UI-TARS 7B
ByteDancehuggingface.co/ByteDance-Seed/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...
Updated 41 min ago · first seen 11 Sept 2026
model_01M294WWEDDVPC4KVBMXHGH4MK
- Parameters
- 8.29B
- T2 · 3 h ago
- Context
- 128K tokens
- T2 · 3 h ago
- Released
- 16 Apr 2025
- T2 · 41 min ago
- License
- apache-2.0
- T2 · 2 h ago
- Knowledge cutoff
- Jan 2025
- T2 · 3 h ago
Specification
- Release date
- 16 Apr 2025
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- License
- apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Architecture
- Qwen2_5_VLForConditionalGeneration
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Parameters
- 8.29B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Context window
- 128K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Max output
- 2.05K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Knowledge cutoff
- Jan 2025
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Input modalities
- image, text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Output modalities
- text
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Languages
- en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- File size
- 33.2 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hugging Face repo
- ByteDance-Seed/UI-TARS-1.5-7B
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Pipeline tag
- image-text-to-text
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Downloads
- 550,484
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Likes
- 602
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hf inference providers
- featherless-ai
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Last modified
- 2025-04-18T01:35:38+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads all time
- 4,063,108
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 41 min agomedium
- Model type
- qwen2_5_vl
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Openrouter id
- bytedance/ui-tars-1.5-7b
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Supported parameters
- frequency_penalty, logit_bias, logprobs, max_tokens, presence_penalty, repetition_penalty, seed, stop, structured_outputs, temperature, top_k, top_logprobs, top_p
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Tags
- transformers, safetensors, qwen2_5_vl, image-text-to-text, multimodal, gui, en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Weights dtype
- F32
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
32
Source tiers
T232
Freshest observation
41 min ago
Conflicts
None
Modalities
- Modalities
- imagetext
- Input
- imagetext
- Output
- text
Capabilities
Tool calling
No
OpenRouter public model & pricing listing · T2
Structured output
Yes
OpenRouter public model & pricing listing · T2
Reasoning
Unavailable
Vision
Yes
OpenRouter public model & pricing listing · T2
Audio
Unavailable
Fine-tuning available
Unavailable
- Context window
- 128K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Max output
- 2.05K tokens
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Knowledge cutoff
- Jan 2025
Source:OpenRouter public model & pricing listingT2observed 3 h agomedium
- Languages
- en
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
No benchmark results recorded
Current prices
| Provider | Input / 1M | Output / 1M | Cached in | Batch in / out | Context | Observed | Source |
|---|---|---|---|---|---|---|---|
| OpenRouterbytedance/ui-tars-1.5-7b | $0.10 | $0.20 | $0.10 | — | 128K | 1 h ago | openrouter.aiT2 |
USD per 1M tokens as published by each provider (USD). Rows are append-only: every change is kept in the history below.
Available through 1
Price history
Input price · USD / 1M tokens
Output price · USD / 1M tokens
- OpenRouter
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| NVIDIA DGX B200 | 4bit | 1,440 GB | 5.3 GB | Yes |
| Apple M3 Ultra | 4bit | — | 5.3 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 5.3 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 5.3 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 5.3 GB | Yes |
| Apple M2 Ultra | 4bit | — | 5.3 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 5.3 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 5.3 GB | Yes |
| NVIDIA H200 NVL | 4bit | 141 GB | 5.3 GB | Yes |
| Apple M1 Ultra | 4bit | — | 5.3 GB | Yes |
| Apple M3 Max | 4bit | — | 5.3 GB | Yes |
| Apple M4 Max | 4bit | — | 5.3 GB | Yes |
| Mac Studio (Apple M5 Max) | 4bit | — | 5.3 GB | Yes |
| MacBook Pro (Apple M5 Max) | 4bit | — | 5.3 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 5.3 GB | Yes |
| Apple M2 Max | 4bit | — | 5.3 GB | Yes |
| NVIDIA H100 NVL | 4bit | 94 GB | 5.3 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 5.3 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 5.3 GB | Yes |
| Apple M1 Max | 4bit | — | 5.3 GB | Yes |
| Apple M4 Pro | 4bit | — | 5.3 GB | Yes |
| Mac mini (Apple M5 Pro) | 4bit | — | 5.3 GB | Yes |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 5.3 GB | Yes |
| Apple M3 Pro | 4bit | — | 5.3 GB | Yes |
| Apple M1 Pro | 4bit | — | 5.3 GB | Yes |
| Apple M2 Pro | 4bit | — | 5.3 GB | Yes |
| Apple M4 | 4bit | — | 5.3 GB | Yes |
| iMac (Apple M4) | 4bit | — | 5.3 GB | Yes |
| Mac mini (Apple M6) | 4bit | — | 5.3 GB | Yes |
| MacBook Air (Apple M5) | 4bit | — | 5.3 GB | Yes |
| MacBook Pro (Apple M5) | 4bit | — | 5.3 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 5.3 GB | Yes |
| Apple M2 | 4bit | — | 5.3 GB | Yes |
| Apple M3 | 4bit | — | 5.3 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 5.3 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 5.3 GB | Yes |
| Apple M1 | 4bit | — | 5.3 GB | Yes |
No lineage recorded
Papers 8
- arXiv:2504.07981Active35
- arXiv:2404.07972Active35
- arXiv:2409.08264Active35
- arXiv:2401.13919Active35
- arXiv:2504.01382Active35
- arXiv:2405.14573Active35
- arXiv:2410.23218Active35
- arXiv:2501.12326Active35
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
Release daterelease_date2
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 16 Apr 2025 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
| 22 Jul 2025 | → | superseded | OpenRouter public model & pricing listingT2 | medium | deterministic |
Opennessopenness1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| open-weights | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Licenselicense1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| apache-2.0 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Architecturearchitecture1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Qwen2_5_VLForConditionalGeneration | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Parametersparameter_count1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 8.29B | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Context windowcontext_length1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 128K tokens | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Max outputmax_output_tokens1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 2.05K tokens | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Knowledge cutoffknowledge_cutoff1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Jan 2025 | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Modalitiesmodalities1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| image, text | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Input modalitiesmodalities_input1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| image, text | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Output modalitiesmodalities_output1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| text | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Languageslanguages1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| en | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
File sizefile_size_gb1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 33.2 GB | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Hugging Face repohf_repo1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| ByteDance-Seed/UI-TARS-1.5-7B | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Pipeline tagpipeline_tag1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| image-text-to-text | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Model cardmodel_card_url1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Downloadsmetric.downloads1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 550,484 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Likesmetric.likes1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 602 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Descriptiondescription1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 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... | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Gatedgated1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| No | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Hf inference providershf_inference_providers1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| featherless-ai | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Last modifiedlast_modified1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 2025-04-18T01:35:38+00:00 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Library namelibrary_name1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| transformers | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Downloads all timemetric.downloads_all_time1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| 4,063,108 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Model typemodel_type1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| qwen2_5_vl | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Openrouter idopenrouter_id1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| bytedance/ui-tars-1.5-7b | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Structured outputstructured_output1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Supported parameterssupported_parameters1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| frequency_penalty, logit_bias, logprobs, max_tokens, presence_penalty, repetition_penalty, seed, stop, structured_outputs, temperature, top_k, top_logprobs, top_p | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Tool callingtool_calling1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| No | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Visionvision1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| Yes | → current | current | OpenRouter public model & pricing listingT2 | medium | deterministic |
Weights dtypeweights_dtype1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| F32 | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
UI-TARS 7B: release date changed from 2025-04-16 to 2025-07-22
Release date16 Apr 2025→22 Jul 2025openrouterUI-TARS 7B: release date changed from 2025-07-22 to 2025-04-16
Release date22 Jul 2025→16 Apr 2025huggingfaceOpenRouter lists UI-TARS 7B at $0.1 in / $0.2 out per 1M tokens
openrouter
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B | model_page | T2· Quality secondary | 41 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=ByteDance-Seed&p=0&sort=downloads | listing | T2· Quality secondary | 51 min ago | 3 |
| OpenRouter public model & pricing listing | openrouter.ai/api/v1/models | catalogue | T2· Quality secondary | 1 h ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/ByteDance-Seed/UI-TARS-1.5-7B/raw/main/README.md | model_card | T2· Quality secondary | 1 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.