gpt-oss-20b is 4.1× cheaper per million tokens (blended). Nemotron 3.5 Super VL has the larger context window (1,048,576 vs 131,072 tokens, 8.0×).
Nemotron 3.5 Super VL vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
Nemotron 3.5 Super VLopen
NVIDIA · nvidia__nemotron-3.5-super-vl
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | nvidia__nemotron-3.5-super-vl | openai__gpt-oss-20b |
|---|---|---|
| Provider | NVIDIA | OpenAI |
| Slug | nvidia__nemotron-3.5-super-vl | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | nvidia/NVIDIA-Nemotron-3.5-Super-VL | openai/gpt-oss-20b |
Quality
| Field | nvidia__nemotron-3.5-super-vl | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | nvidia__nemotron-3.5-super-vl | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.15 | $0.03 |
| Cached input $ / 1M | $0.02 | $0.03 |
| Output $ / 1M tokens | $0.50 | $0.13 |
Context
| Field | nvidia__nemotron-3.5-super-vl | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 1,048,576 | 131,072 |
| Max output tokens | 943,718 | 117,964 |
Modalities
| Field | nvidia__nemotron-3.5-super-vl | openai__gpt-oss-20b |
|---|---|---|
| Input | text, image, video | text |
| Output | text | text |