Specifically, I’m making a simple call to OpenAI using Python asking about where a baseball game was played.

completion = openai.chat.completions.create(
  model="gpt-3.5-turbo",
  messages = [
  {"role": "system", "content": "You are a helpful assistant."},
  {"role": "user", "content": "Who won the world series in 2020?"},
  {"role": "assistant", "content": "The Los Angeles Dodgers won the World Series in 2020."},
  {"role": "user", "content": "Where was it played?"}
  ]
)

print (completion)

The output shows up like this:

ChatCompletion(id='chatcmpl-9UgP85B0gYBjEAiYMcF3Ryt9Y3fdZ', choices=[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(content='The 2020 World Series was played at Globe Life Field in Arlington, Texas.', role='assistant', function_call=None, tool_calls=None))], created=1717099870, model='gpt-3.5-turbo-0125', object='chat.completion', system_fingerprint=None, usage=CompletionUsage(completion_tokens=17, prompt_tokens=53, total_tokens=70))

But I’d like it to show up like this:

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "The 2020 World Series was played in Texas at Globe Life Field in Arlington.",
        "role": "assistant"
      },
      "logprobs": null
    }
  ],
  "created": 1677664795,
  "id": "chatcmpl-7QyqpwdfhqwajicIEznoc6Q47XAyW",
  "model": "gpt-3.5-turbo-0613",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 17,
    "prompt_tokens": 57,
    "total_tokens": 74
  }
}

FWIW, I’m using Python 3.12 and Windows Terminal.