Dashboard usage vs Prompt response usage not matching

[Diet]

Welcome to the community!

Prompt caching seems to currently be borked, there’s a bunch of threads on this

4o input not being cached

[image] I just received this response.

Understanding Prompt caching

I am not sure how the prompt caching is working for my case: I am trying to understand how prompt caching is being applied to my case. For that I prompted the GPT-4o model with 4 different prompts. When I analyzed the chat completion object, I get the following values for the 4 completion objects: Prompt tokens: 13418, Cached tokens: 0 Prompt tokens: 12183, Cached tokens: 8192 Prompt tokens: 14614, Cached tokens: 8192 Prompt tokens: 15326, Cached tokens: 8192 Here “Prompt tokens” is the ob…

Cachedtoken not working recently while using chatCompletion api

CachedToken is not working recently (since Dec.20 2024) Is there anyone having similar problem or knowing how to solve this problem? [fyi] Prompt length is around 2000~2400 tokens Most of prompt is not changing Chaning part of prompt is after 1800 token length which means, first 0~1800 tokens are exactly same [image]

Stopped to use Cached Tokens

Stopped to use cached tokens. When i analyze the api response log, i see about 80% of cached tokens. What could be the problem? [Screenshot 2024-12-30 at 22.50.48]

OpenAI status (https://status.openai.com/) seems to think everything is working as normal, and I don’t see any OAI employee activity in these threads unless I’ve missed something.

Soo…

Sorry there’s not much anyone can do other than wait (or migrate to Azure) I guess