Odaily Planet Daily News According to the DeepSeek official account, DeepSeek has launched a multimodal visual understanding model, V4-Flash-Vision-Exp, and opened API services.
Built on V4-Flash, this model adds image understanding and visual generation capabilities. It supports multimodal input and output such as text and images, and provides developers with callable interfaces for inference, generation, and other abilities.
Built on V4-Flash, this model adds image understanding and visual generation capabilities. It supports multimodal input and output such as text and images, and provides developers with callable interfaces for inference, generation, and other abilities.