How to beginner · 3 min read

How to use Qwen on Together AI

Q: How to use Qwen on Together AI

Use the OpenAI Python SDK with base_url="https://api.together.xyz/v1" and your TOGETHER_API_KEY to call the qwen-v1 model on Together AI. Create a client with OpenAI(api_key=os.environ["TOGETHER_API_KEY"], base_url="https://api.together.xyz/v1") and invoke chat.completions.create with the model and messages.

Quick answer

Use the OpenAI Python SDK with base_url="https://api.together.xyz/v1" and your TOGETHER_API_KEY to call the qwen-v1 model on Together AI. Create a client with OpenAI(api_key=os.environ["TOGETHER_API_KEY"], base_url="https://api.together.xyz/v1") and invoke chat.completions.create with the model and messages.

PREREQUISITES

Python 3.8+
Together AI API key (set TOGETHER_API_KEY environment variable)
pip install openai>=1.0

Setup

Install the openai Python package (version 1.0 or higher) and set your Together AI API key as an environment variable TOGETHER_API_KEY. Together AI uses an OpenAI-compatible API endpoint, so you specify base_url="https://api.together.xyz/v1" when creating the client.

bash

pip install openai>=1.0

Step by step

This example shows how to create a client for Together AI, call the qwen-v1 model with a simple chat prompt, and print the response.

python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["TOGETHER_API_KEY"],
    base_url="https://api.together.xyz/v1"
)

response = client.chat.completions.create(
    model="qwen-v1",
    messages=[{"role": "user", "content": "Hello, how do I use Qwen on Together AI?"}]
)

print(response.choices[0].message.content)

output

Hello! To use Qwen on Together AI, create an OpenAI-compatible client with your API key and call the qwen-v1 model as shown.

Common variations

You can use other Qwen variants if available by changing the model parameter. For asynchronous calls, use async functions with await. Streaming responses are supported by passing stream=True and iterating over the response chunks.

python

import asyncio
from openai import OpenAI

async def async_chat():
    client = OpenAI(
        api_key=os.environ["TOGETHER_API_KEY"],
        base_url="https://api.together.xyz/v1"
    )

    stream = await client.chat.completions.create(
        model="qwen-v1",
        messages=[{"role": "user", "content": "Stream a response from Qwen."}],
        stream=True
    )

    async for chunk in stream:
        print(chunk.choices[0].delta.content or "", end="", flush=True)

asyncio.run(async_chat())

output

Streaming response text from Qwen model printed token by token...

Troubleshooting

If you get authentication errors, verify your TOGETHER_API_KEY environment variable is set correctly.
If the model is not found, confirm qwen-v1 is the correct model name and Together AI supports it.
For network issues, check your internet connection and that https://api.together.xyz/v1 is reachable.

✅

Key Takeaways

Together AI uses an OpenAI-compatible API with a custom base_url.
Use OpenAI SDK with base_url="https://api.together.xyz/v1" and your API key.
Call chat.completions.create with model="qwen-v1" to use Qwen.
Support for async and streaming calls is available via the OpenAI SDK.
Always verify environment variables and model names to avoid common errors.

Verified 2026-04 · qwen-v1

Verify ↗