{"data":{"id":"bytedance/ui-tars-1.5-7b","name":"ByteDance: UI-TARS 7B ","created":1753205056,"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...","architecture":{"tokenizer":"Other","instruct_type":null,"modality":"text+image->text","input_modalities":["image","text"],"output_modalities":["text"]},"endpoints":[{"name":"Parasail | bytedance/ui-tars-1.5-7b","model_id":"bytedance/ui-tars-1.5-7b","model_name":"ByteDance: UI-TARS 7B ","context_length":128000,"pricing":{"prompt":"0.0000001","completion":"0.0000002","input_cache_read":"0.0000001","discount":0},"provider_name":"Parasail","tag":"parasail/bf16","quantization":"bf16","max_completion_tokens":2048,"max_prompt_tokens":null,"supported_parameters":["max_tokens","temperature","top_p","frequency_penalty","presence_penalty","repetition_penalty","seed","stop","top_k","logit_bias","structured_outputs","logprobs","top_logprobs"],"supports_tool_choice":{"none":true,"auto":true,"required":true,"function":true},"status":0,"uptime_last_30m":100,"uptime_last_5m":100,"uptime_last_1d":100,"supports_implicit_caching":false,"supports_voice_cloning":false,"supports_multiple_audio_references":false,"supports_image_reference":false,"latency_last_30m":null,"throughput_last_30m":null}]}}