Using Ling 3.0 Flash Santé on Vercel AI Gateway
Implementation guide · Ling 3.0 · InclusionAI
Serverless
Vercel AI Gateway exposes Ling 3.0 Flash Santé through model ID inclusionai/ling-3.0-flash-sante. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-09-07. Next refresh: weekly.
Quick Start
- 1
- 2Use the Vercel AI Gateway SDK or REST API to call
inclusionai/ling-3.0-flash-sante— see the documentation for request format. - 3
Code Examples
Install
pip install openaiAPI key
AI_GATEWAY_API_KEYModel ID
inclusionai/ling-3.0-flash-santecreator/model-name e.g. kwaipilot/kat-coder-pro-v2
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="inclusionai/ling-3.0-flash-sante",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Pricing on Vercel AI Gateway
| Type | Price (per 1M) |
|---|---|
| Input tokens | Free |
| Output tokens | Free |
Capabilities
ReasoningJSON / Tool useStructured Outputs
About Ling 3.0 Flash Santé
Ling-3.0-flash-Santé is InclusionAI's health/medicine domain fine-tune of Ling-3.0-flash (124B total / 5.1B active, 262K context). Proprietary API checkpoint — not MIT — with weights not released on Hugging Face; listed on ModelScope (inclusionAI/Ling-3.0-Flash-Sante). Served via OpenRouter inclusionai/ling-3.0-flash-sante:free and Vercel AI Gateway.
Model Specs
Released2026-09-04
Parameters124B (5.1B activated)
Context262k
ArchitectureMixture of Experts