---
id: "bytedance/ui-tars-1.5-7b"
also: ["bytedance/ui-tars-1.5-7b", "ByteDance-Seed/UI-TARS-1.5-7B"]
cheapest_list_usd_per_m: "0.1 in, 0.2 out, at parasail/bf16 on openrouter"
cheapest_effective_usd_per_m: "0.0999 in, 0.1949 out, at parasail/bf16 on openrouter"
context: 128000
max_output: 2048
input: ["image", "text"]
output: ["text"]
released: "2025-07-22"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "repetition_penalty", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_logprobs", "top_p"]
endpoints: 1
gateways: "openrouter (1)"
no_training: 1
trains: 0
retains_prompts: 0
---
# ByteDance: UI-TARS 7B 

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...