This is by design, its the same reason inference providers on Openrouter will advertise super cheap pricing but cache TTLs of 2 min/ 70% hit rate.
Cache rules everything around me.
Cache rules everything around me.
$100 on DeepSeek has lasted over a week, whereas on OpenRouter it lasted two days
That eventually grew into what is now my 'software factory' and I've realized, eventually, it's still C.R.E.A.M. (I named it flower) but it's _context_ rules everything around me.