputinputExtension represents a set of optional pre-processing integrations.
Optional logitlogitBias modifies the likelihood of specified tokens appearing in a response.
Optional maxmaxTokens represents the max number of tokens to return.
model represents the model to use.
onMessage represents a function that will receive the messages.
Optional presencepresencePenalty represents a value between -2.0 and 2.0 to penalize tokens based on presence.
prompt represents the prompt to process.
Optional stopstop represents one or more sequences where the API will stop generating tokens.
Optional temperaturetemperature represents the randomness in GPT's output.
Optional topKtopK represents the variability of the generated text.
Optional topPtopP represents the diversity of the generated text.
CompletionSSEInput represents the full potential input options for streaming completion.