{"id":"qwen/qwen3-vl-8b-instruct","name":"Qwen3 VL 8B Instruct","owned_by":"qwen","description":"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...","context_window":262144,"max_tokens":32768,"type":"language","tags":["tool-use","vision"],"released":1760463308,"modalities":{"input":["image","text"],"output":["text"]},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"pricing":{"input":"0.000000117","output":"0.000000455"},"legal":[]}