Announcement
Prime Inference's claimed cost advantage for Nemotron 3.5 Super VL
PrimeIntellect says Prime Inference's 96.9% cache hit rate brings effective input costs to $0.024 per million tokens.
TLDR
PrimeIntellect says Prime Inference has the highest cache hit rate among providers serving Nemotron 3.5 Super VL. It says that puts the effective input cost about 70% below the largest provider's. A post quoting the claim notes that the listed price is the same, but the effective price is lowest.
Combined views
—
2 Sources, first seen ago
