Qwen3.6 35B A3B
AlibabaQwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
In
$0.10
Out
$0.90
Blended
$0.30
Where to buy this model
11 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| ● PrimeIntellect cheapestfp8 | $0.01 | $0.09 | $0.03 | - |
| ● Darkbloom fp4 | $0.05 | $0.70 | $0.21 | +600% |
| ● AkashML fp8 | $0.10 | $0.90 | $0.30 | +900% |
| $0.10 | $0.90 | $0.30 | +900% | |
| $0.10 | $0.95 | $0.31 | +933% | |
| ● CoreWeave fp8 | $0.10 | $0.95 | $0.31 | +933% |
| ● DekaLLM | $0.10 | $1.00 | $0.33 | +1000% |
| ● Venice fp8 | $0.10 | $1.00 | $0.33 | +1000% |
| ● Phala | $0.20 | $1.27 | $0.47 | +1467% |
| ● AtlasCloud fp8 | $0.25 | $1.25 | $0.50 | +1567% |
| ● SiliconFlow fp8 | $0.24 | $1.80 | $0.63 | +2000% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 262K
- max output
- 236K
- cache read /1M
- $0.03
- 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 Coder 30B A3B Instruct | $0.15 | $0.6 | 262K |
| Qwen3 VL 30B A3B Instruct | $0.15 | $0.6 | 262K |
| Qwen3 Coder Next | $0.12 | $0.8 | 262K |
| Qwen3.6 35B A3B · this model | $0.1 | $0.9 | 262K |
| Qwen3 Next 80B A3B Instruct | $0.1 | $1.1 | 262K |
| Qwen3.5-35B-A3B | $0.14 | $1 | 262K |