Access Qwen Using OpenAI-Compatible API

In this tutorial, you'll learn how to access Qwen models using the OpenAI SDK through Puter's OpenAI-compatible endpoint. No Alibaba API key needed, just your Puter auth token.

Prerequisites

• A Puter account
• Your Puter auth token, go to puter.com/dashboard and click Copy to get your auth token

• Node.js installed on your machine

Setup

Install the OpenAI SDK:

npm install openai

Then configure the client with Puter's base URL and your auth token:

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.puter.com/puterai/openai/v1/",
  apiKey: "YOUR_PUTER_AUTH_TOKEN",
});

Replace YOUR_PUTER_AUTH_TOKEN with the auth token you copied from your Puter dashboard. That's all you need. No Alibaba API key required.

Basic Chat Completion

Here's a simple chat completion using Qwen 2.5 72B Instruct:

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.puter.com/puterai/openai/v1/",
  apiKey: "YOUR_PUTER_AUTH_TOKEN",
});

const response = await client.chat.completions.create({
  model: "qwen/qwen-2.5-72b-instruct",
  messages: [
    { role: "user", content: "What is the capital of France?" },
  ],
});

console.log(response.choices[0].message.content);

Sample output:

The capital of France is Paris.

The code is identical to what you'd write for OpenAI directly. The only difference is the base URL and the model string.

Streaming

For longer responses, enable streaming to get results in real-time:

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.puter.com/puterai/openai/v1/",
  apiKey: "YOUR_PUTER_AUTH_TOKEN",
});

const stream = await client.chat.completions.create({
  model: "qwen/qwen-2.5-72b-instruct",
  messages: [
    { role: "user", content: "Write a short story about a robot learning to paint." },
  ],
  stream: true,
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) {
    process.stdout.write(content);
  }
}

Set stream: true and iterate over the chunks as they arrive. Each chunk contains a piece of the response that you can display immediately.

Conclusion

That's it. You now have access to Qwen through the OpenAI SDK via Puter, no Alibaba API key needed. Swap the model string to use any Qwen model, from the lightweight Qwen 2.5 to the powerful Qwen 3.5, or any of the hundreds of other AI models available through Puter.

Related

• How to Use the OpenAI SDK with Puter
• Free, Unlimited Qwen API
• Qwen Models on Puter
• Access DeepSeek Using OpenAI-Compatible API
• Access Kimi Using OpenAI-Compatible API
• Supported AI Models