Gemma 4 31B is cheaper than Qwen3 30B A3B Instruct 2507 at $0.14/M vs $0.2/M input tokens.
| Spec | Gemma 4 31B | Qwen3 30B A3B Instruct 2507 |
|---|---|---|
| Input price | $0.14/M tokens | $0.2/M tokens |
| Output price | $0.4/M tokens | $0.8/M tokens |
| Context window | 262K tokens | 131K tokens |
| Released | Apr 2026 | Jul 2025 |
Not enough votes to call it. On the specs, Gemma 4 31B has the edge: bigger model tier, newer, bigger context window, major provider backing.
Gemma 4 31B is cheaper on both — 1.4× input, 2.0× output
Qwen3 30B A3B Instruct 2507 uses 4.4x more emoji
Gemma 4 31B is cheaper than Qwen3 30B A3B Instruct 2507 at $0.14/M vs $0.2/M input tokens.
| Spec | Gemma 4 31B | Qwen3 30B A3B Instruct 2507 |
|---|---|---|
| Input price | $0.14/M tokens | $0.2/M tokens |
| Output price | $0.4/M tokens | $0.8/M tokens |
| Context window | 262K tokens | 131K tokens |
| Released | Apr 2026 | Jul 2025 |
Not enough votes to call it. On the specs, Gemma 4 31B has the edge: bigger model tier, newer, bigger context window, major provider backing.
Gemma 4 31B is cheaper on both — 1.4× input, 2.0× output
Qwen3 30B A3B Instruct 2507 uses 4.4x more emoji