Hugging Face

pip install "huggingface_hub>=0.28.0"

from huggingface_hub import InferenceClient

client = InferenceClient(
    provider="sambanova",
    api_key="your-sambanova-api-key"  # SambaNova API key, not your Hugging Face token
)

messages = [
    {
        "role": "user",
        "content": "What is the capital of France?"
    }
]

completion = client.chat.completions.create(
    model="meta-llama/Llama-3.3-70B-Instruct",
    messages=messages,
    max_tokens=500
)

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