gpt-oss-120b is 25.0× cheaper per million tokens (blended). Nemotron 3 Super has the larger context window (1,048,576 vs 131,072 tokens, 8.0×).
Nemotron 3 Super vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
Nemotron 3 Superopen
NVIDIA · nvidia__nemotron-3-super-120b-a12b
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | nvidia__nemotron-3-super-120b-a12b | openai__gpt-oss-120b |
|---|---|---|
| Provider | NVIDIA | OpenAI |
| Slug | nvidia__nemotron-3-super-120b-a12b | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | openai/gpt-oss-120b |
Quality
| Field | nvidia__nemotron-3-super-120b-a12b | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | nvidia__nemotron-3-super-120b-a12b | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $0.30 | $0.02 |
| Cached input $ / 1M | $0.15 | $0.02 |
| Output $ / 1M tokens | $2.40 | $0.09 |
Context
| Field | nvidia__nemotron-3-super-120b-a12b | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 1,048,576 | 131,072 |
| Max output tokens | 262,144 | 65,536 |
Modalities
| Field | nvidia__nemotron-3-super-120b-a12b | openai__gpt-oss-120b |
|---|---|---|
| Input | text | text |
| Output | text | text |