I've directly inspected calls for pro/Max plans and as of today they have 1hr cache expiries. This has definitely degraded to 5 min in the past but that's the behavior today.
If you're paying API rates, you can choose 5m or 1hr yourself (and pay different rates).
Keeping a 1hr cache warm could still be useful, sure, but outside that, I don't see much use of this today.
When using API keys the default is still 5 minutes. Setting 1 hour for the entire session is actually a lot more wasteful considering the 2x rate that it comes with
Yes, this wastes cycle. They dump your cache and deallocate the VMs so that others can use it. This will result in tokens wasted and downtime for others.
Can you expand on this? I can't imagine this is holding up an entire machine or materially impacting capacity. Isn't it common to have a tiered cache and to ultimately evict (or move to another tier) if there's an active inference request and no available capacity elsewhere?
Yes, however if a tool like this commoditizes a way to stay "higher" in the cache hierarchy to avoid getting dropped, then for the same total capacity, Anthropic have to become stricter about retention.
Earn is synonymous with profit, and this hurts their profits. Introducing latency can benefit much more people and actually make usage more efficient. Reducing latency can sieze up a functioning system.
Lately, I’ve been thinking about how this related to fractional banking. If you were to eliminate fractional banking introduced in the US by Hamilton, you would destroy a lot of current prosperity.
Exactly. I really wish people wouldn't use this. If this becomes popular, anthropic will just modify their cache policy to be much less fair. It's not like they have infinite cache.
There are a lot of workflows where cache is likely to be consumed exactly once (e.g. anything chat-like where a single thread is extended; if a prefix cache hit is found, and a set of new longer prefixes is inserted in the cache, it is unlikely that the original shorter prefix will be consumed in later turns). I could see allowing each session key a small number (1?) of 24-hour cache entries, where inserting a new cache entry (perhaps the maximum-length prefix, perhaps an API-tagged specified-length prefix) consumes that slot and either boots the rest of the items from cache, or demotes them to 5 minutes or something. Basically: workflow awareness, not uniform handling.
Make the cache TTL more adaptive. Have more tiers than just 5m and 1h. Long-running subagents become increasingly ubiquitous. There's no reason for Anthropic to not do a better job for this use case.
This is a good idea if it could manage it in an acceptable way.
For example, there might be something I intended to complete in one sitting, but took two sittings in the same day unexpectedly. Maybe it could just be a few cache delays per day or something, tagged in advance somehow.
I've directly inspected calls for pro/Max plans and as of today they have 1hr cache expiries. This has definitely degraded to 5 min in the past but that's the behavior today.
If you're paying API rates, you can choose 5m or 1hr yourself (and pay different rates).
Keeping a 1hr cache warm could still be useful, sure, but outside that, I don't see much use of this today.
When using API keys the default is still 5 minutes. Setting 1 hour for the entire session is actually a lot more wasteful considering the 2x rate that it comes with
Is the 5-minute expiration correct? I thought it was more like ~1 hour.
You can set the retention globally (whole session) to 1 hour which will actually make it more expensive. The default is 5 minutes.
*UPD:* actually it appears the default is authentication-dependent. API key gets 5 minutes, subscriptions - 1 hour.
Feels like will be shut down real quick
Yes, this wastes cycle. They dump your cache and deallocate the VMs so that others can use it. This will result in tokens wasted and downtime for others.
Can you expand on this? I can't imagine this is holding up an entire machine or materially impacting capacity. Isn't it common to have a tiered cache and to ultimately evict (or move to another tier) if there's an active inference request and no available capacity elsewhere?
Yes, however if a tool like this commoditizes a way to stay "higher" in the cache hierarchy to avoid getting dropped, then for the same total capacity, Anthropic have to become stricter about retention.
Why? Seems fine if people want to burn more cache reads.
Because it makes Anthropic earn less money
> Because it makes Anthropic burn more money
Fixed that for you.
"Earn"?
Cache duration is arbitrary. What it actually does (if used en masse) is decrease the amount of oversubscription their infra can handle..
Earn is synonymous with profit, and this hurts their profits. Introducing latency can benefit much more people and actually make usage more efficient. Reducing latency can sieze up a functioning system.
Lately, I’ve been thinking about how this related to fractional banking. If you were to eliminate fractional banking introduced in the US by Hamilton, you would destroy a lot of current prosperity.
How will this not lead to tragedy of the commons?
Exactly. I really wish people wouldn't use this. If this becomes popular, anthropic will just modify their cache policy to be much less fair. It's not like they have infinite cache.
Glad this exists. It will force anthropic to fix their flawed cache mechanism.
How should they fix it?
There are a lot of workflows where cache is likely to be consumed exactly once (e.g. anything chat-like where a single thread is extended; if a prefix cache hit is found, and a set of new longer prefixes is inserted in the cache, it is unlikely that the original shorter prefix will be consumed in later turns). I could see allowing each session key a small number (1?) of 24-hour cache entries, where inserting a new cache entry (perhaps the maximum-length prefix, perhaps an API-tagged specified-length prefix) consumes that slot and either boots the rest of the items from cache, or demotes them to 5 minutes or something. Basically: workflow awareness, not uniform handling.
Make the cache TTL more adaptive. Have more tiers than just 5m and 1h. Long-running subagents become increasingly ubiquitous. There's no reason for Anthropic to not do a better job for this use case.
Don't we pay for cache input though?
You can send and receive 1 byte and refresh the cache. Keeping the cache alive isn't free, but it's close.
The idea is this keeps it in cache so you don’t have to pay to re-input.
This is a good idea if it could manage it in an acceptable way.
For example, there might be something I intended to complete in one sitting, but took two sittings in the same day unexpectedly. Maybe it could just be a few cache delays per day or something, tagged in advance somehow.