Async¶

AsyncFreeTheAI has the same options and methods, awaited.

import asyncio
from freetheai import AsyncFreeTheAI

async def main():
    async with AsyncFreeTheAI() as client:
        reply = await client.chat.completions.create(
            model="fta/zai/glm-5.3",
            messages=[{"role": "user", "content": "Hello!"}],
        )
        print(reply["choices"][0]["message"]["content"])

        async for text in client.chat.completions.stream_text(
            model="fta/zai/glm-5.3",
            messages=[{"role": "user", "content": "Count to five."}],
        ):
            print(text, end="")

asyncio.run(main())

Many requests at once¶

Fire as many as you like with asyncio.gather. The client learns how many replies your account may run at once and queues the rest, so you don't get concurrency errors:

questions = ["What is DNS?", "What is TLS?", "What is HTTP/3?"]
replies = await asyncio.gather(*(
    client.chat.completions.create(model="fta/zai/glm-5.3-flash", messages=[{"role": "user", "content": q}])
    for q in questions
))