Note: no pagination actually occurs yet, this is for forwards-compatibility.

Note: no pagination actually occurs yet, this is for forwards-compatibility.

The request counts for different statuses within the batch.

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

Log probability information for the choice.

Represents a streamed chunk of a chat completion response returned by model, based on the provided input.

A chat completion delta generated by streamed model responses.

Log probability information for the choice.

An object specifying the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models newer than gpt-3.5-turbo-1106.

Specifying a particular function via {"name": "my_function"} forces the model to call that function.

A chat completion message generated by the model.

The function that the model called.

Specifies a tool the model should use. Use to force the model to call a specific function.

Options for streaming response. Only set this when you set stream: true.

Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint).

Usage statistics for the completion request.

The usage information for the request.

Represents an embedding vector returned by embedding endpoint.

The File object represents a document that has been uploaded to OpenAI.

Represents the url or the content of an image generated by the OpenAI API.

Describes an OpenAI model offering that can be used with the API.

A list of the categories, and whether they are flagged or not.

A list of the categories along with their scores as predicted by model.

Represents if a given text input is potentially harmful.

The role of the author of a message

Controls which (if any) tool is called by the model. none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool.

The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format.