AI Gateway

The AI Gateway is Cencori's runtime control point. Your application sends AI traffic to Cencori once, and Cencori handles provider routing, security enforcement, observability, and cost tracking.

Use https://api.cencori.com/v1 as the base URL for OpenAI-compatible SDKs. Most SDKs append /chat/completions automatically.

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: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'Hello!' },
  ],
  temperature: 0.7,
  maxTokens: 1000,
});
 
console.log(response.content);
console.log(response.usage); // { promptTokens, completionTokens, totalTokens }

const stream = cencori.ai.chatStream({
  model: 'claude-opus-4',
  messages: [{ role: 'user', content: 'Tell me a story' }],
});
 
for await (const chunk of stream) {
  process.stdout.write(chunk.delta);
}

const response = await cencori.ai.chat({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'What is the weather in Tokyo?' }],
  tools: [
    {
      type: 'function',
      function: {
        name: 'get_weather',
        description: 'Get weather for a location',
        parameters: {
          type: 'object',
          properties: { location: { type: 'string' } },
          required: ['location'],
        },
      },
    },
  ],
});
 
console.log(response.toolCalls);

Native Cencori Endpoint

curl -X POST https://cencori.com/api/ai/chat \
  -H "CENCORI_API_KEY: csk_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": false
  }'

OpenAI-Compatible Endpoint

curl -X POST https://api.cencori.com/v1/chat/completions \
  -H "Authorization: Bearer csk_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Every request requires a project API key:

• Preferred for /api/ai/*: CENCORI_API_KEY: csk_...
• Preferred for https://api.cencori.com/v1/*: Authorization: Bearer csk_...

Create and manage project keys in the dashboard. If authentication succeeds but routing fails with a provider configuration error, add your provider key in AI Gateway → BYOK or choose a model from an enabled provider.

The gateway's only built-in request check is PII protection. It applies the same way to managed keys and BYOK, streaming and non-streaming, native and OpenAI-compatible endpoints.

• Default: off. Requests pass through unchanged and return 200 OK, even if they contain personal data. This is expected, not a bypass.
• To turn it on: open the project's Settings → General, and under Request handling turn on PII protection (paid plans).
• When on: any email address, phone number, US SSN, or card number in the input blocks the request with 403 security_violation. Nothing is masked — the request is either blocked or passed through unchanged. Model responses are not scanned.
• Bypass: passthrough: true / fast_lane: true body fields, or x-cencori-passthrough: true / x-cencori-fast-lane: true headers, skip the check on chat requests.

If you test with an email or card number and get 200 OK, check whether PII protection is on for the project before assuming a provider-key (BYOK) issue.