Chat Completion Response Format

Parameters	Type	Description
id	string	Unique identifier for chat completion
choices	array	Chat completion options list. If n > 1, there can be multiple options
created	integer	Unix timestamp for when the chat completion was created (in seconds)
model	string	Model used for chat completion
system_fingerprint	string	Fingerprint representing the backend configuration of the running model
object	string	Object type, always `chat.completion`
usage	object	Usage statistics for the request
completion_tokens	integer	Number of tokens in the generated completion
prompt_tokens	integer	Number of tokens in the prompt
total_tokens	integer	Total number of tokens used (prompt + completion)

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-3.5-turbo-0613",
  "system_fingerprint": "fp_44709d6fcb",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "\n\nHello there, how may I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

Chat completed object

Chat Completion Response Format#

Chat Completion Response Format