Python

pip install openai

from openai import OpenAI

client = OpenAI(
    base_url="https://kymaapi.com/v1",
    api_key="kyma-your-api-key"
)

response = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain quantum computing simply."}
    ]
)

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

messages = [
    {"role": "system", "content": "You are a Python tutor."}
]

while True:
    user_input = input("You: ")
    if user_input.lower() == "quit":
        break
    
    messages.append({"role": "user", "content": user_input})
    
    response = client.chat.completions.create(
        model="llama-3.3-70b",
        messages=messages
    )
    
    reply = response.choices[0].message.content
    messages.append({"role": "assistant", "content": reply})
    print(f"AI: {reply}")

stream = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[{"role": "user", "content": "Write a haiku about coding"}],
    stream=True
)

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

import asyncio
from openai import AsyncOpenAI

client = AsyncOpenAI(
    base_url="https://kymaapi.com/v1",
    api_key="kyma-your-api-key"
)

async def main():
    response = await client.chat.completions.create(
        model="llama-3.3-70b",
        messages=[{"role": "user", "content": "Hello!"}]
    )
    print(response.choices[0].message.content)

asyncio.run(main())

response = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[{"role": "user", "content": "Be creative"}],
    temperature=0.9,      # 0-2, higher = more creative
    max_tokens=1000,       # max response length
    top_p=0.95,           # nucleus sampling
)