The chat completion choices generated by the model. Always contains exactly one choice.
A token representing part of the assistant's response to the prompt.
The reason the chat completion ended. null
when streaming, otherwise "stop".
The index of the choice in the request. Always 0.
The time the chat completion was created, in Unix time.
A unique identifier for the chat completion.
The model used to generate the chat completion.
The object type, which is always chat_completion
.
Generated using TypeDoc
The response body for a single chunk generated by the Create Chat Completion request request with
stream
set totrue
.