riva-translate-4b-instruct-v1_1 vs Nemotron 3 Super
riva-translate-4b-instruct-v1_1 is cheaper on output tokens, while Nemotron 3 Super offers a larger context window. Choose riva-translate-4b-instruct-v1_1 or Nemotron 3 Super based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | riva-translate-4b-instruct-v1_1 | Nemotron 3 Super |
|---|---|---|
| Provider | Nvidia | Nvidia |
| Input / 1M tokens | $0.00 | $0.20 |
| Output / 1M tokens | $0.00 | $0.80 |
| Context window | 128K | 262K |
| Parameters | — | 120B |
| Open weights | Yes | Yes |
| Released | Dec 2025 | Mar 2026 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.