Qwen3.8 27B is 1.2× cheaper per million tokens (blended). Qwen3.8 27B has the larger context window (1,000,000 vs 300,000 tokens, 3.3×). Qwen3.8 27B is open-weights; the other is not.
Nova Pro 1.0 vs Qwen3.8 27B
Live catalog fields. Best-in-row is highlighted.
Nova Pro 1.0
Amazon · amazon__nova-pro-v1
Qwen3.8 27Bopen
Qwen · qwen__qwen3.8-27b
Identity
| Field | amazon__nova-pro-v1 | qwen__qwen3.8-27b |
|---|---|---|
| Provider | Amazon | Qwen |
| Slug | amazon__nova-pro-v1 | qwen__qwen3.8-27b |
| Status | live | live |
| Open weights | No | Yes |
| License | — | — |
| HuggingFace | — | Qwen/Qwen3.8-27B |
Quality
| Field | amazon__nova-pro-v1 | qwen__qwen3.8-27b |
|---|---|---|
| Quality index (0–100) | — | 89.0 |
Cost
| Field | amazon__nova-pro-v1 | qwen__qwen3.8-27b |
|---|---|---|
| Input $ / 1M tokens | $0.80 | $0.42 |
| Cached input $ / 1M | — | $0.09 |
| Output $ / 1M tokens | $3.20 | $3.00 |
Context
| Field | amazon__nova-pro-v1 | qwen__qwen3.8-27b |
|---|---|---|
| Max context tokens | 300,000 | 1,000,000 |
| Max output tokens | 5,120 | 131,072 |
Modalities
| Field | amazon__nova-pro-v1 | qwen__qwen3.8-27b |
|---|---|---|
| Input | text, image | text, image, video |
| Output | text | text |