Cencori

The unified infrastructure layer for AI applications.

One SDK. Every AI primitive. Always secure. Always logged.

npm install cencori

Quick Start

import { Cencori } from 'cencori';

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

// AI Gateway - Chat with any model
const response = await cencori.ai.chat({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }]
});

console.log(response.content);

Products

| Product | Status | Description | |---------|--------|-------------| | AI Gateway | ✅ Available | Multi-provider routing, security, observability | | Billing | ✅ Available | End-user usage monetization and Stripe integration | | Integration | ✅ Available | SDKs, Vercel AI, TanStack |

AI Gateway

Chat Completions

const response = await cencori.ai.chat({
  model: 'gpt-4o', // or 'claude-3-opus', 'gemini-1.5-pro', etc.
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What is the capital of France?' }
  ],
  temperature: 0.7,
  maxTokens: 1000
});

console.log(response.content);
console.log(response.usage); // { promptTokens, completionTokens, totalTokens }

Multimodal (Image Input)

const response = await cencori.ai.chat({
  model: 'gpt-4o',
  messages: [{
    role: 'user',
    content: [
      { type: 'text', text: 'What is in this image?' },
      { type: 'image_url', image_url: { url: 'https://example.com/image.jpg' } }
    ]
  }]
});

Tool Usage (Function Calling)

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 the current weather for a location',
      parameters: {
        type: 'object',
        properties: { location: { type: 'string' } },
        required: ['location']
      }
    }
  }]
});

if (response.toolCalls) {
  console.log(response.toolCalls); // [{ function: { name: 'get_weather', arguments: '{"location":"Tokyo"}' } }]
}

Structured Output (Object Generation)

interface UserProfile {
  name: string;
  age: number;
  interests: string[];
}

const response = await cencori.ai.generateObject<UserProfile>({
  model: 'gpt-4o',
  prompt: 'Generate a fictional user profile',
  schema: {
    type: 'object',
    properties: {
      name: { type: 'string' },
      age: { type: 'number' },
      interests: { type: 'array', items: { type: 'string' } }
    },
    required: ['name', 'age', 'interests']
  }
});

console.log(response.object); // { name: 'Alice', age: 28, interests: ['hiking'] }

Embeddings

const response = await cencori.ai.embeddings({
  model: 'text-embedding-3-small',
  input: 'Hello world'
});

console.log(response.embeddings[0]); // [0.1, 0.2, ...]

Image Generation

Generate images from text prompts using multiple providers:

const response = await cencori.ai.generateImage({
  prompt: 'A futuristic city at sunset with flying cars',
  model: 'gpt-image-1.5',  // Best text rendering, top ELO rating
  size: '1024x1024',
  quality: 'hd'
});

console.log(response.images[0].url); // https://...

Supported Models: | Provider | Models | Description | |----------|--------|-------------| | OpenAI | gpt-image-1.5, gpt-image-1, dall-e-3, dall-e-2 | Text rendering, creative | | Google | gemini-3-pro-image, imagen-3 | High photorealism |

Framework Integrations

Vercel AI SDK

import { cencori } from 'cencori/vercel';
import { streamText } from 'ai';

const result = await streamText({
  model: cencori('gpt-4o'),
  messages: [{ role: 'user', content: 'Hello!' }]
});

for await (const chunk of result.textStream) {
  console.log(chunk);
}

With React/Next.js

import { cencori } from 'cencori/vercel';
import { useChat } from '@ai-sdk/react';

export default function Chat() {
  const { messages, input, handleInputChange, handleSubmit } = useChat({
    api: '/api/chat'
  });
  
  return (
    <div>
      {messages.map(m => <div key={m.id}>{m.content}</div>)}
      <form onSubmit={handleSubmit}>
        <input value={input} onChange={handleInputChange} />
      </form>
    </div>
  );
}

Why Cencori?

• 🛡️ Security Built-in: PII detection, content filtering, jailbreak protection
• 📊 Observability: Every request logged, every token tracked
• 💰 Cost Control: Budget alerts, spend caps, per-request costing
• 🔄 Multi-Provider: Switch between OpenAI, Anthropic, Google, etc.
• ⚡ One SDK: AI model routing, security shield, and billing - unified

Links

• Documentation
• Dashboard
• GitHub

License

MIT