Gemma 4 31B is 8.0× cheaper per million tokens (blended). Qwen3.8 27B leads quality index by 11.0 points (87.4 vs 76.4). Qwen3.8 27B has the larger context window (1,000,000 vs 262,144 tokens, 3.8×).
Gemma 4 31B vs Qwen3.8 27B
Live catalog fields. Best-in-row is highlighted.
Gemma 4 31Bopen
Google · google__gemma-4-31b-it
Qwen3.8 27Bopen
Qwen · qwen__qwen3.8-27b
Identity
| Field | google__gemma-4-31b-it | qwen__qwen3.8-27b |
|---|---|---|
| Provider | Qwen | |
| Slug | google__gemma-4-31b-it | qwen__qwen3.8-27b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | google/gemma-4-31B-it | Qwen/Qwen3.8-27B |
Quality
| Field | google__gemma-4-31b-it | qwen__qwen3.8-27b |
|---|---|---|
| Quality index (0–100) | 76.4 | 87.4 |
Cost
| Field | google__gemma-4-31b-it | qwen__qwen3.8-27b |
|---|---|---|
| Input $ / 1M tokens | $0.09 | $0.42 |
| Cached input $ / 1M | $0.05 | $0.09 |
| Output $ / 1M tokens | $0.34 | $3.00 |
Context
| Field | google__gemma-4-31b-it | qwen__qwen3.8-27b |
|---|---|---|
| Max context tokens | 262,144 | 1,000,000 |
| Max output tokens | 16,384 | 131,072 |
Modalities
| Field | google__gemma-4-31b-it | qwen__qwen3.8-27b |
|---|---|---|
| Input | image, text, video | text, image, video |
| Output | text | text |