How many chat choices or images to return.

Number between -2.0 and 2.0.

The language of the input audio.

Maximum number of tokens to generate in the reply.

ID of the model to use.

Set an organization where the user has access to multiple organizations.

Number between -2.0 and 2.0.

An optional text to guide the model's style or continue a previous audio segment.

The quality of the image that will be generated.

Format of the returned response, use "json_format" to enable JSON mode, which guarantees the message the model generates is valid JSON.

When set, system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

The size of the generated images.

The speed of the generated audio.

Custom text sequences that will cause the model to stop generating.

Stream the response, which will be returned as a series of message chunks.

The style of the generated images.

When set, system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result.

A list of tools the model may call.

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

An image.

Moderation represents the moderation of a text, including whether it is flagged.

Represents a transcription response returned by model, based on the provided input.

Callback when new stream data is received.

Opt is a function which can be used to set options on a request.