All models
ByteDance
UI-TARS 7B fastruns locally
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...
Input / 1M
$0.10
USD per million tokens
Output / 1M
$0.20
USD per million tokens
Est. cost / token
$0.000000125
$0.13 per 1M, 3:1 mix
Context window
128K
max output 2K
Major features
VisionOpen weightsCachingJSON schema
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning2
- math2
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context3
- agentic1
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 5.3 GB |
| Q3_K_M | fair | 5.9 GB |
| Q4_K_Mrecommended | good | 7 GB |
| Q5_K_M | very good | 7.9 GB |
| Q6_K | excellent | 8.8 GB |
| Q8_0 | near-lossless | 11 GB |
| F16 | lossless | 19.1 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.10 | $0.20 | $0.10 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.10
- Output
- $0.20
- Cached input
- $0.10
- Blended (3:1)
- $0.13
Details
- Company
- ByteDance
- Version
- 1.5
- Family
- Ui
- Released
- 2025-07-22
- Parameters
- 8.3B
- Max output
- 2K
- Open weights
- Yes
- Inputs
- image, text
- Last synced
- 25 min ago