Text Completion Response Format

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

Parameters	Type	Description
id	string	Completed unique identifier
choices	array	The list of completion options generated by the model for input prompts
created	integer	Created Unix timestamp (seconds)
model	string	Model for completion
system_fingerprint	string	Fingerprint representing the backend configuration of the running model
object	string	Object type, always `text_completion`
usage	object	Usage statistics for completion requests
completion_tokens	integer	Number of tokens in generated completion
prompt_tokens	integer	Number of tokens in the prompt
total_tokens	integer	Total number of tokens used (prompt + completion)

{
  "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
  }
}

Complete object

Text Completion Response Format#

Text Completion Response Format