Hi all, Since API slowness is a consistent issue, I made some experiments to test the response times of GPT-3.5 and GPT-4, comparing both OpenAI and Azure. As a reminder, mostly the response time depends on the number of output tokens generated by the model. Here’s a summary of the results: [gp…

GPT-3.5 and GPT-4 API response time measurements - FYI

qrdl June 8, 2023, 1:28pm 5

Blockquote

Cheaper? How much cheaper? I thought they were the same price.

1 Like

Topic		Replies	Views
GPT 4 API is Very Slow Still API gpt-4 , chatgpt , api	15	6664	December 16, 2023
Gpt-4-0125-preview INCREDIBLY slower than 3.5 turbo API	12	9489	July 22, 2024
Gpt-4-0125-preview is slower than gpt-4-0613? Feedback gpt-4 , api	5	5521	January 30, 2024
Benchmarking response time for GPT4 by context+output tokens API gpt-4 , api-speed	6	6453	November 3, 2023
Gpt-4o tokens per second comparable to gpt-3.5-turbo. Data and analysis API gpt-4 , gpt-35-turbo , playground , gpt-4-turbo , gpt-4o	3	11023	August 16, 2024