UI-TARS 7B

Name: UI-TARS 7B
Author: ByteDance

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

by ByteDance(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

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

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 configure
curl -s -X POST https://api.opensmartroute.ai/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", ...}

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

model-bytedance-ui-tars-1-5-7b.ocm.jsonjson

{
  "ocm": "1",
  "id": "model-bytedance-ui-tars-1-5-7b",
  "kind": "llm",
  "name": "UI-TARS 7B ",
  "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...",
  "publisher": "ByteDance",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "llm",
      "bytedance",
      "openrouter",
      "open-weights",
      "image",
      "models"
    ],
    "languages": [
      "en"
    ],
    "modalities": [
      "image",
      "text"
    ],
    "supports_tools": false,
    "supports_streaming": true,
    "context_window": 128000
  },
  "quality_prior": 0.6,
  "examples": [
    "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..."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "models",
      "ref": "1753205056",
      "url": "https://openrouter.ai/bytedance/ui-tars-1.5-7b",
      "key": "bytedance/ui-tars-1.5-7b",
      "catalogue": "https://openrouter.ai/api/v1"
    },
    "model": "bytedance/ui-tars-1.5-7b",
    "pricing": {
      "input_usd_per_1m": 0.1,
      "output_usd_per_1m": 0.2,
      "cache_read_usd_per_1m": 0.1
    },
    "max_output_tokens": 2048,
    "output_modalities": [
      "text"
    ],
    "hugging_face_id": "ByteDance-Seed/UI-TARS-1.5-7B",
    "created": 1753205056,
    "benchmarks": {
      "hub_downloads": 605818,
      "hub_downloads_total": 4253451,
      "hub_likes": 604,
      "hub_trending": 1
    }
  },
  "cost": {
    "usd_per_1k_tokens": 0.00015
  },
  "endpoints": [
    {
      "protocol": "openai",
      "url": "https://openrouter.ai/api/v1"
    }
  ]
}

Fetch it by URL: GET /api/v1/registry/model-bytedance-ui-tars-1-5-7b/manifest?version=1.0.0

About

UI-TARS 7B

Facts

Use it

Manifest

Reviews