UI-TARS 7B
ByteDance · released Apr 16, 2025 · ByteDance-Seed/UI-TARS-1.5-7B
- Type
- Open weightsApache License 2.0
- Params
- 8.3B
- Context
- 128K
about 96K words of context
Our take
Written Sep 2, 2026UI-TARS is a vision-language model from ByteDance that reads both text and images to understand and interact with software interfaces. At 8.3 billion parameters it is unusually compact for a multimodal model, and it carries a permissive Apache licence that allows commercial use without restriction.
Pick this for interface-automation tasks where you need open weights and a permissive licence, or where identical pricing across both hosts removes comparison friction. Use it when you need 128,000 tokens of context for long interface sequences or documentation. Skip it if you need measured quality data to make a decision, or if throughput consistency across providers matters.
The case for it
- Apache 2.0 licence allows commercial use, modification and redistribution without restriction.
- Identical pricing across both tracked hosts removes cost-comparison friction.
- 8.3 billion parameters is notably smaller than typical multimodal models, easing deployment.
The case against it
- No benchmark scores in our data — chat, reasoning, coding and UI-specific accuracy are all unverified.
- Throughput is only known for one of two offers; the other is undisclosed.
- All 8.3 billion parameters appear active per token, with no efficiency architecture indicated.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 16.1 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 24.1 GB spare means a 10% error in the size would not change the answer.
Apple M1 (8-core GPU) · 16 GB
Room to spare. 5.3 GB spare means a 10% error in the size would not change the answer.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first.
Check against your own machine → · Where to rent it hosted →
Or rent it from someone else
Prices checked 4 hours ago — each listing carries its own date.
- per 1M tokens
- $0.10 in / $0.20 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.10 / $0.20checked 4 hours ago | 128K | not measured | Unknown | Unknown | Unknown |
| Parasailbf16Through OpenRouter | $0.10 / $0.20checked 4 hours ago | 128K2K max reply | 11 tok/s | No | No | Confirmed |
Across the 2 listings we hold: 1 says it does not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✗ | ✗ | ✓ |
| Parasailbf16Through OpenRouter | ✗ | ✗ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 0 of 2 listings say yes, 2 say no. Strict schema: 2 of 2 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
- We hold a decode speed for it, but no prompt-processing (prefill) figure, so how long the input side of a job takes is unknown to us.
Licence and identifiers
What the licence allowsApache License 2.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- ByteDance-Seed/UI-TARS-1.5-7B
- Architecture
- Dense
- Takes in, gives back
- Text and images in, text out
- Catalogue slug
- bytedance-ui-tars-7b