Qwen/Qwen3-VL-235B-A22B-Instruct
deepinfra
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
- Context window
- 262,144 tokens
- Input cost
- —
- Output cost
- —
- Latency (p50)
- —