Seed1.5-VL
No estimate
No hardware requirements for this model
The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.
On record
Full specification
Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.
Origin
Who built this model, where, and when it was published.
- Organisation
- ByteDance
- Organisation type
- Industry
- Country
- China
- Published
- 11 May 2025
- Authors
- Dong Guo, Faming Wu, Feida Zhu, Fuxing Leng, Guang Shi, Haobin Chen, Haoqi Fan, Jian Wang, Jianyu Jiang, Jiawei Wang, Jingji Chen, Jingjia Huang, Kang Lei, Liping Yuan, Lishu Luo, Pengfei Liu, Qinghao Ye, Rui Qian, Shen Yan, Shixiong Zhao, Shuai Peng, Shuangye Li, Sihang Yuan, Sijin Wu, Tianheng Cheng, Weiwei Liu, Wenqian Wang, Xianhan Zeng, Xiao Liu, Xiaobo Qin, Xiaohan Ding, Xiaojun Xiao, Xiaoyi…
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision, Language, Multimodal, Video
- Task
- Visual question answering, Video description, Language modeling/generation, Question answering, Character recognition (OCR)
Size
How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.
- Training data
- 3,000,000,000,000 tokens
"more than 3T multimodal data tokens"
Training compute
The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.
- Training compute
- 1.4 × 10²⁴ FLOP
- How it was established
- Hardware
989000000000000 FLOP / GPU / sec [H800, bf16 assumed] * 1300000 GPU-hours [see training time notes] * 3600 sec / hour * 0.3 [assumed utilization] = 1.388556e+24 FLOP
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Training hardware
- NVIDIA H800 SXM5
- Chip-hours
- 1,300,000
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- API access
- Training code
- Unreleased
API (log in and select Doubao-1.5-thinking-vision-pro to experience): https://www.volcengine.com/experience/ark?model=doubao-1-5-thinking-vision-pro-250428 GitHub sample code (Apache 2.0): https://github.com/ByteDance-Seed/Seed1.5-VL
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Likely above 10²³ FLOP
- Yes
- Why it is tracked
- SOTA improvement
- Record confidence
- Confident
Table 6
Sources
Where this record came from and when it was last checked.
- Reference
- Seed1.5-VL Technical Report
- Last updated
- 28 November 2025
What the numbers mean
What this model is
Seed1.5-VL was published by ByteDance, in the country recorded as China, during May 2025. The publishing organisation is categorised as industry.
It works in the domain of Vision, Language, Multimodal, Video, and is recorded as performing the task of visual question answering, Video description, Language modeling/generation, Question answering, Character recognition (OCR).
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Training and provenance
The training run consumed about 1.4 × 10²⁴ FLOP, on hardware recorded as NVIDIA H800 SXM5. That figure measures what producing the model cost, and has no bearing on how fast it answers.
It was trained on a corpus of about 3,000,000,000,000 tokens of text.
It is tracked in the underlying dataset for one reason in particular: sOTA improvement.
Answers
Seed1.5-VL — common questions
Seed1.5-VL— how much compute was used to train it?
Training consumed around 1.4 × 10²⁴ FLOP, on hardware recorded as NVIDIA H800 SXM5. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.
Seed1.5-VL— what GPU do I need to run it?
None. This is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.
Seed1.5-VL— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Seed1.5-VL— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
Seed1.5-VL— who created it?
It was published by ByteDance, based in China, an organisation categorised as industry.
Seed1.5-VL— when was it released?
It was published in May 2025.
Seed1.5-VL— what is it used for?
It works in the domain of Vision, Language, Multimodal, Video, and is recorded as handling the task of visual question answering, Video description, Language modeling/generation, Question answering, Character recognition (OCR). Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
The other direction
Looking at it from the other side?
This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.