The Orchestrator › Models › ByteDance

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...

Specifications

ProviderByteDance
Model IDbytedance/ui-tars-1.5-7b
Context window128K tokens (128,000)
Modalitiestext + image → text
TokenizerOther
Router sourcesOpenRouter, TrustedRouter
Released2025-07-22
Tracked since2026-11-14
PopularityNot in the ranked set
Reasoning—

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRouterbytedance/ui-tars-1.5-7b$0.1$0.2128K
standardTrustedRouterbytedance/ui-tars-1.5-7b$0.105$0.211128K

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$0.105$0.211128K
2026-11-14$0.1$0.2128K

Capabilities

Vision (image input)Structured outputsNo content storage (attested)Zero data retention

Trust flags come from TrustedRouter's per-provider attestations.

Supported parameters

frequency_penalty, logit_bias, logprobs, max_tokens, presence_penalty, repetition_penalty, seed, stop, structured_outputs, temperature, top_k, top_logprobs, top_p