Nvidia NIM Python SDK - Helicone OSS LLM Observability

Warning

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.

This integration is used to log usage with the Nvidia NIM API. For other Nvidia inference providers that are OpenAI-compatible, such as Dynamo, see here.

How to Integrate#

Create an account and generate an API key

Log into Helicone or create an account. Once you have an account, you can generate an API key here.

Set up your Helicone API key in your .env file

HELICONE_API_KEY=<your-helicone-api-key>NVIDIA_API_KEY=<your-nvidia-api-key>

Modify the base URL path

OpenAI SDK

from openai import OpenAIfrom dotenv import load_dotenvimport osload_dotenv()helicone_api_key = os.getenv("HELICONE_API_KEY")nvidia_api_key = os.getenv("NVIDIA_API_KEY")client = OpenAI(  api_key=nvidia_api_key,  base_url="https://nvidia.helicone.ai/v1",  default_headers={    "Helicone-Auth": f"Bearer {helicone_api_key}"  })chat_completion = client.chat.completions.create(  model="nvidia/llama-3.1-nemotron-70b-instruct",  messages=[{"role": "user", "content": "Hello, how are you?"}],  max_tokens=1024,  temperature=0.7)print(chat_completion)

Verify your requests in Helicone

With the above setup, any calls to Nvidia will automatically be logged and monitored by Helicone. Review them in your Helicone dashboard.

This step-by-step guide covers function calling, response formatting and monitoring with Helicone.

How to Prompt Thinking Models Effectively

Best practices to to effectively prompt thinking models like Deepseek and OpenAI o1-o3 for optimal results.

How to Integrate#

Related Guides#