Qwen3.5 397B A17B is cheaper than OpenAI o4-mini at $0.6/M vs $1.1/M input tokens.
| Spec | OpenAI o4-mini | Qwen3.5 397B A17B |
|---|---|---|
| Input price | $1.1/M tokens | $0.6/M tokens |
| Output price | $4.4/M tokens | $3.6/M tokens |
| Context window | — | 262K tokens |
| Parameters | Not disclosed | 397B (17B active) |
| Weights | Closed | Open |
| Free API (OpenRouter) | No | No |
| Released | Apr 2025 | Feb 2026 |
| SWE-bench Verified | 68.1% | 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.
Qwen3.5 397B A17B is cheaper on both: 1.8× input, 1.2× output.
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
Qwen3.5 397B A17B uses 690.3x more bold