Back to all models
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...
qwen/qwen3-vl-8b-instruct
Context Size
262.144K
Input Price
37,500 pts/M2,306 Ks/M
Output Price
112,500 pts/M6,919 Ks/M
Architecture
Image
Text
Supported Parameters
frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Details
TokenizerQwen3
Max Completion235,929 tokens
Provider Context262.144K tokens
ModeratedNo
CreatedOct 14, 2025