deepseek
UI-TARS 7B vs DeepSeek V4 Flash 0731
74.2 overall · $0.190 / 1M
// bytedance
UI-TARS 7B
bytedance/ui-tars-1.5-7b
image inputprompt caching
UI-TARS 7B costs $0.100 per 1M input tokens and $0.200 per 1M output tokens with a 128K-token context window.
A model from bytedance, released Jul 22, 2025. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- $0.100
- Output / 1M
- $0.200
- Context
- 128K
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | $0.100 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $0.200 |
| Blended price 3:1 input:output — #45 cheapest of 343 listed models | $0.125 |
| Cached input read Blank means not priced separately — not free | $0.100 |
| Cache write | — |
| Context window | 128,000 tokens |
| Max output | 2,048 tokens |
| Input modalities | image, text |
| Tool calling | No |
| Extended reasoning | No |
| Knowledge cutoff | 2025-01-31 |
| Listed | Jul 22, 2025 |
What UI-TARS 7B costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $40.00/mo |
| RAG assistant 8K in / 600 out × 100K requests | $92.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $96.00/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $115.00/mo |
| Bulk classification 500 in / 20 out × 5M requests | $270.00/mo |
Compare UI-TARS 7B with
Benchmarked models at a similar price.
openai
UI-TARS 7B vs GPT-6 Luna
72.0 overall · $0.200 / 1M
deepseek
UI-TARS 7B vs DeepSeek V4.1 Flash
81.1 overall · $0.200 / 1M
z-ai
UI-TARS 7B vs GLM 5.3 Flash
71.6 overall · $0.237 / 1M
deepseek
UI-TARS 7B vs DeepSeek V4 Flash 0423
65.5 overall · $0.061 / 1M
deepseek
UI-TARS 7B vs DeepSeek V4 Flash Vision Exp
76.8 overall · $0.330 / 1M
UI-TARS 7B FAQ
How much does UI-TARS 7B cost?
UI-TARS 7B lists at $0.100 per 1M input tokens and $0.200 per 1M output tokens, with cached input reads at $0.100 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $92.00 at list price.
What is the context window of UI-TARS 7B ?
UI-TARS 7B accepts up to 128,000 tokens of context and can return up to 2,048 output tokens per response.
Does UI-TARS 7B support tool calling?
UI-TARS 7B does not list tool (function) calling support. It accepts image, text input.
How does UI-TARS 7B score on benchmarks?
LiveBench has not published a run for UI-TARS 7B yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for UI-TARS 7B ?
On OpenRouter the model ID is "bytedance/ui-tars-1.5-7b". It was listed on Jul 22, 2025.
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.