Vercel AI SDK with Meridian

Drop-in OpenAI-compatible provider for the Vercel AI SDK. Route through Meridian to get unified billing, rate limiting, and model access control.

Quick start

npm install ai @ai-sdk/openai

import { createOpenAI } from '@ai-sdk/openai';
import { generateText } from 'ai';

const meridian = createOpenAI({
  apiKey: 'nim_live_***',
  baseURL: 'https://meridian.getnimbus.net/api/v1',
});

const { text } = await generateText({
  model: meridian('azure-swc/gpt-4.1'),
  prompt: 'hello',
});

Edge / streaming with streamText

Use streamText for real-time token streaming. Works on Edge runtime when you set export const runtime = 'edge'.

import { createOpenAI } from '@ai-sdk/openai';
import { streamText } from 'ai';

export const runtime = 'edge';

const meridian = createOpenAI({
  apiKey: 'nim_live_***',
  baseURL: 'https://meridian.getnimbus.net/api/v1',
});

export async function POST(req: Request) {
  const { prompt } = await req.json();

  const result = streamText({
    model: meridian('azure-swc/gpt-4.1'),
    prompt,
  });

  return result.toDataStreamResponse();
}