Qwen
Qwen: Qwen3 VL 8B Instruct
Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features improved multimodal fusion with Interleaved-MRoPE for long-horizon...
| Specifications | |
|---|---|
| Provider | Qwen |
| Input pricing | $0.12/M tokens |
| Output pricing | $0.45/M tokens |
| Context length | 262K tokens |
| Max output | 33K tokens |
| Input modalities | imagetext |
| Output modalities | text |
| Tokenizer | Qwen3 |
| Content moderated | No |
| HuggingFace | Qwen/Qwen3-VL-8B-Instruct |
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p