# Nvidia NIM Python SDK
> Use the OpenAI Python SDK to integrate with Nvidia NIM via Helicone to log your Nvidia usage.
import { strings } from "/snippets/strings.mdx";
import LegacyWarning from "/snippets/legacy-provider-warning.mdx";
This integration is used to log usage with the [Nvidia NIM](https://build.nvidia.com/) API. For other Nvidia inference providers that are OpenAI-compatible, such as Dynamo, see [here](/integrations/nvidia/dynamo).
## {strings.howToIntegrate}
```bash
HELICONE_API_KEY=
NVIDIA_API_KEY=
```
```python OpenAI SDK
from openai import OpenAI
from dotenv import load_dotenv
import os
load_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)
```
## {strings.relatedGuides}
{strings.chatbotCookbookDescription}
{strings.howToPromptThinkingModelsCookbookDescription}