All Models
Qwen3.5 35B A3B
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
Benchmarks
Available Providers (15)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 OrcaRouter | qwen/qwen3.5-35b-a3b | $0.06/MTok | $0.46/MTok | 262.1K | 65.5K | |
 Merge Gateway | qwen/qwen3.5-35b-a3b | $0.06/MTok | $0.46/MTok | 131.1K | 32.8K | |
 EmpirioLabs AI | qwen3-5-35b-a3b | $0.06/MTok | $0.46/MTok | 256K | 64K | |
 Requesty | qwen3.5-35b-a3b | $0.13/MTok | $0.90/MTok | 262.1K | 262.1K | |
 Kilo Gateway | qwen/qwen3.5-35b-a3b | $0.16/MTok | $1.30/MTok | 262.1K | 262.1K | |
 NanoGPT | qwen3.5-35b-a3b | $0.23/MTok | $1.80/MTok | 260.1K | 65.5K | |
 SiliconFlow | Qwen/Qwen3.5-35B-A3B | $0.24/MTok | $1.80/MTok | 262.1K | 262.1K | |
 Mixlayer | qwen/qwen3.5-35b-a3b | $0.25/MTok | $1.30/MTok | 262.1K | 262.1K | |
 Jalapeno Cloud | Qwen3.5-35B-A3B | $0.25/MTok | $2/MTok | 262.1K | 65.5K | |
 Hugging Face | Qwen/Qwen3.5-35B-A3B | $0.25/MTok | $2/MTok | 262.1K | 65.5K | |
 OpenRouter | qwen/qwen3.5-35b-a3b | $0.25/MTok | $1.25/MTok | 262.1K | 262.1K | |
 Alibaba | qwen3.5-35b-a3b | $0.25/MTok | $2/MTok | 262.1K | 65.5K | |
 NovitaAI | qwen/qwen3.5-35b-a3b | $0.25/MTok | $2/MTok | 262.1K | 65.5K | |
 Weights & Biases | Qwen/Qwen3.5-35B-A3B | $0.25/MTok | $1.25/MTok | 262.1K | 262.1K | |
 Ofox | bailian/qwen3.5-35b-a3b | $0.29/MTok | $1.83/MTok | 262.1K | 65.5K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output