alicloud-ai-multimodal-qwen-vl

Category: provider Pass criteria: command exits 0 and output/alicloud-ai-multimodal-qwen-vl/validate.txt is generated. Use Qwen VL models for image input + text output understanding tasks via DashScope compatible-mode API. Prefer the Qwen3 VL family: When you need explicit "latest" routing or reproducible snapshots, use supported aliases/snapshots from the official model list, such as: Legacy names still seen in some workloads: Using local image: Structured extraction (JSON mode): Structured extraction (JSON Schema): - Save raw model responses and normalized extraction results to output/alicloud-ai-multimodal-qwen-vl/ . - Include input image reference and prompt for traceability. - Install dependencies (recommended in a venv): - Set DASHSCOPE_API_KEY in environment, or add dashscope_api_key to ~/.alibabacloud/credentials . - qwen3-vl-plus - qwen3-vl-flash - qwen3-vl-plus-latest - qwen3-vl-plus-2025-12-19 - qwen3-vl-flash-latest - qwen-vl-max-latest - qwen-vl-plus-latest - qwen-vl-ocr - qwen-vl-ocr-latest - prompt (string, required): user question/instruction about image. - image (string, required): HTTPS URL, local path, or data: URL. - model (string, optional): default qwen3-vl-plus .