{"id":"bytedance/ui-tars-1.5-7b","name":"UI-TARS 7B ","owned_by":"bytedance","description":"UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, it builds upon the UI-TARS framework with reinforcement...","context_window":128000,"max_tokens":2048,"type":"language","tags":["vision"],"released":1753205056,"modalities":{"input":["image","text"],"output":["text"]},"supported_parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","presence_penalty","repetition_penalty","seed","stop","structured_outputs","temperature","top_k","top_logprobs","top_p"],"pricing":{"input":"0.0000001","output":"0.0000002","input_cache_read":"0.0000001"},"legal":[]}