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.

Available Endpoints

Endpoint	Description	Providers
`/api/ai/chat`	Chat completions	OpenAI, Anthropic, Google, xAI, Mistral, DeepSeek, Meta
`/api/ai/embeddings`	Vector embeddings	OpenAI, Google, Cohere
`/api/ai/images/generate`	Image generation	OpenAI, Google
`/api/ai/audio/transcriptions`	Speech-to-text	OpenAI
`/api/ai/audio/speech`	Text-to-speech	OpenAI
`/api/ai/moderation`	Content moderation	OpenAI
`https://api.cencori.com/v1/chat/completions`	OpenAI-compatible chat endpoint	OpenAI-compatible clients

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

SDK Usage

Codetext

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 }

Streaming

Codetext

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);
}

Tool Calling

Codetext

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);

Direct API Usage

Native Cencori Endpoint

Codetext

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

Codetext

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!"}]
  }'

Authentication

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 provider access in Project > Providers or choose a model from an enabled provider.