Ling 3.0 Flash Sante is now available on AI Gateway for free
Vercel has integrated the inclusionAI Ling 3.0 Flash Sante model into its AI Gateway platform. The model is available for free usage until October 4, 2024, via two specific model IDs.
Verified State Diff
Impact & Verification Analysis
Healthcare software developers, medical AI researchers, and enterprise teams building clinical decision support or medical documentation tools.
This release provides specialized medical-grade AI infrastructure with enterprise-ready features like Zero Data Retention and unified API management, lowering the barrier to entry for deploying high-parameter, domain-specific models in regulated environments.
Full Fact Overview
The Ling 3.0 Flash Sante model is a Mixture-of-Experts (MoE) architecture featuring 124B total parameters, 5.1B active parameters per token, and a 256K token context window. It is specifically optimized for medical reasoning, healthcare workflows, and evidence-based retrieval while maintaining general-purpose coding and agentic capabilities. Vercel's AI Gateway implementation allows for unified API access, including features like custom reporting, Zero Data Retention, and routing rules. Users can choose between 'inclusionai/ling-3.0-flash-sante' (which triggers billing post-October 4) or 'inclusionai/ling-3.0-flash-sante-free' (which ceases operation post-October 4) to manage cost exposure.