Cencori ships a first-party provider for the Vercel AI SDK. Use it when you want Vercel's chat and streaming primitives with Cencori's routing, security, and observability behind the model call.

Installation

Codetext

npm install ai cencori

Environment

Codetext

# .env.local
CENCORI_API_KEY=csk_live_...

Recommended Setup

Create a shared provider export for your server code:

Codetext

// lib/cencori.ts
import { cencori } from 'cencori/vercel';
 
export { cencori };

If you need custom provider settings, use createCencori() instead:

Codetext

import { createCencori } from 'cencori/vercel';
 
export const cencori = createCencori({
  apiKey: process.env.CENCORI_API_KEY!,
});

Route Handler

Codetext

// app/api/chat/route.ts
import { streamText } from 'ai';
import { cencori } from '@/lib/cencori';
 
export async function POST(req: Request) {
  const { messages, model = 'gpt-4o' } = await req.json();
 
  const result = streamText({
    model: cencori(model),
    messages,
  });
 
  return result.toDataStreamResponse();
}

React Chat UI

Codetext

// app/page.tsx
'use client';
 
import { useChat } from 'ai/react';
 
export default function Chat() {
  const { messages, input, handleInputChange, handleSubmit } = useChat({
    api: '/api/chat',
    body: {
      model: 'gpt-4o',
    },
  });
 
  return (
    <div>
      {messages.map((message) => (
        <div key={message.id}>
          {message.role}: {message.content}
        </div>
      ))}
 
      <form onSubmit={handleSubmit}>
        <input value={input} onChange={handleInputChange} />
      </form>
    </div>
  );
}

Text Generation

Codetext

import { generateText } from 'ai';
import { cencori } from '@/lib/cencori';
 
const result = await generateText({
  model: cencori('gemini-2.5-flash'),
  prompt: 'Write a haiku about AI infrastructure.',
});
 
console.log(result.text);

Switching Models

Codetext

await generateText({
  model: cencori('gpt-4o'),
  prompt: 'Hello',
});
 
await generateText({
  model: cencori('claude-sonnet-4.5'),
  prompt: 'Hello',
});
 
await generateText({
  model: cencori('gemini-2.5-flash'),
  prompt: 'Hello',
});

When To Use The OpenAI-Compatible Base URL

If a library expects an OpenAI-compatible baseURL and apiKey instead of a first-party provider, use:

baseURL: https://api.cencori.com/v1
apiKey: your Cencori project key (csk_...)

Use cencori/vercel when you are already inside the Vercel AI SDK.