Context
262K
Input
$0.40/M
Output
$3.20/M
Aliases:qwen/qwen3.5-122bqwen3-5-122b-a10balibaba-qwen3.5-122bqwen3.5-122b
Alibaba's Qwen3.5 native vision-language model with 122B total / 10B active parameters using a hybrid linear-attention sparse mixture-of-experts architecture.
novita/qwen3.5-122b-a10bQuantbf16
- Input
- $0.40/M
- Output
- $3.20/M
- Context
- 262K
- Max out
- 66K
- Caching
- Not offered
- Thinking out
- $3.20/M