All Models
Qwen3.6 Plus
Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference. Compared to the 3.5 series, it delivers...
Benchmarks
Available Providers (21)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Alibaba Coding Plan (China) | qwen3.6-plus | $0/MTok | $0/MTok | 1M | 65.5K | |
 Alibaba Coding Plan | qwen3.6-plus | $0/MTok | $0/MTok | 1M | 65.5K | |
 Alibaba Token Plan | qwen3.6-plus | $0/MTok | $0/MTok | 1M | 65.5K | |
 Alibaba Token Plan (China) | qwen3.6-plus | $0/MTok | $0/MTok | 1M | 65.5K | |
 Merge Gateway | qwen/qwen3.6-plus | $0.28/MTok | $1.65/MTok | 1M | 250K | |
 AIHubMix | qwen3.6-plus | $0.28/MTok | $1.69/MTok | 991K | 64K | |
 CrossModel | qwen/qwen3.6-plus | $0.32/MTok | $1.88/MTok | 1M | 65.5K | |
 Pioneer | qwen3.6-plus | $0.33/MTok | $1.95/MTok | 1M | 65.5K | |
 Kilo Gateway | qwen/qwen3.6-plus | $0.33/MTok | $1.95/MTok | 1M | 65.5K | |
 OpenRouter | qwen/qwen3.6-plus | $0.33/MTok | $1.95/MTok | 1M | 65.5K | |
 OpenCode Go | qwen3.6-plus | $0.50/MTok | $3/MTok | 1M | 65.5K | |
 LLM Gateway | qwen3.6-plus | $0.50/MTok | $3/MTok | 262.1K | 65.5K | |
 OpenCode Zen | qwen3.6-plus | $0.50/MTok | $3/MTok | 262.1K | 65.5K | |
 ZenMux | qwen/qwen3.6-plus | $0.50/MTok | $3/MTok | 1M | 64K | |
 EmpirioLabs AI | qwen3-6-plus | $0.50/MTok | $3/MTok | 1M | 65.5K | |
 Together AI | Qwen/Qwen3.6-Plus | $0.50/MTok | $3/MTok | 1M | 500K | |
 Auriko | qwen-3.6-plus | $0.50/MTok | $3/MTok | 1M | 65.5K | |
 OrcaRouter | qwen/qwen3.6-plus | $0.50/MTok | $3/MTok | 1M | 65.5K | |
 Alibaba | qwen3.6-plus | $0.50/MTok | $3/MTok | 1M | 65.5K | |
 Alibaba (China) | qwen3.6-plus | $0.50/MTok | $3/MTok | 1M | 65.5K | |
 Charm Hyper | qwen3.6-plus | $2/MTok | $6/MTok | 1M | 64K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output