Qwen3.5-122B-A10B
AlibabaThe Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
In
$0.26
Out
$2.08
Blended
$0.72
Where to buy this model
4 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| ● SiliconFlow cheapestfp8 | $0.26 | $2.08 | $0.72 | - |
| ● Alibaba | $0.26 | $2.08 | $0.72 | +0% |
| ● AtlasCloud fp8 | $0.30 | $2.40 | $0.83 | +15% |
| $0.40 | $3.20 | $1.10 | +53% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 262K
- max output
- 66K
- Family
- qwen
- Modalities
- text · image · video
- Features
- json · reasoning · tools
Live pricing, updated 2026-11-03.
Alibaba models at a similar price
| Model | In | Out | Ctx |
|---|---|---|---|
| Qwen3.8 27B | $0.15 | $1.88 | 1.024M |
| Qwen3.5 Plus 2026-02-15 | $0.26 | $1.56 | 1M |
| Qwen3 VL 235B A22B Instruct | $0.21 | $1.9 | 262K |
| Qwen3.5-122B-A10B · this model | $0.26 | $2.08 | 262K |
| Qwen3.6 Plus | $0.325 | $1.95 | 1M |
| Qwen3.5-27B | $0.26 | $2.6 | 262K |