Model
Nemotron 3 Super
1 providers
$0.2
best input /M · Weights & Biases
$0.8
best output /M
262K
context window
262K
max output
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| Weights & Biases nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | $0.2 | $0.8 | $0.2 | — | 262K | reasoningtoolsstructuredno vision | Mar 11, 2026 |
Price badge
https://models.sutraworks.ai/badge/wandb/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.