Ask about visual content
Pair an image or short video with a specific question.
MOSS VLBeta
MOSS VL: AI Image & Video Understanding
Understand images and short videos with MOSS VL. Ask about visual details, summarize a scene or explore information inside a picture. Beta availability varies.
From 2 credits / requestProvider unavailable
Your output
A little input. A new possibility.
Your finished audio, image or text will appear here.
01 / Inside the model
Look closer. Ask a better question.
MOSS VL is a vision-language model for understanding images and video alongside text. The official project describes document reading, OCR, multi-image reasoning and temporal video understanding in Chinese and English. This page previews our question-and-upload workflow. The upstream API is currently unavailable for this integration, so generation is disabled and no credits are charged.
Read beyond the picture
The official model covers text recognition and document understanding.
Reason over time
The model family also studies events and relationships across video frames.
02 / Examples & listening room
Explore the official modelSee it. Hear it. Get a feel for it.
Official examples are credited to OpenMOSS. Studio samples were generated by us with the named API model. These are saved previews, not a result of your current settings. Research capabilities and available studio controls may differ.
Watching, reasoning and responding
Official MOSS-VL family video · original multilingual content03 / Use cases
Where it fits.
Document exploration
Ask about a chart, screenshot or page layout when the service becomes available.
Scene understanding
Explore questions about visible objects, actions and relationships.
04 / Questions
A few things worth knowing.
Can I use MOSS VL right now?
No. The upstream model is unavailable to this integration. The form is disabled and cannot charge credits.
What is the configured rate?
The configured rate is 2 credits per image request or 6 credits for a video up to 60 seconds, once the integration is available.
Is visual understanding the same as image generation?
No. VL analyses visual input and returns an answer; Image Base and SFT generate new pictures from text.
Made for your next idea
Choose a model, add your input and review the credit cost. Successful results stay in your account history; AI output may be inaccurate.
Text is rounded up to a whole credit. Audio is billed per started minute. Live voice uses one credit per 6 seconds.
Failed tasks are refunded automatically.
Result links can expire. Download files you want to keep.
Model documentation