Qwen3.5-122B-A10B
qwen/qwen3.5-122b-a10b
- context
- 262K
- modalities
- text, image, video → text
- capabilities
- Tool use, Reasoning, Vision, Structured output, Low cost
Overview
The 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...
Providers
- AlibabaView Alibaba
- AtlasCloudView AtlasCloud
- DeepInfraView DeepInfra
- NovitaView Novita
- SiliconFlowView SiliconFlow
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| Alibaba | $0.26 | $2.08 |
| AtlasCloud | $0.30 | $2.40 |
| DeepInfra | $0.29 | $2.40 |
| Novita | $0.40 | $3.20 |
| SiliconFlow | $0.26 | $2.08 |
Alibaba
- input / 1M
- $0.26
- output / 1M
- $2.08
AtlasCloud
- input / 1M
- $0.30
- output / 1M
- $2.40
DeepInfra
- input / 1M
- $0.29
- output / 1M
- $2.40
Novita
- input / 1M
- $0.40
- output / 1M
- $3.20
SiliconFlow
- input / 1M
- $0.26
- output / 1M
- $2.08
Use this model
through Nautili
Route requests to Qwen3.5-122B-A10B through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.