Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
UI-TARS 7B - Model - OpenSmartRoute
Modelv1.0.0
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.
Reference model card from the OpenRouter listing - model bytedance/ui-tars-1.5-7b. Prices are per million tokens as listed; ratings and installs below are from this marketplace.
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...
Facts
Vendor
ByteDance
Context window
128,000 tokens
Max output
2,048 tokens
Input price
$0.10 / 1M tokens
Output price
$0.20 / 1M tokens
Input
image, text
Output
text
Tool calling
no
Structured outputs
yes
Reasoning
no
Open weights
ByteDance-Seed/UI-TARS-1.5-7B
Endpoint: https://openrouter.ai/api/v1 (OpenAI-compatible), model bytedance/ui-tars-1.5-7b
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "model-bytedance-ui-tars-1-5-7b", ...}
Installed into a catalogue, chosen by a router
Install UI-TARS 7B and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
