Token usage calculation with streaming responses - is this not supported?

API Feedback
1

Hi, I need to track token usage for cost calculation purposes. and show it to users on the frontend. When using streaming mode, I don’t see token usage information in the response chunks. Is there a way to:

  1. Get token counts during or after a streaming response completes?
  2. Calculate costs for streaming requests without having to estimate tokens beforehand?

I’ve checked the API documentation but couldn’t find clear guidance on this. Any insights?

2

It is usually in the last part of the stream.

Are you using Completions or Responses API?

If you use Completions API you need this parameter: include_usage

response = client.chat.completions.create(
    model='gpt-4.1-mini',
    messages=[
        {'role': 'user', 'content': 'Count to 100, with a comma between each number and no newlines. E.g., 1, 2, 3, ...'}
    ],
    temperature=0,
    stream=True,
    stream_options={"include_usage": True}, # retrieving token usage for stream response
)
  • There is also a cookbook teaching how to get usage with completions streams here.

If you are using Responses API you just need to take a look at the response.completed event:


stream = client.responses.create(
    model="gpt-4.1-mini",
    input=[
        {
            "role": "user",
            "content": "How many s's are in the word 'mississippi'? Give me other words with the same amount of s's.",
        },
    ],
    stream=True,
)

for event in stream:
    print(event.type,event)
    if event.type=='response.completed':
       print(f"usage: {event.response.usage}")
       print(event.response.output_text)
       print(event.response.usage)

More info here:
https://platform.openai.com/docs/guides/streaming-responses?api-mode=responses