NVIDIA Nemotron 3 Super 120B vs Llama 4 Scout 17B 16E Instruct
Llama 4 Scout 17B 16E Instruct is cheaper on output tokens, while NVIDIA Nemotron 3 Super 120B offers a larger context window. Choose NVIDIA Nemotron 3 Super 120B or Llama 4 Scout 17B 16E Instruct based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | NVIDIA Nemotron 3 Super 120B | Llama 4 Scout 17B 16E Instruct |
|---|---|---|
| Provider | Weights & Biases | Weights & Biases |
| Input / 1M tokens | $0.20 | $0.17 |
| Output / 1M tokens | $0.80 | $0.66 |
| Context window | 262K | 64K |
| Parameters | — | — |
| Open weights | Yes | Yes |
| Released | Mar 2026 | Jan 2025 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.