← All models View on HuggingFace →
Qwen: Qwen3 VL 30B A3B Thinking
qwen/qwen3-vl-30b-a3b-thinking
VisionTool useJSONReasoningStreaming
Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...
Pricing
Input
$0.13 / 1M
Output
$1.56 / 1M
Specs
Context
131,072 tokens
Input
text, image
Output
text
Knowledge cutoff: 2025-03-31
Released: 2025-10
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Open weights · HuggingFace
19,032 downloads/mo
198 likes
apache-2.0 image-text-to-text