@truell20 Please help us understand how this new pro plan (rate limited, not request based) works with the new background agent functionality and the usage-based pricing option.
I am also concerned about re-enabling usage-based pricing without the visibility we had to requests over time in the dashboard. I had been happy to spend close to half the Ultra price monthly, but with the lack of clarity here, I’ve turned off my usage based pricing.
I used in the new charging mode in 4 claude4 requests that were billed at 0.75x in the original mode, then I switched back to the original billing mode and it showed me that I had consumed 15 requests…
lol im not laughing at you just how unacceptable the situation has been allowed to become that we’re creating meta documentation and things to work around implementation that is neither documented before production push nor useful to any human past “ah a rate limit is a rate limit”
Hey all, so our docs should not be updated to include a lot of the information you are asking for, but not everything may be fully updated in every page yet - the most relevant page can be found here:
If anyone has any questions, please post them below and I’ll try to get back to them!
I am on Pro-plan & enabled usage based pricing. For this month, I exhausted the 500 request limit & additionally used $15 so far - which means my net usage so far in this billing cycle is $20 + 15 = $35.
So based on new pricing, if I use only $15 worth requests per month, then will I be only charged $15 OR still $20 ?
Basically, earlier one was predictable. I know how much I am gonna charged. 1 sonnet-4 thinking request = $0.03. Now, with rate limit removed & other stuff, what is it gonna be ?
Also, if i disabled usage based pricing, how can I know how much of my monthly quota of 500 requests is consumed ?
You will always be charged your based plan amount of $20, regardless of how many requests you use. However, instead of giving you the set 500 requests a month, there is no longer a hard cap per month, but much like ChatGPT and Claude, we now enforce rate limits for how many requests you can do a set timeframe.
The only time you will ever need usage-based pricing is if you attempt to use more requests than you can with the rate limiting of your plan. In this case, usage-based pricing can be enabled to fill the gap between the $20 and $200 a month plan.
To summarise:
The new Pro plan allows for more included usage than the old one, spread in time across the month
If you hit your rate limits, you will be asked to switch models or enable usage-based pricing
The majority of users should not be hit with rate limits often
I had 2 subscriptions at 20$ to have 1000 credits, in this case can I keep two subscription to have twice the limit rate or will I then simply be decreased to 20$ ?
The rate limit account for two patterns of usage: “burst usage” where you use a ton of requests quite quickly, and also sustained usage, where you use requests throughout the space of a few hours for a whole day.
We believe the majority of users won’t see any right in normal usage, and those who do What he is more than their plan allows can still use usage based pricing to top up with extra requests.