Point your LLM SDK at this gateway instead of the direct API endpoint:

# Python / OpenAI SDK
from openai import OpenAI
client = OpenAI(
    base_url="http://localhost:7860/v1",
    api_key="gw-demo-key-1234"  # gateway key, not your real OpenAI key
)

# cURL
curl -X POST http://localhost:7860/v1/chat/completions \
  -H "Authorization: Bearer gw-demo-key-1234" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o","messages":[{"role":"user","content":"Hello"}]}'
        

The gateway redacts sensitive data before the request reaches OpenAI / Anthropic. Your real API keys stay server-side.