InclusionAI launches Ling-3.0-flash-Sante, a 124B medical MoE that activates 5.1B parameters

InclusionAI, Ant Group's model lab, has launched Ling-3.0-flash-Sante, a health-and-medicine Mixture-of-Experts model that activates about 5.1 billion parameters per token from a 124 billion-parameter Ling-3.0-flash backbone and is free to call on OpenRouter and Vercel AI Gateway. Named after the French word *sante* (health), the model is aimed at medical knowledge reasoning, professional healthcare tasks, deep research, evidence-based retrieval, and long-horizon clinical workflows, while keeping the base model's general reasoning, coding, and agent skills.