Verified by us: this deal no longer works.
100% of the community still says it works — but we checked, and it's dead.
The free period for Ling 3.0 Flash Sante on Vercel AI Gateway ended on October 4, 2026. The model is now billed at standard rates, about $0.075 per million input tokens and $0.22 per million output tokens, and the -free model ID is no longer listed.
The briefing

The free period for Ling 3.0 Flash Sante on Vercel AI Gateway ended on October 4, 2026. Starting October 5,
inclusionai/ling-3.0-flash-santeis billed at standard rates, about $0.075 per million input tokens and $0.22 per million output tokens, andinclusionai/ling-3.0-flash-sante-freeis no longer in the model list.
The free inclusionai/ling-3.0-flash-sante:free variant on OpenRouter has also been removed. Only the paid inclusionai/ling-3.0-flash-sante remains.
Specs and capabilities
Ling 3.0 Flash Sante is InclusionAI's healthcare-focused version of Ling 3.0 Flash, built for medical reasoning, research, evidence retrieval, and multi-step medical tasks while keeping general reasoning, coding, and agent abilities. It can help with research and lookups but does not replace a licensed clinician.
It is a mixture-of-experts model with about 124B total parameters and about 5.1B active per token, a 256K context window, up to 32K output tokens, and function calling support.
How to use it now
To keep using it on Vercel AI Gateway, set the model to inclusionai/ling-3.0-flash-sante. Usage is billed at the live price on the model page.
import { streamText } from 'ai';
const result = streamText({
model: 'inclusionai/ling-3.0-flash-sante',
prompt: 'Compare the evidence in these abstracts and identify where they disagree.',
});
For OpenAI-compatible clients, set the base URL to https://ai-gateway.vercel.sh/v1 and call it with your AI Gateway API key using the same model name.
