← model directory

qwen

Qwen: Qwen3.5 397B A17B

qwen/qwen3.5-397b-a17b

↓ runs free on your own hardware

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...

specs & pricing
Type
text
Provider
qwen
Model ID
qwen/qwen3.5-397b-a17b
Capabilities
vision, tools, reasoning
Context window
262K tokens
Self-hostable
Yes — runs on your own GPU
Input price
$0.43 / 1M tokens
Output price
$2.57 / 1M tokens

Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.

Qwen: Qwen3.5 397B A17B — pricing, context & specs | Wide Area Intelligence