Similar issue here. We track our tokens from each request internally. While we are no longer seeing cached tokens, we are also seeing an increase in token usage in our dashboard that is not correct. We’ve notified OpenAI support, but I recommend you log your own usage as well. We are being charged nearly double the price.
3 Likes
Similar issue here, started from ~18 Dec.
Also we monitor cache by analyzing the usage field in completion responses. Our current metrics show approximately 80% cache hit ratio, while it’s <1% in OpenAI dashboard.
Haven’t got any response from OpenAI support yet
3 Likes
Exactly same here.
What exact date the problem has started?
For me it was 17th … 19th… and remains the same till today (January 2nd)
2 Likes
They keep insisting that the problem is with our code. I created a program to list the consumption of all threads and all of them contain cached tokens (about 70% should be cached). and yet there are 0 cached tokens on the dashboard. I’ve had a reasonable increase in the cost of APIs since then and I believe I’m being extra charged for this.
2 Likes
And this is that same input with OpenAI (not as many times, since caching isn’t working). I have no idea why the tiny sliver of caching occurs.
2 Likes
At least you’re still getting the sliver - I don’t even see that anymore - pretty sure it’s a problem with my code! 
3 Likes
I know I was joking before, but today’s charges were triple what I’m used to – and what I planned on based on caching from a month ago. 
Is this program you wrote avail for others to use, I’d prefer not to reinvent the wheel to go back through and track everything.
1 Like
I have the same experience and was wondering where the small amount of caching comes from.
I then switched from cost view to activity view in the dashboard. Regarding token usage, it looks almost as if the labels have been switched (and consequently the costs).
2 Likes
2 Likes
I’m seeing the same. Wondering what will happen about the overages these past couple of months.
1 Like
Same for me. but they didn’t recalculated the past. lets wait
2 Likes
Support confirmed that the caching issue is fixed. They’re also looking into any potential overcharges, so past billing concerns might get resolved too.
2 Likes
Caching seems to work again for my application as well. 
I just checked the dashboard. I haven’t changed the code, but it seems that the token cache is being resumed 
Wondering where we are on this, in regards to being reimbursed for overcharges when caching was not functioning properly.
Also, when it comes to support, how are you reaching out? Just through the Intercom-bot, or something else? I used the Intercom-bot last week, but it doesn’t look like anyone has read it and I haven’t received an email.
