One URL change. Full AI governance.
Point your existing SDK at the Arbitex gateway. DLP inspection, policy enforcement, and tamper-proof audit logging activate immediately — no application rewrites.
Up and running in three steps
No custom SDK. No application rewrites. Works with any OpenAI-compatible library.
Point your SDK at the gateway
Change one line in your existing code. Arbitex exposes an OpenAI-compatible API — swap your base URL and every AI call flows through the gateway. No custom SDK, no application rewrites.
Works with any OpenAI-compatible library. Python, Node, curl, or any HTTP client.
Send a request
Your existing prompts and model calls go through unchanged. The gateway inspects every request and response in real time — applying your configured DLP policies, routing rules, and compliance bundle requirements.
No latency added for most requests. Policy enforcement runs in-path at the edge.
See it in the audit log
Every request generates a tamper-evident audit record — tamper-proof, OCSF-formatted, and available for export to your SIEM. Compliance evidence packs for PCI-DSS, HIPAA, SOX, and seven other frameworks are generated automatically.
Audit records are available immediately. Export to Splunk, Sentinel, or Elastic on demand.
curl https://api.arbitex.ai/v1/chat/completions \
-H "Authorization: Bearer $ARBITEX_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"messages": [
{"role": "user", "content": "Summarize this vendor contract."}
]
}'import httpx
client = httpx.Client(
base_url="https://api.arbitex.ai/v1",
headers={"Authorization": f"Bearer {api_key}"},
)
response = client.post("/chat/completions", json={
"model": "gpt-4o",
"messages": [
{"role": "user", "content": "Summarize this vendor contract."}
],
})
data = response.json()const response = await fetch(
"https://api.arbitex.ai/v1/chat/completions",
{
method: "POST",
headers: {
"Authorization": `Bearer ${process.env.ARBITEX_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "gpt-4o",
messages: [
{ role: "user", content: "Summarize this vendor contract." }
],
}),
}
);
const data = await response.json();How onboarding works
Most organizations are in production within one week of their discovery call.
Discovery Call
We learn your compliance requirements, existing AI stack, and deployment constraints to scope the right configuration.
Environment Setup
Your Arbitex tenant is provisioned, SSO is connected, and your first API key is issued — typically completed within one business day.
Policy Configuration
An Arbitex engineer works with your team to activate the right DLP tiers, compliance bundles, and routing rules for your workflows.
Go Live
Point your SDK at the gateway, validate requests in the audit log, and move to production with a dedicated support contact on standby.
Choose your plan
All plans include the full DLP pipeline, audit logging, and multi-provider routing. Compare all plan features →
Team
Typical for teams deploying AI tools and internal applications.
- 250K requests / month + overage
- 9 providers + BYOE
- DLP: Regex + secret detection
- SSO (SAML 2.0)
- 30-day audit log retention
- Email support
SMB
For businesses with multiple AI-integrated workflows that need complete control.
- 2M requests / month
- 9 providers + BYOE
- Full 3-tier DLP pipeline with AI entity recognition
- Response inspection & filtering
- Compare & Summarize routing modes
- Budget caps & usage quotas
- Compliance bundle activation
- 90-day audit log retention
- SCIM 2.0 + WebAuthn/FIDO2
- MCP Server
- Config versioning & rollback
- Webhooks + SIEM export
- Email & phone support (9×5)
Enterprise
For regulated industries, large deployments, and organizations that need the Hybrid Outpost.
- Unlimited requests
- 9 providers + BYOE
- Full 3-tier DLP pipeline with AI entity recognition
- Hybrid Outpost (data plane in your VPC)
- Custom compliance bundle configuration
- WebAuthn / FIDO2 + SCIM 2.0
- Configurable audit log retention
- SIEM direct sink (Splunk / Sentinel / Elastic)
- Dedicated onboarding + implementation support
- Enterprise MSA + SLA
All plans are custom-quoted based on your organization's requirements. Talk to an Arbitex engineer to get a proposal tailored to your deployment. Contact us at [email protected] →
Request a demo
Tell us about your environment and an Arbitex engineer will reach out to schedule a tailored walkthrough.