Skip to main content
This integration method is maintained but no longer actively developed. For the best experience and latest features, use our new AI Gateway with unified API access to 100+ models.
1
2
HELICONE_API_KEY=<your-helicone-api-key>
LLAMA_API_KEY=<your-llama-api-key>
3
import os
from llama_api_client import LlamaAPIClient

# Load environment variables
helicone_api_key = os.getenv("HELICONE_API_KEY")
llama_api_key = os.getenv("LLAMA_API_KEY")

client = LlamaAPIClient(
    api_key=llama_api_key,
    base_url="https://llama.helicone.ai/v1",
    default_headers={
        "Helicone-Auth": f"Bearer {helicone_api_key}"
    }
)

completion = client.chat.completions.create(
    model="Llama-4-Maverick-17B-128E-Instruct-FP8",
    messages=[
        {
            "role": "user",
            "content": "What is the moon made of?",
        }
    ],
)

print(completion.completion_message.content.text)

from openai import OpenAI
from dotenv import load_dotenv
import os

load_dotenv()

helicone_api_key = os.getenv("HELICONE_API_KEY")
llama_api_key = os.getenv("LLAMA_API_KEY")

client = OpenAI(
  api_key=llama_api_key,
  base_url="https://llama.helicone.ai/v1",
  default_headers={
    "Helicone-Auth": f"Bearer {helicone_api_key}"
  }
)

chat_completion = client.chat.completions.create(
  model="Llama-4-Maverick-17B-128E-Instruct-FP8",
  messages=[{"role": "user", "content": "Hello, how are you?"}],
  max_completion_tokens=1024,
  temperature=0.7
)

print(chat_completion)
4