Nemotron 3 Super 120 B A12 B vs Minimax M2 Her: cost comparison
Prices updated 2026-10-31 · computed from live provider data
Short answer: Minimax M2 Her is cheaper on a
3:1 input/output blend — $0.525 per million tokens versus
$0.825, a 36% difference.
Nemotron 3 Super 120 B A12 B offers the larger context window at 1,048,576 tokens, against 65,536 for Minimax M2 Her.
Head to head
| Nemotron 3 Super 120 B A12 B | Minimax M2 Her | |
|---|---|---|
| Input, per 1M tokens | $0.300 | $0.300 |
| Output, per 1M tokens | $2.40 | $1.20 |
| Blended 3:1, per 1M | $0.825 | $0.525 |
| Context window | 1,048,576 | 65,536 |
| Vendor | nvidia | minimax |
Monthly cost at real volumes
| Workload (input / output) | Nemotron 3 Super 120 B A12 B | Minimax M2 Her |
|---|---|---|
| 1M in / 250K out | $0.900 | $0.600 |
| 10M in / 2.5M out | $9.00 | $6.00 |
| 100M in / 25M out | $90.00 | $60.00 |
Which should you pick?
Pick Nemotron 3 Super 120 B A12 B when you need the longer context window (1,048,576 vs 65,536 tokens). Pick Minimax M2 Her when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.