Skip to main content
Integrate llm.kiwi into your Python backend using the industry-standard OpenAI library.

​
Installation

pip install openai

​
Setup

Set your API key as an environment variable for security: 
export LLM_KIWI_API_KEY='sk-...'

​
Basic Usage

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ.get("LLM_KIWI_API_KEY"),
    base_url="https://api.llm.kiwi/v1"
)

response = client.chat.completions.create(
    model="pro",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "How do I make a perfect kiwi smoothie?"}
    ]
)

print(response.choices[0].message.content)

​
Advanced Configuration

You can configure timeouts and retries directly in the client: 
client = OpenAI(
    api_key="YOUR_KEY",
    base_url="https://api.llm.kiwi/v1",
    timeout=20.0,
    max_retries=3
)

​
Async Usage

For high-concurrency applications, use the AsyncOpenAI client: 
import asyncio
from openai import AsyncOpenAI

async_client = AsyncOpenAI(
    api_key="YOUR_KEY",
    base_url="https://api.llm.kiwi/v1"
)

async def main():
    response = await async_client.chat.completions.create(
        model="fast",
        messages=[{"role": "user", "content": "Hello!"}]
    )
    print(response.choices[0].message.content)

asyncio.run(main())