Streaming Responses

Streaming LLM Responses

Streaming delivers tokens as generated instead of waiting for the complete response — essential for good UX.

# Anthropic streaming
import anthropic

client = anthropic.Anthropic()

with client.messages.stream(
    model='claude-opus-4-5',
    max_tokens=1024,
    messages=[{'role':'user','content':'Write a poem about Python'}]
) as stream:
    for text in stream.text_stream:
        print(text, end='', flush=True)

# OpenAI streaming
from openai import OpenAI
client = OpenAI()
stream = client.chat.completions.create(
    model='gpt-4o',
    messages=[{'role':'user','content':'Write a poem'}],
    stream=True
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end='', flush=True)

# FastAPI streaming endpoint
from fastapi.responses import StreamingResponse
@app.post('/chat')
async def chat(msg: str):
    async def generate():
        async with client.messages.stream(
            model='claude-opus-4-5', max_tokens=500,
            messages=[{'role':'user','content':msg}]
        ) as stream:
            async for text in stream.text_stream:
                yield text
    return StreamingResponse(generate(), media_type='text/plain')