Nvidia Nemotron 3.5 Super VL 120 B A12 B vs Step 3.7 Flash: cost comparison
Prices updated 2026-11-05 · computed from live provider data
Short answer: Nvidia Nemotron 3.5 Super VL 120 B A12 B is cheaper on a
3:1 input/output blend — $0.275 per million tokens versus
$0.438, a 37% difference.
Nvidia Nemotron 3.5 Super VL 120 B A12 B offers the larger context window at 1,048,576 tokens, against 262,144 for Step 3.7 Flash.
Head to head
| Nvidia Nemotron 3.5 Super VL 120 B A12 B | Step 3.7 Flash | |
|---|---|---|
| Input, per 1M tokens | $0.200 | $0.200 |
| Output, per 1M tokens | $0.500 | $1.15 |
| Blended 3:1, per 1M | $0.275 | $0.438 |
| Context window | 1,048,576 | 262,144 |
| Vendor | baseten | empiriolabs |
Monthly cost at real volumes
| Workload (input / output) | Nvidia Nemotron 3.5 Super VL 120 B A12 B | Step 3.7 Flash |
|---|---|---|
| 1M in / 250K out | $0.325 | $0.487 |
| 10M in / 2.5M out | $3.25 | $4.88 |
| 100M in / 25M out | $32.50 | $48.75 |
Which should you pick?
Pick Nvidia Nemotron 3.5 Super VL 120 B A12 B when you need the longer context window (1,048,576 vs 262,144 tokens). Pick Nvidia Nemotron 3.5 Super VL 120 B A12 B when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.