The chat completion choices generated by the model. Always contains exactly one choice.
The reason the chat completion ended. Always "stop" for non-streamed completions.
The index of the choice in the request. Always 0.
The assistant's response to the prompt.
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
.
The usage incurred by the chat completion.
The number of tokens used for the completion.
The number of tokens used for the prompt.
The sum of the prompt and completion tokens.
Generated using TypeDoc
The response body for a Create Chat Completion request.
See
Chat Completion Response Body