UI-TARS 7B with Jev
UI-TARS 7B is a model from ByteDance, released 2025-07-22. It costs $0.100 per million input tokens and $0.200 per million output tokens, reads up to 128K tokens of context, and writes up to 2,048 tokens in one reply. Through llm11, set model to bytedance/ui-tars-1.5-7b.
- Input price
- $0.100 / 1M
- Output price
- $0.200 / 1M
- Context window
- 128K tokens
- Max output
- 2K tokens
- Cached input
- $0.100 / 1M
- Released
- 2025-07-22
- Accepts
- image, text
Read from the provider's prompt cache
Read from the live catalogue and refreshed daily. At blended list price, 86% of the 332 priced models we can call cost more.
Using UI-TARS 7B with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. UI-TARS 7B does the answering when Jev sends it work, or when you name it yourself. At list price UI-TARS 7B falls in the llm11-fast band, but no pack routes to it because ByteDance is not one of the labs the packs draw from. You can still pin it: pass bytedance/ui-tars-1.5-7b as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for UI-TARS 7B with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00009 | $0.090 |
| Question over retrieved documents | 4,000 / 500 | $0.00050 | $0.500 |
| Long document summary | 30,000 / 1,000 | $0.00320 | $3.20 |
Cheaper models to try
The catalogue has no benchmark score for UI-TARS 7B , so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen Qwen3 Coder 30B A3B Instruct | $0.070 | $0.280 | 262K | |
| Qwen Qwen3.5-Flash | $0.065 | $0.260 | 1M | |
| Qwen Qwen3.5-9B | $0.100 | $0.150 | 262K | |
| Mistral Ministral 3 3B 2512 | $0.100 | $0.100 | 131K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="bytedance/ui-tars-1.5-7b",
messages=[{"role": "user", "content": "Hello"}],
)Questions
- What is UI-TARS 7B with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. UI-TARS 7B does the answering when Jev sends it work, or when you name it yourself. At list price UI-TARS 7B falls in the llm11-fast band, but no pack routes to it because ByteDance is not one of the labs the packs draw from. You can still pin it: pass bytedance/ui-tars-1.5-7b as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is UI-TARS 7B a System One model?
- No. UI-TARS 7B answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does UI-TARS 7B cost?
- $0.100 per million input tokens and $0.200 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00050, so a thousand of them is about $0.500. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the UI-TARS 7B context window?
- 128,000 tokens, with up to 2,048 tokens in a single reply.
- Does UI-TARS 7B support tool calling and structured output?
- The catalogue lists structured output, but it does not list tool calling and reasoning controls.
- Can I use UI-TARS 7B through llm11?
- Yes. Set model to bytedance/ui-tars-1.5-7b on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to UI-TARS 7B ?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price UI-TARS 7B falls in the llm11-fast band, but no pack routes to it because ByteDance is not one of the labs the packs draw from. You can still pin it: pass bytedance/ui-tars-1.5-7b as model and routing steps aside while verification still runs.
- What is a cheaper alternative to UI-TARS 7B ?
- Nearest in price and below it: Qwen Qwen3 Coder 30B A3B Instruct at $0.070 in and $0.280 out, Qwen Qwen3.5-Flash at $0.065 in and $0.260 out and Qwen Qwen3.5-9B at $0.100 in and $0.150 out. The catalogue has no benchmark score for UI-TARS 7B , so this is a price ordering. It does not claim these answer as well.