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 U…

bytedance/ui-tars-1.5-7b

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 learning-based reasoning, enabling robust action planning and execution across virtual interfaces.

This model achieves state-of-the-art results on a range of interactive and grounding benchmarks, including OSworld, WebVoyager, AndroidWorld, and ScreenSpot. It also demonstrates perfect task completion across diverse Poki games and outperforms prior models in Minecraft agent tasks. UI-TARS-1.5 supports thought decomposition during inference and shows strong scaling across variants, with the 1.5 version notably exceeding the performance of earlier 72B and 7B checkpoints.

Specifications & capabilities

Input
image, text
Output
text
Context window · tokens
128000
Knowledge cutoff
2025-01-31
Capabilities
multimodal, promptCaching, structuredOutputs, visionInput
Description source ↗

Published prices

1–3 / 3

bytedance/ui-tars-1.5-7b ↗

$0.10

Inference provider
openRouter
Platform
OpenRouter
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions

Provider specifications & access

1–3 / 3

ByteDance-Seed/UI-TARS-1.5-7B ↗

source model id
HuggingFace/bytedance-seed-ui-tars-1.5-7b@1
hosting
foundry-managed-compute
platforms
  • Microsoft Foundry
license
apache-2.0
architecture
input_modalities
  • text
output_modalities
  • text
capabilities

    ByteDance-Seed/UI-TARS-1.5-7B ↗

    source model id
    HuggingFace/bytedance-seed-ui-tars-1.5-7b@2
    hosting
    foundry-managed-compute
    platforms
    • Microsoft Foundry
    license
    apache-2.0
    architecture
    input_modalities
    • text
    output_modalities
    • text
    capabilities

      ByteDance-Seed/UI-TARS-1.5-7B ↗

      source model id
      publishers/hf-bytedance-seed/models/ui-tars-1.5-7b@001
      hosting
      vertex-self-deployed
      platforms
      • Google Cloud Vertex AI
      architecture
      input_modalities
      • image
      • text
      output_modalities
      • text
      capabilities
      • multimodal
      • visionInput

      Source specification observations

      1–3 / 3

      openRouter ↗

      field
      context_length
      value
      128000
      normalized value
      128000
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      knowledge_cutoff
      reported field
      knowledge_cutoff
      value
      2025-01-31
      normalized value
      2025-01-31
      precision
      day
      scope
      source-model
      source id
      openRouter
      confidence
      1

      openRouter ↗

      field
      max_output_tokens
      value
      2048
      normalized value
      2048
      scope
      source-model
      source id
      openRouter
      confidence
      1

      Original sources

      1–9 / 9

      Hugging Face · ByteDance-Seed/UI-TARS-1.5-7B ↗

      Google Cloud · Model page ↗

      Microsoft Foundry · Model page ↗

      Microsoft Foundry · Model page ↗

      OpenRouter · Model page ↗

      Microsoft Foundry · Model documentation ↗

      Google Cloud · Catalog ↗

      Microsoft Foundry · Catalog ↗

      OpenRouter · Catalog ↗

      Source links

      1–4 / 4

      Explore more models

      Models

      Loading
      EVIDENCE / COMPARISON

      Benchmarks

      Explore every benchmark

      Loading

      These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

      Install TensorTrace