Python OpenAI SDK

from openai import OpenAI

client = OpenAI(
    api_key="sk-live-your-callai-key",
    base_url="https://api.callaiapi.com/v1"
)

response = client.chat.completions.create(
    model="claude-3-7-sonnet",
    messages=[
        {"role": "system", "content": "You are a senior full-stack architect."},
        {"role": "user", "content": "Explain quicksort in Python."}
    ],
    stream=True
)

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

2. Async concurrency & long-thinking timeouts

import asyncio
from openai import AsyncOpenAI

# For DeepSeek R1 and similar reasoning models, set timeout to 120s
client = AsyncOpenAI(
    api_key="sk-live-your-callai-key",
    base_url="https://api.callaiapi.com/v1",
    timeout=120.0
)

async def main():
    stream = await client.chat.completions.create(
        model="deepseek-r1",
        messages=[{"role": "user", "content": "Derive the shortest distance from a point to a plane in 3D."}],
        stream=True
    )
    async for chunk in stream:
        delta = chunk.choices[0].delta.content or ""
        print(delta, end="", flush=True)

asyncio.run(main())