Ling 3.0 Flash Sante

NetGuide's September 8, 2026 coverage reports that Ant Group's inclusionAI lab unveiled Ling 3.0 Flash Sante on September 4, 2026 as a medicine-focused variant of its open-weight language model, currently available only through API access. The article details the underlying Ling 3.0 Flash architecture as a mixture-of-e The piece notes that while the base Ling 3.0 Flash ships under an MIT licence on Hugging Face with an Artificial Analysis Intelligence Index around 38 at more than 300 tokens per second, InclusionAI has not released weights for the Sante variant, which runs exclusively via provider APIs. It flags the vendor-cited Diagn

Lookonchain's September 5, 2026 report confirms that Ant Group's Lingbao AI launched the medical health model Ling-3.0-flash-Sante, built on Ling-3.0-flash with enhanced medical capabilities using a Mixture of Experts architecture of 124B total parameters with 5.1B activated per token. Key capabilities cited include me The report explicitly states that Sante is now integrated with OpenRouter and Vercel, with free access available, confirming the Vercel AI Gateway serving route for this model. These benchmark figures originate from vendor-published material and have not been independently verified, consistent with the model-focused st

Vercel's AI Gateway changelog confirms that Ling 3.0 Flash Sante from InclusionAI is available on AI Gateway and free to use through October 4, 2026. The post explicitly names the model as a health and medicine-focused Mixture-of-Experts variant of Ling 3.0 Flash, with 124B total parameters, about 5.1B active parameter The changelog entry describes Ling 3.0 Flash Sante as built for medical reasoning, professional healthcare tasks, deep research, evidence-based retrieval, and multi-step medical workflows, while retaining the base model's general reasoning, coding, and agentic capabilities. Two model IDs are offered: the standard inclu

The OpenRouter listing for inclusionAI's Ling 3.0 Flash (released Jul 23, 2026) explicitly names Ling 3.0 Flash Sante as a sibling text model in the inclusionAI Ling 3.0 Flash family. Sante is described as a health and medicine-focused mixture-of-experts model built on the Ling 3.0 Flash base, sharing the same architec According to the same page's expanded description, Ling 3.0 Flash Sante targets medical knowledge reasoning, clinical safety, evidence-based retrieval, and long-horizon medical tasks while retaining general capabilities in reasoning, coding, and agentic workflows. The evidence confirms Sante's existence as a distinct,

The OpenRouter product page for Ling 3.0 Flash Sante documents InclusionAI's health and medicine-focused mixture-of-experts model built on Ling 3.0 Flash, with 5.1B active parameters out of 124B total. The page confirms a 262K-token context window, a release date of September 4, 2026, and lists the model as serving bot Hosting telemetry on the OpenRouter page indicates the model is served via NovitaAI with reported latency and throughput figures and an uptime of 100%, establishing baseline infrastructure observability for the integration. Per Vercel AI Gateway focus rules, gateway-level pricing and availability details are not used a