bytedance
ByteDance: UI-TARS 7B
bytedance/ui-tars-1.5-7b
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
UI-TARS-1.5-7B is ByteDance’s released 7B multimodal agent variant for GUI-oriented tasks. The OpenRouter catalog lists image and text inputs, text output, a 128,000-token context, and structured-output support. ByteDance’s model card describes the UI-TARS-1.5 approach as reasoning before acting through reinforcement learning, with uses spanning desktop, browser, mobile, and game interfaces. Variant-specific results appear in the card’s model-scale table, but the evidence pack contains no independent evaluation. Treat it as a candidate for controlled GUI workflows and validate it on the intended workload.[1][2]
Strengths
- Accepts image and text inputs and returns text, matching screenshot-driven GUI pipelines.[1][2]
- The card describes reinforcement-learning-based reasoning before action, intended to improve adaptability and inference-time scaling.[2]
- The catalog reports a 128,000-token context and structured-output support, useful for long observations and machine-readable actions.[1]
Limitations
Where to use it
- A candidate for prototypes that inspect desktop, browser, or mobile screenshots and emit textual next actions for an external executor.[1][2]
- May fit research or evaluation on GUI grounding and general computer-use agents.[2]
- Could be explored for game interfaces, with the caveat that this variant is not specifically optimized for games.[2]
Sources
- [1] OpenRouter catalog · ByteDance: UI-TARS 7B Sources checked: Nov 13, 2026
- [2] Model documentation · ByteDance: UI-TARS 7B Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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
- Model ID
- bytedance/ui-tars-1.5-7b
- Creator
- bytedance
- Added to OpenRouter
- 22.07.2025
- Context length
- 128,000
- Modality
- text+image->text
- Input modalities
- image, text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.100 / out $0.200
- Knowledge cutoff
- 31.01.2025
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Parasailbf16 | 128,000 | $0.100 | $0.200 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.