Cheapest way to deploy NVIDIA-Nemotron-3-Super-120B-A12B-BF16 in 2026

Rank	Provider	Pricing	Hardware	Monthly
#1	AWS	API	—	$825
#2	Azure	GPU · On-demand	RTX PRO 6000	$895
#3	Baseten	API	—	$990
#4	Nebius	GPU · On-demand	H100 SXM	$2.12k
#5	Nebius	GPU · On-demand	H200 SXM	$2.52k

View full results with your assumptions →

• What's the cheapest way to host NVIDIA-Nemotron-3-Super-120B-A12B-BF16?

  The cheapest API option for NVIDIA-Nemotron-3-Super-120B-A12B-BF16 in nfer's index is AWS at $0.150/1M input + $0.650/1M output tokens. For self-hosted workloads, the cheapest GPU rental that fits is Azure on RTX PRO 6000 at $1.24/hour. The right choice depends on your daily token volume — see the break-even chart on this page.
• How much VRAM does NVIDIA-Nemotron-3-Super-120B-A12B-BF16 need?

  NVIDIA-Nemotron-3-Super-120B-A12B-BF16 248 GB at native precision; roughly 124 GB at int8 and 62 GB at int4. Native precision is bf16. Quantization roughly halves (int8) or quarters (int4) the VRAM footprint at modest accuracy cost.
• Can I use NVIDIA-Nemotron-3-Super-120B-A12B-BF16 commercially?

  Released under other. Most permissive open-source licenses allow commercial use; confirm specific clauses with the publisher before deploying.
• What's the difference between API and GPU rental for NVIDIA-Nemotron-3-Super-120B-A12B-BF16?

  Token-priced API providers (like AWS) bill per million input/output tokens — best for low or bursty volume. Renting a GPU (e.g. Azure at $1.24/hour) is a flat ~$894.96/month regardless of usage — better economics once you sustain enough tokens per day to justify the fixed cost. The break-even chart on this page shows the exact crossover point.
• Is NVIDIA-Nemotron-3-Super-120B-A12B-BF16 available with EU data residency?

  NVIDIA-Nemotron-3-Super-120B-A12B-BF16 is not a European-developed model. 2 EU-owned providers offer hosting in nfer's index — filter on EU sovereignty in the comparator to see them.