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 learning-based reasoning, enabling reliable action planning and execution across virtual interfaces.
$0.05
$0.05
$0.10
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games.
On NagaAI, UI-TARS 7B costs $0.05 per 1M input tokens and $0.10 per 1M output tokens. You pay only for what you use, with no subscription.
UI-TARS 7B reads up to 128k tokens in one request, counting the prompt and the answer together.
UI-TARS 7B can answer in a JSON schema you give it. Tool calling is not available for it.
It takes text and images as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Seed 2.1 TurboByteDanceSeed-2.0-CodeByteDanceSeed-2.0-LiteByteDance$0.125 / $1 per 1MSeed-2.0-MiniByteDance
LFM3-1.7BLiquid AI$0.04 / $0.10 per 1M
Ripple 65B PreviewRicursive AI$0.10 / $0.30 per 1MNot enough throughput data
Not enough TTFT data
Not enough activity data to display a chart