$LLMZone Docs

Streaming

Stream responses in real-time using the requests library

Python Streaming with requests

stream.py
import requests

BASE_URL = "https://api.llmzone.net/v1"
API_KEY = "YOUR_API_KEY"


def main():
    response = requests.post(
        f"{BASE_URL}/chat/completions",
        headers={
            "Authorization": f"Bearer {API_KEY}",
            "Content-Type": "application/json",
        },
        json={
            "model": "claude-opus-4-6",
            "messages": [
                {"role": "user", "content": "Hello!"}
            ],
            "stream": True,
        },
        stream=True,
    )

    for line in response.iter_lines():
        if line:
            print(line.decode("utf-8"))


if __name__ == "__main__":
    main()

Expected Output

data: {"choices":[{"index":0,"delta":{"content":"Hello! How are","role":"assistant"}}],...}
data: {"choices":[{"index":0,"delta":{"content":" you doing today?","role":"assistant"}}],...}
data: {"choices":[{"index":0,"delta":{"content":" Is there something","role":"assistant"}}],...}
data: {"choices":[{"index":0,"delta":{"content":" I can help you with?","role":"assistant"}}],...}
data: [DONE]

For Node.js streaming examples, see the Node.js / TypeScript page.

On this page