At least in the self-hosted LLM inference engines, you have to pre-allocate space for the maximum amount of context you want to allow for each parallel session. By using a lower maximum, you don't have to allocate as much VRAM for each session, allowing more usage for the same amount of hardware. Thus, cheaper.
At least in the self-hosted LLM inference engines, you have to pre-allocate space for the maximum amount of context you want to allow for each parallel session. By using a lower maximum, you don't have to allocate as much VRAM for each session, allowing more usage for the same amount of hardware. Thus, cheaper.
Uses less quota (i.e., cheaper). For people who like to keep their contexts small, this is a no-brainer.
> k3 (1M) consumes about twice as much quota as k3-256k
Cheaper?
k3-256 consumes half the quota, so... yes? (assuming the user isn't making use of the larger context window)