+
+
+
+
Try AI Gateway

Every AI request, under your control.

One endpoint for 100+ models. AI control, security, observability, and monetization.
OpenAI-compatible API. Fast setup. No rewrite.

Supported Providers

Browse all 100+ models
+
+
+
+

Everything in one gateway

AI Gateway combines six essential capabilities into one unified solution.

+
+

Multi-Provider Routing

14+ providers, one API

Route requests to OpenAI, Anthropic, Google, Mistral, Meta, and more through a single unified API.

  • OpenAI-compatible API
  • Automatic fallback
  • Model equivalence mapping

AI Security

Production-grade protection

Real-time protection against prompt injection, PII leakage, and harmful content.

  • Prompt injection detection
  • PII scanning
  • Content filtering

Full Observability

See everything

Complete visibility into every AI request. Logs, analytics, latency, and cost tracking.

  • Request/response logging
  • P50/P90/P99 latency
  • Cost per request

Developer Platform

Ship faster

TypeScript and Python SDKs, Vercel AI SDK integration, API key management.

  • TypeScript & Python SDKs
  • Vercel AI SDK provider
  • Rate limiting

Compliance Ready

Enterprise-grade audit

Full audit trail, security incident logging, and data governance policies.

  • Audit logs
  • Security incidents
  • Policy enforcement

End-User Billing

Monetize AI usage

Meter, limit, and charge your users for AI consumption. Stripe Connect native with markup pricing.

  • Per-user metering
  • Rate plan enforcement
  • Stripe Connect payouts
+
+
+
+

Universal AI Gateway

Connect any client to any model with a single, secure API.

Client Request
Cencori
OpenAI
Claude
Gemini
+
+
+
+

Integrate in 3 lines

Drop-in replacement for your existing OpenAI calls. Switch providers with one parameter.

1
Install the SDK
2
Add your API key
3
Start making requests
cencori.ts
import { Cencori } from 'cencori';

const cencori = new Cencori({
  apiKey: process.env.CENCORI_API_KEY
});

const response = await cencori.ai.chat({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }]
});
+
+
+
+
14+
Providers Supported
<50ms
Added Latency
99.9%
Uptime SLA
100+
Models Available
+
+
+
+

The only AI gateway
that makes you money.

Every other gateway stops at routing. Cencori closes the loop with native monetization, budgets, and direct payouts — no extra plumbing, no revenue leakage.

Zero-latency margin calculator

Set percentage markups or flat fees per model. The math is calculated on the fly as payloads pass through the gateway.

Hard edge quota enforcement

Define strict token, request, or dollar limits per user. When limits are exceeded, Cencori blocks requests with a neat 429 at the edge, keeping your API bills safe.

Direct Stripe Connect payouts

Link your Stripe account once. Invoices are dispatched, funds are collected, and payouts land directly in your account. Cencori never touches the money.

Stripe Connect: Connected
acct_cencori_19a
+100%
Cost (0%)100%300%
Raw API Cost$5.00per 1M tokens
Retail Price Charged$10.00per 1M tokens
Gross Margin50%
Your Margin Profit+$5.00/1M
3. Pass User Context in Header
const response = await cencori.ai.chat({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: '...' }],
  user: 'user_123' // Meters & limits instantly
});

Every request meters token counts and charges user balance automatically at the network edge.

+
+
+
+

Controls

Set limits before costs drift.
Not after the spike.

Hard spend caps

Set limits that actually stop traffic when a budget is reached, so one broken workflow does not become an expensive incident.

Budget alerts

Get warned before you hit the threshold, with alerts designed for teams managing production and staging separately.

End-user billing

Allocate AI costs downstream with cleaner billing controls for products that need customer-level usage accounting.

Project-level control

Set different rules for production, staging, and internal tools so your budget policy matches how the organization actually works.

+
+
+
+

Build Different.

The intelligence era is here. The infrastructure is Cencori.