gptty
gptty copied to clipboard
[debug] Include analytics and usage statistics for the given API key
Provide users with insights into their API usage, response patterns, and other metrics to help them optimize their interactions with ChatGPT.
We can define a callable using the logic below to display current API usage stats for the present day within the chat runtime.
import datetime
r = openai.api_requestor.APIRequestor()
resp = r.request("GET", f'/usage?date={datetime.datetime.now().strftime("%Y-%m-%d")}')
resp_object = resp[0]
resp_object.data # this object has all the info
requests_today = resp['data'][0]['n_requests'] # num requests
query_tokens_today = resp['data'][0]['n_context_tokens_total'] # query tokens
response_tokens_today = resp['data'][0]['n_generated_tokens_total'] # response tokens
https://github.com/openai/openai-cookbook/blob/main/examples/How_to_handle_rate_limits.ipynb