Nemotron 3 Super is 7.1× cheaper per million tokens (blended). Qwen3.8 27B has the larger context window (1,000,000 vs 262,144 tokens, 3.8×).
Nemotron 3 Super vs Qwen3.8 27B
Live catalog fields. Best-in-row is highlighted.
Nemotron 3 Superopen
NVIDIA · nvidia__nemotron-3-super-120b-a12b
Qwen3.8 27Bopen
Qwen · qwen__qwen3.8-27b
Identity
| Field | nvidia__nemotron-3-super-120b-a12b | qwen__qwen3.8-27b |
|---|---|---|
| Provider | NVIDIA | Qwen |
| Slug | nvidia__nemotron-3-super-120b-a12b | qwen__qwen3.8-27b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | Qwen/Qwen3.8-27B |
Quality
| Field | nvidia__nemotron-3-super-120b-a12b | qwen__qwen3.8-27b |
|---|---|---|
| Quality index (0–100) | — | 87.4 |
Cost
| Field | nvidia__nemotron-3-super-120b-a12b | qwen__qwen3.8-27b |
|---|---|---|
| Input $ / 1M tokens | $0.09 | $0.42 |
| Cached input $ / 1M | — | $0.09 |
| Output $ / 1M tokens | $0.40 | $3.00 |
Context
| Field | nvidia__nemotron-3-super-120b-a12b | qwen__qwen3.8-27b |
|---|---|---|
| Max context tokens | 262,144 | 1,000,000 |
| Max output tokens | 16,384 | 131,072 |
Modalities
| Field | nvidia__nemotron-3-super-120b-a12b | qwen__qwen3.8-27b |
|---|---|---|
| Input | text | text, image, video |
| Output | text | text |