Complete the object

Represents a completion response object from the API. Note: Streaming response and non-streaming response objects have the same structure (different from chat endpoints).

id	string	Unique identifier of completion
choices	array	A list of completion options generated by the model for input prompts
created	integer	Unix timestamp of creation completion (seconds)
model	string	Model for completion
system_fingerprint	string	This fingerprint represents the backend configuration of the model run
object	string	Object type, always "text_completion"
usage	object	Fulfillment of requested usage statistics
completion_tokens	integer	Number of tags in completions generated
prompt_tokens	integer	Number of tags in prompt
total_tokens	integer	Total number of tags used in request (hint + complete)

{
  "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7",
  "object": "text_completion",
  "created": 1589478378,
  "model": "gpt-3.5-turbo",
  "choices": [
    {
      "text": "\n\nThis is indeed a test",
      "index": 0,
      "logprobs": null,
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 7,
    "total_tokens": 12
  }
}