How do I get the total token usage after a chat completion?

[MatteoMgr2008]

I'm using the openai Python SDK to call the chat completion API with GPT-3.5.

It works fine, but I’d like to see how many tokens are used for:

• the prompt
• the completion
• the total

Is there a way to get that info from the response?

Here's my code:

response = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    messages=[{"role": "user", "content": "Tell me a joke"}]
)

Thanks!

[Istituto-freudinttheprodev]

Yes, you can get detailed token usage directly from the response!

The openai.ChatCompletion.create() response includes a .usage object with:

• prompt_tokens
• completion_tokens
• total_tokens

Just do this:

response = openai.ChatCompletion.create(
    model="gpt-3.5-turbo",
    messages=[{"role": "user", "content": "Tell me a joke"}]
)

print(response.usage)

Output will look like:

{
  'prompt_tokens': 7,
  'completion_tokens': 12,
  'total_tokens': 19
}

This is super helpful for tracking costs or usage limits.

✅ Let me know if it helps, and feel free to mark as Answer!

[Istituto-freudinttheprodev]

Thank you so much!