Qwen: Qwen3 VL 235B A22B Instruct chat
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...
Capabilities
Context Window 262k tokens
Max Output 16k tokens
Inputs
Outputs
Pricing (per 1M tokens)
Input $0.20
Output $0.88
Cache Read $0.11
Cache Write -
Supported Parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p