DeepSeek V3.2 Speciale is cheaper than Qwen3.5 122B A10B at $0.28/M vs $0.4/M input tokens.
| Spec | DeepSeek V3.2 Speciale | Qwen3.5 122B A10B |
|---|---|---|
| Input price | $0.28/M tokens | $0.4/M tokens |
| Output price | $0.42/M tokens | $3.2/M tokens |
| Context window | 131K tokens | 262K tokens |
| Weights | Open | Open |
| Free API (OpenRouter) | No | No |
| Released | Dec 2025 | Feb 2026 |
Not enough votes to call it. On the specs, nothing separates them.
DeepSeek V3.2 Speciale costs 7.6x less per token.
DeepSeek V3.2 Speciale is cheaper on both: 1.4× input, 7.6× output.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 9 Sep 2026.
DeepSeek V3.2 Speciale uses 3.2x more hedging