DeepSeek V3 (March 2024) is cheaper than Qwen3.5 122B A10B at $0.14/M vs $0.4/M input tokens.
| Spec | DeepSeek V3 (March 2024) | Qwen3.5 122B A10B |
|---|---|---|
| Input price | $0.14/M tokens | $0.4/M tokens |
| Output price | $0.28/M tokens | $3.2/M tokens |
| Context window | 128K tokens | 262K tokens |
| Released | Mar 2024 | Feb 2026 |
| MMLU-Pro | 81.2% | 86.7 |
Not enough votes to call it. On the specs, nothing separates them.
DeepSeek V3 (March 2024) costs 11x less per token.
DeepSeek V3 (March 2024) is cheaper on both — 2.9× input, 11× output
Qwen3.5 122B A10B uses 2.6x more transitions
DeepSeek V3 (March 2024) is cheaper than Qwen3.5 122B A10B at $0.14/M vs $0.4/M input tokens.
| Spec | DeepSeek V3 (March 2024) | Qwen3.5 122B A10B |
|---|---|---|
| Input price | $0.14/M tokens | $0.4/M tokens |
| Output price | $0.28/M tokens | $3.2/M tokens |
| Context window | 128K tokens | 262K tokens |
| Released | Mar 2024 | Feb 2026 |
| MMLU-Pro | 81.2% | 86.7 |
Not enough votes to call it. On the specs, nothing separates them.
DeepSeek V3 (March 2024) costs 11x less per token.
DeepSeek V3 (March 2024) is cheaper on both — 2.9× input, 11× output
Qwen3.5 122B A10B uses 2.6x more transitions