Qwen3 Next 80B A3B Instruct vs Qwen3.5-35B-A3B
Qwen3 Next 80B A3B Instruct is the cheaper option on input by 36%; Qwen3.5-35B-A3B is cheaper on output by 9%. Figures below are per million tokens, from vendor pricing cited in our reporting.
| Qwen3 Next 80B A3B Instruct | Qwen3.5-35B-A3B | |
|---|---|---|
| Input per 1M tokens | $0.09 | $0.14 |
| Output per 1M tokens | $1.10 | $1 |
| Cached input per 1M | — | $0.05 |
| Context window | 262K tokens | 262K tokens |
| Parameters | — | — |
| Licence | open weights | open weights |
| Benchmark | — | — |
| Vendor | Alibaba | Alibaba |
| Released | — | — |
What the numbers say
- Input price gap: 36% ($0.09 vs $0.14).
- Blended three-to-one input/output rate: $1.37 for Qwen3 Next 80B A3B Instruct, $1.42 for Qwen3.5-35B-A3B.
- Context: 262K tokens against 262K tokens.
- Licence: Qwen3 Next 80B A3B Instruct is open weights; Qwen3.5-35B-A3B is open weights.
Sources
Qwen3 Next 80B A3B Instruct specs · Qwen3.5-35B-A3B specs · Full price index