Total Requests
—
last 24h
Allowed
—
passed through
Blocked
—
policy violations
Redacted
—
sensitive data cleaned
Avg Latency
—
proxy overhead
Audit Events
| Timestamp | Request ID | Tenant | Model | Action | Policy | Rules | Latency |
|---|
◇
No audit events yet
Send a request through the proxy to see events here
curl -X POST https://sentinelgate.polsia.app/v1/chat/completions ...
Active Policy
Loading...
Integration Guide
Point your OpenAI SDK at SentinelGate
// Just change the base URL — that's it
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://sentinelgate.polsia.app/v1',
apiKey: process.env.OPENAI_API_KEY,
defaultHeaders: {
'X-Tenant-Id': 'my-team'
}
});
// Use as normal — SentinelGate proxies to OpenAI
const res = await client.chat.completions.create({
model: 'gpt-4o',
messages: [{ role: 'user', content: 'Hello!' }]
});
Or use curl
# Every request is audited and policy-checked
curl -X POST https://sentinelgate.polsia.app/v1/chat/completions \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "X-Tenant-Id: my-team" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-4o","messages":[{"role":"user","content":"Hello"}]}'
# Check response headers for audit info:
# X-SentinelGate-Request-Id: sg-17108...
# X-SentinelGate-Policy: default
# X-SentinelGate-Action: allow