Integrations

Vercel AI SDK

Connect DEVUP AI to the Vercel AI SDK using the official devupai/ai provider. Build generative AI applications in Next.js and Node.js with text generation, streaming, tool calling, and streaming route handlers.

Prerequisites

A DEVUP AI account with a valid API key (Dashboard → API Keys).
Node.js 22.0.0 or later.

Installation

Install the DEVUP AI SDK, the Vercel AI SDK core library, the OpenAI-compatible adapter, and Zod:

npm install devupai ai @ai-sdk/openai-compatible zod

Create the provider

Initialize the provider instance by importing createDevupAI from devupai/ai:

import { createDevupAI } from "devupai/ai";

const devupai = createDevupAI({
  apiKey: process.env.DEVUP_API_KEY,
});

generateText

Generate non-streaming text completions using generateText:

import { createDevupAI } from "devupai/ai";
import { generateText } from "ai";

const devupai = createDevupAI({
  apiKey: process.env.DEVUP_API_KEY,
});

const { text } = await generateText({
  model: devupai("deepseek-ai/DeepSeek-V4-Pro"),
  prompt: "Say hello in one word.",
});

console.log(text.trim());

streamText

Stream tokens in real time using streamText and iterate over textStream:

import { createDevupAI } from "devupai/ai";
import { streamText } from "ai";

const devupai = createDevupAI({
  apiKey: process.env.DEVUP_API_KEY,
});

const result = streamText({
  model: devupai("deepseek-ai/DeepSeek-V4-Pro"),
  prompt: "Count from 1 to 3.",
});

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

Tool calling

Define typed tools with Zod schemas and resolve responses across multi-step execution rounds:

import { createDevupAI } from "devupai/ai";
import { generateText, tool, stepCountIs } from "ai";
import { z } from "zod";

const devupai = createDevupAI({
  apiKey: process.env.DEVUP_API_KEY,
});

const getWeather = tool({
  description: "Get the current weather for a city",
  inputSchema: z.object({
    city: z.string().describe("The name of the city"),
  }),
  execute: async ({ city }) => {
    return { city, temperature: "22C" };
  },
});

const result = await generateText({
  model: devupai("deepseek-ai/DeepSeek-V4-Pro"),
  prompt: "What is the weather in Algiers? Use the get_weather tool.",
  tools: { get_weather: getWeather },
  stopWhen: stepCountIs(2),
});

console.log("Tool called:", result.toolCalls[0].toolName);
console.log("Final text:", result.text.trim());

Next.js route handler

Return a streaming HTTP response from an App Router API route handler using toTextStreamResponse:

import { createDevupAI } from "devupai/ai";
import { streamText } from "ai";

const devupai = createDevupAI({
  apiKey: process.env.DEVUP_API_KEY,
});

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

  const result = streamText({
    model: devupai("deepseek-ai/DeepSeek-V4-Pro"),
    prompt,
  });

  return result.toTextStreamResponse();
}

TanStack AI

VS Code