Async/Await & Concurrent API Calls

Python asyncio enables concurrent I/O without threading complexity. async def defines a coroutine — a function that can pause (await) while waiting for I/O without blocking the event loop. For AI: call 5 LLM APIs simultaneously instead of sequentially with asyncio.gather(). Streaming LLM responses use async for to iterate over chunks as they arrive.

import asyncio
import anthropic

client = anthropic.AsyncAnthropic()

async def analyze_document(doc: str) -> str:
    response = await client.messages.create(
        model="claude-opus-4-5", max_tokens=512,
        messages=[{"role": "user", "content": f"Summarize: {doc}"}]
    )
    return response.content[0].text

# Process 5 documents concurrently instead of sequentially
async def batch_analyze(docs: list[str]) -> list[str]:
    tasks = [analyze_document(doc) for doc in docs]
    return await asyncio.gather(*tasks)  # 5x faster than sequential

results = asyncio.run(batch_analyze(my_documents))