DeepSeek V3.2 Exp is cheaper than Qwen3.5 397B A17B at $0.2/M vs $0.6/M input tokens.
| Spec | DeepSeek V3.2 Exp | Qwen3.5 397B A17B |
|---|---|---|
| Input price | $0.2/M tokens | $0.6/M tokens |
| Output price | $0.4/M tokens | $3.6/M tokens |
| Context window | 164K tokens | 262K tokens |
| Released | Sep 2025 | Feb 2026 |
| SWE-bench Verified | 67.8% | 76.4% |
Not enough votes to call it. On the specs, Qwen3.5 397B A17B has the edge: bigger model tier, newer, bigger context window.
DeepSeek V3.2 Exp costs 9.0x less per token.
DeepSeek V3.2 Exp is cheaper on both — 3.0× input, 9.0× output
Qwen3.5 397B A17B uses 14.8x more emoji
DeepSeek V3.2 Exp is cheaper than Qwen3.5 397B A17B at $0.2/M vs $0.6/M input tokens.
| Spec | DeepSeek V3.2 Exp | Qwen3.5 397B A17B |
|---|---|---|
| Input price | $0.2/M tokens | $0.6/M tokens |
| Output price | $0.4/M tokens | $3.6/M tokens |
| Context window | 164K tokens | 262K tokens |
| Released | Sep 2025 | Feb 2026 |
| SWE-bench Verified | 67.8% | 76.4% |
Not enough votes to call it. On the specs, Qwen3.5 397B A17B has the edge: bigger model tier, newer, bigger context window.
DeepSeek V3.2 Exp costs 9.0x less per token.
DeepSeek V3.2 Exp is cheaper on both — 3.0× input, 9.0× output
Qwen3.5 397B A17B uses 14.8x more emoji