gpt-oss-20b is 2.8× cheaper per million tokens (blended). Nemotron 3 Nano 30B A3B has the larger context window (262,144 vs 131,072 tokens, 2.0×).
Nemotron 3 Nano 30B A3B vs gpt-oss-20b
Live catalog fields. Best-in-row is highlighted.
Nemotron 3 Nano 30B A3Bopen
NVIDIA · nvidia__nemotron-3-nano-30b-a3b
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Identity
| Field | nvidia__nemotron-3-nano-30b-a3b | openai__gpt-oss-20b |
|---|---|---|
| Provider | NVIDIA | OpenAI |
| Slug | nvidia__nemotron-3-nano-30b-a3b | openai__gpt-oss-20b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | openai/gpt-oss-20b |
Quality
| Field | nvidia__nemotron-3-nano-30b-a3b | openai__gpt-oss-20b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | nvidia__nemotron-3-nano-30b-a3b | openai__gpt-oss-20b |
|---|---|---|
| Input $ / 1M tokens | $0.06 | $0.02 |
| Cached input $ / 1M | $0.01 | $0.01 |
| Output $ / 1M tokens | $0.24 | $0.09 |
Context
| Field | nvidia__nemotron-3-nano-30b-a3b | openai__gpt-oss-20b |
|---|---|---|
| Max context tokens | 262,144 | 131,072 |
| Max output tokens | 235,929 | 32,768 |
Modalities
| Field | nvidia__nemotron-3-nano-30b-a3b | openai__gpt-oss-20b |
|---|---|---|
| Input | text | text |
| Output | text | text |