Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.32 |
| Output tokens | $3.20 |
Capabilities
VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution
About Qwen3.6-27B
Qwen3.6-27B is a dense open-weight multimodal model from Alibaba's Qwen team, released April 22, 2026. It combines a 27B parameter language model with a vision encoder for text, image, and video tasks, supports a 262K native context window extensible to around 1M tokens via YaRN, and is tuned for agentic coding, repository-level reasoning, tool use, and multimodal reasoning.
Get Started
Model Specs
Released2026-04-22
Parameters27B
Context262K
ArchitectureDense