gpt-oss-120b is 138.9× cheaper per million tokens (blended). Nova Premier 1.0 has the larger context window (1,000,000 vs 131,072 tokens, 7.6×). gpt-oss-120b is open-weights; the other is not.
Nova Premier 1.0 vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
Nova Premier 1.0
Amazon · amazon__nova-premier-v1
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | amazon__nova-premier-v1 | openai__gpt-oss-120b |
|---|---|---|
| Provider | Amazon | OpenAI |
| Slug | amazon__nova-premier-v1 | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | openai/gpt-oss-120b |
Quality
| Field | amazon__nova-premier-v1 | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | amazon__nova-premier-v1 | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $2.50 | $0.02 |
| Cached input $ / 1M | $0.63 | $0.02 |
| Output $ / 1M tokens | $12.50 | $0.09 |
Context
| Field | amazon__nova-premier-v1 | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 1,000,000 | 131,072 |
| Max output tokens | 32,000 | 65,536 |
Modalities
| Field | amazon__nova-premier-v1 | openai__gpt-oss-120b |
|---|---|---|
| Input | text, image | text |
| Output | text | text |