Qwen3.5 397B A17B is cheaper than Claude 3.7 Thinking Sonnet at $0.6/M vs $6/M input tokens.
| Spec | Claude 3.7 Thinking Sonnet | Qwen3.5 397B A17B |
|---|---|---|
| Input price | $6/M tokens | $0.6/M tokens |
| Output price | $30/M tokens | $3.6/M tokens |
| Context window | 200K tokens | 262K tokens |
| Released | Feb 2025 | Feb 2026 |
| GPQA Diamond | 84.8% | 88.4% |
Not enough votes to call it. On the specs, Qwen3.5 397B A17B has the edge: bigger model tier, newer.
Qwen3.5 397B A17B costs 8.3x less per token.
Qwen3.5 397B A17B is cheaper on both — 10× input, 8.3× output
Qwen3.5 397B A17B uses 22.8x more emoji
Qwen3.5 397B A17B is cheaper than Claude 3.7 Thinking Sonnet at $0.6/M vs $6/M input tokens.
| Spec | Claude 3.7 Thinking Sonnet | Qwen3.5 397B A17B |
|---|---|---|
| Input price | $6/M tokens | $0.6/M tokens |
| Output price | $30/M tokens | $3.6/M tokens |
| Context window | 200K tokens | 262K tokens |
| Released | Feb 2025 | Feb 2026 |
| GPQA Diamond | 84.8% | 88.4% |
Not enough votes to call it. On the specs, Qwen3.5 397B A17B has the edge: bigger model tier, newer.
Qwen3.5 397B A17B costs 8.3x less per token.
Qwen3.5 397B A17B is cheaper on both — 10× input, 8.3× output
Qwen3.5 397B A17B uses 22.8x more emoji