Nemotron 3 Super
NVIDIA released 2026-03-11
DeepSeek V4 Flash 0731 is both better and cheaper.
It scores +26.1 higher and costs 36% less ($0.105/M against $0.164/M) on this workload — and it does everything this model does.
Solar Pro 4 is cheaper still (68% less) but drops 1.0M → 524K context.
The same model via free is 100% cheaper (free/M) — same weights, different latency.
Every price dimension
| Input | $0.085/M |
|---|---|
| Output | $0.400/M |
Independent scores
| Intelligence | 25.7 |
|---|---|
| Coding | 37.7 |
| Agentic | 8.8 |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Capability
| Context window | 1M |
|---|---|
| Max output | 16K |
| Input modes | text |
| Tool use | yes |
| Reasoning | optional |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...