At 96.9%, Prime Inference has the highest cache hit rate of any provider serving Nemotron 3.5 Super VL.
This brings the effective input cost to $0.024/M tokens, the lowest of any provider, and ~70% below the largest provider.
Prime Intellect's Prime Inference posts top cache hit rate for Nemotron 3.5 Super VL
AIPrime Inference reports a 96.9% cache hit rate, the highest of any provider serving Nemotron 3.5 Super VL. That brings its effective input cost to $0.024 per million tokens, the lowest of any provider and about 70% below the largest one.
Source details
Prime Intellect · x.comPublished
Original title: At 96.9%, Prime Inference has the highest cache hit rate of any provider serving Nemotron 3.5 Super VL.