by Qwen
The Qwen3 series of compact visual-understanding models achieves an effective fusion of thinking mode and non-thinking mode, outperforming the open-source Qwen3-VL-30B-A3B with faster response speeds. It comprehensively upgrades image and video understanding, supporting ultra-long contexts such as long videos and long documents, spatial awareness, and universal object recognition; it also possesses visual 2D/3D localization capabilities and is capable of handling complex real-world tasks.
| Input | $0.02 / 1M tokens |
| Output | $0.21 / 1M tokens |
| Cache read | $0.0041 / 1M tokens |
| Context window | 254,000 tokens |
| Modalities | text, image, video |
| Features | tools, function_calling, structured_outputs |
Use qwen3-vl-flash via the AIHubMix unified API — one interface for every major LLM.