Ant launches Ling-3.2-flash multimodal model with million-token context

Ant Group released Ling-3.2-flash on November 5, a native multimodal model that accepts text, images, and video with 560 billion total parameters and 25 billion activated per inference step. The model supports a one-million-token context window and is available through an online chat interface and APIs compatible with OpenAI and Anthropic protocols, with free access for the first two weeks after launch. Ant says Ling-3.2-flash targets complex visual understanding, multistep agent tasks, 3D understanding and interaction, and medical multimodal applications.

Ant Group released Ling-3.2-flash on November 5, adding a native multimodal model that accepts text, images, and video. The model has 560 billion total parameters, activates 25 billion per inference step, and supports a one-million-token context window. Ant says the model focuses on complex visual understanding, multistep agent tasks, 3D understanding and interaction, and medical multimodal applications. It is available through an online chat interface and APIs compatible with OpenAI and Anthropic protocols, with free access for the first two weeks after launch. Ant Ling https://developer.ant-ling.com/en/docs/getting-started/changelog