Ling 3.0 Flash Sante — Free Health-Focused MoE Model on OpenRouter

What shipped

InclusionAI's Ling 3.0 Flash Sante, a health and medicine-focused mixture-of-experts model, is now available on OpenRouter at no cost under the inclusionai/ling-3.0-flash-sante:free endpoint.

What changed

Ling 3.0 Flash Sante is built on InclusionAI's Ling 3.0 Flash architecture: 5.1B active parameters out of 124B total with a 256K token context window and 32K max output tokens. It supports tools, reasoning, logprobs, frequency/presence penalties, and top-k/top-p sampling. The :free tier costs $0 per request and sits alongside the paid tier at InclusionAI's standard pricing. This is the second domain-specific Ling variant on OpenRouter after Ling 3.0 Flash Fin (Finnish language).

Why a builder cares

Free access to a medical-domain MoE model with 256K context means you can prototype health chatbots, clinical summarizers, medical RAG pipelines, and pharma research tools without any upfront inference cost. The tool-calling support also makes it usable for agentic healthcare workflows.