Where is the total_seconds on GPT 4o API?

API Feedback
1

I couldn’t find any metric analog to elapsed.total_seconds() from the legacy API, such as in

rawResponse: LegacyAPIResponse = client.chat.completions.with_raw_response.create(
    messages=[...],
    functions=myFunctionSpec,
)
responseSeconds: float = rawResponse.elapsed.total_seconds()

New code using Structured Outputs following example from the docs:

completion: ParsedChatCompletion[ResumeSearchQuery] = client.beta.chat.completions.parse(
    model='gpt-4o-mini-2024-07-18',
    messages=[...],
    response_format=MySpec
)
resp: MySpec | None = completion.choices[0].message.parsed
1 Like