Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b
- context
- 262K
- modalities
- text, image, video → text
- capabilities
- Tool use, Reasoning, Vision, Structured output
Overview
The Qwen3.5 series 397B-A17B 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. It delivers...
Providers
- AlibabaView Alibaba
- AtlasCloudView AtlasCloud
- DeepInfraView DeepInfra
- DigitalOceanView DigitalOcean
- GMICloudView GMICloud
- NovitaView Novita
- ParasailView Parasail
- PhalaView Phala
- StreamLakeView StreamLake
- VeniceView Venice
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| Alibaba | $0.39 | $2.34 |
| AtlasCloud | $0.55 | $3.50 |
| DeepInfra | $0.45 | $3.00 |
| DigitalOcean | $0.55 | $3.50 |
| GMICloud | $0.60 | $3.60 |
| Novita | $0.60 | $3.60 |
| Parasail | $0.50 | $3.60 |
| Phala | $0.55 | $3.50 |
| StreamLake | $0.60 | $3.60 |
| Venice | $0.75 | $4.50 |
Alibaba
- input / 1M
- $0.39
- output / 1M
- $2.34
AtlasCloud
- input / 1M
- $0.55
- output / 1M
- $3.50
DeepInfra
- input / 1M
- $0.45
- output / 1M
- $3.00
DigitalOcean
- input / 1M
- $0.55
- output / 1M
- $3.50
GMICloud
- input / 1M
- $0.60
- output / 1M
- $3.60
Novita
- input / 1M
- $0.60
- output / 1M
- $3.60
Parasail
- input / 1M
- $0.50
- output / 1M
- $3.60
Phala
- input / 1M
- $0.55
- output / 1M
- $3.50
StreamLake
- input / 1M
- $0.60
- output / 1M
- $3.60
Venice
- input / 1M
- $0.75
- output / 1M
- $4.50
Use this model
through Nautili
Route requests to Qwen3.5 397B A17B 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.