Model and Inference / TOKEN WIKI
The capabilities of the
multi-modal model The
In one sentence
multi-modal model can handle multiple forms of information such as text, images, audio or video, and the specific support range varies by model.
Why it matters
file format, input size, quality and billing methods may change product experience and cost.
Practical considerations
tests task effects based on real media samples and verifies supported formats, restrictions, and different modes of billing. Can the
FAQ
multimodal model handle all media?
No, you need to check the input and output modes supported by the specific model item by item.
