{"ok":true,"model":{"id":"bytedance/ui-tars-1.5-7b","name":"UI-TARS 7B","vendor":"bytedance","releasedAt":"2025-07-22","contextLength":128000,"maxOutput":2048,"input":["image","text"],"output":["text"],"features":["structured_outputs"],"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...","inputPerM":0.1,"outputPerM":0.2,"cacheReadPerM":0.1,"firstSeen":"2026-10-28","lastSeen":"2026-11-06","gone":null,"history":[{"from":"2026-10-28","to":"2026-11-06","inputPerM":0.1,"outputPerM":0.2,"cacheReadPerM":0.1}]},"priceKnowledge":null,"license":"CC-BY-4.0"}