Overview
JoyAI VL Interaction is a multimodal model from JD. It accepts text, image and video input and returns text, so a single request can pair a written question with pictures or clips and receive a written answer. It is billed per token, with separate rates for input and output.
It accepts text, image and video input and returns text.
Capabilities
JoyAI VL Interaction accepts text, image and video input and returns text. Its output modality is text.
Because it reads images and video alongside a prompt, a single request can carry both the media and the question about it.
Pricing
JoyAI VL Interaction is priced at $0.0714 per 1M input tokens and $0.2857 per 1M output tokens.
JoyAI VL Interaction is available through RealRelay's OpenAI-compatible API.
Use cases
Use JoyAI VL Interaction for question answering over images and video, such as describing a photo, reading a screenshot or summarizing a clip.
Its text output suits assistants and review tools that answer questions about uploaded media and pass the answer to other systems, for example a ticketing or moderation queue.
What is JoyAI VL Interaction?
JoyAI VL Interaction is a JD multimodal model that accepts text, image and video input and returns text.
How much does JoyAI VL Interaction cost?
JoyAI VL Interaction is priced at $0.0714 per 1M input tokens and $0.2857 per 1M output tokens.
What inputs and outputs does JoyAI VL Interaction support?
JoyAI VL Interaction accepts text, image and video input and returns text.
Can JoyAI VL Interaction process images and video?
Yes. JoyAI VL Interaction accepts text, image and video input and returns a text answer.
How do I call JoyAI VL Interaction via the API?
Send requests to RealRelay's OpenAI-compatible API with the model ID jd/joyai-vl-interaction to use JoyAI VL Interaction.