All Models
Qwen3.5 122B-A10B
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...
Benchmarks
Available Providers (17)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Nvidia | qwen/qwen3.5-122b-a10b | $0/MTok | $0/MTok | 262.1K | 65.5K | |
 EmpirioLabs AI | qwen3-5-122b-a10b | $0.12/MTok | $0.92/MTok | 256K | 64K | |
 OrcaRouter | qwen/qwen3.5-122b-a10b | $0.12/MTok | $0.92/MTok | 262.1K | 65.5K | |
 Merge Gateway | qwen/qwen3.5-122b-a10b | $0.12/MTok | $0.92/MTok | 131.1K | 32.8K | |
 Neon | qwen35-122b-a10b | $0.22/MTok | $2.20/MTok | 262.1K | 8K | |
 SiliconFlow | Qwen/Qwen3.5-122B-A10B | $0.26/MTok | $2.08/MTok | 262.1K | 262.1K | |
 Kilo Gateway | qwen/qwen3.5-122b-a10b | $0.26/MTok | $2.08/MTok | 262.1K | 65.5K | |
 OpenRouter | qwen/qwen3.5-122b-a10b | $0.26/MTok | $2.08/MTok | 262.1K | 65.5K | |
 Deep Infra | Qwen/Qwen3.5-122B-A10B | $0.29/MTok | $2.40/MTok | 262.1K | 65.5K | |
 NEAR AI Cloud | Qwen/Qwen3.5-122B-A10B | $0.40/MTok | $3.20/MTok | 131.1K | 32.8K | |
 Mixlayer | qwen/qwen3.5-122b-a10b | $0.40/MTok | $3.20/MTok | 262.1K | 262.1K | |
 Alibaba | qwen3.5-122b-a10b | $0.40/MTok | $3.20/MTok | 262.1K | 65.5K | |
 NovitaAI | qwen/qwen3.5-122b-a10b | $0.40/MTok | $3.20/MTok | 262.1K | 65.5K | |
 Hugging Face | Qwen/Qwen3.5-122B-A10B | $0.40/MTok | $3.20/MTok | 262.1K | 65.5K | |
 NanoGPT | qwen3.5-122b-a10b | $0.44/MTok | $3.50/MTok | 131.1K | 32.8K | |
 Cortecs | qwen3.5-122b-a10b | $0.44/MTok | $3.11/MTok | 262.1K | 262.1K | |
 TensorX | qwen/qwen3.5-122b-a10b | $0.50/MTok | $3.50/MTok | 262.1K | 262.1K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output