Qwen
Qwen: Qwen3 VL 235B A22B Instruct
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...
| Specifications | |
|---|---|
| Provider | Qwen |
| Input pricing | $0.21/M tokens |
| Output pricing | $1.90/M tokens |
| Context length | 262K tokens |
| Max output | 33K tokens |
| Input modalities | textimage |
| Output modalities | text |
| Tokenizer | Qwen3 |
| Knowledge cutoff | 2025-03-31 |
| Content moderated | No |
| HuggingFace | Qwen/Qwen3-VL-235B-A22B-Instruct |
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p