Qwen omni model for text, vision, audio, and multimodal agent tasks
Details
| Field | Value |
|---|---|
| id | qwen-omni-turbo |
| family | qwen |
| modality | text+image+audio+video->text+audio |
| context_length | 32768 |
| max_output_tokens | 2048 |
| knowledge_cutoff | 2024-04 |
| release_date | 2025-01-19 |
| is_open_weights | no |
| supports_tool_call | yes |
| supports_reasoning | no |
| supports_structured_output | no |
| supports_attachment | no |
| input_modalities | text, image, audio, video |
| output_modalities | text, audio |