LLM Opex

Changes

DeepInfra cut nvidia/NVIDIA-Nemotron-3.5-Super-VL (1M cached in) (batch): $0.064 → $0.016/1M cached in (-75%)

DeepInfra · recorded 20 October 2026

Before: $0.064 . Now: $0.016 (-75%).

This price over the stored collections

DeepInfra prices · October 2026 report