← All models View on HuggingFace →
Qwen: Qwen3 VL 235B A22B Thinking
qwen/qwen3-vl-235b-a22b-thinking
VisionTool useJSONReasoningStreaming
Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....
Pricing
Input
$0.26 / 1M
Output
$2.60 / 1M
Specs
Context
131,072 tokens
Input
text, image
Output
text
Knowledge cutoff: 2025-03-31
Released: 2025-09
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p
Open weights · HuggingFace
8,631 downloads/mo
396 likes
apache-2.0 image-text-to-text