# NVIDIA NIM (/docs/providers/nvidia)


Overview [#overview]

[NVIDIA NIM](https://build.nvidia.com) (NVIDIA Inference Microservices) provides GPU-accelerated AI model serving with TensorRT-LLM optimization for enterprise-grade performance.

**Official Website:** [https://build.nvidia.com](https://build.nvidia.com)

Key Features [#key-features]

* **GPU Acceleration** — TensorRT-LLM optimized inference
* **Enterprise-Grade** — High availability and security
* **Self-Hosted Options** — Deploy on your own infrastructure
* **Comprehensive Catalog** — LLMs, vision, multimodal models
* **Free Tier** — Available for prototyping

Usage Example [#usage-example]

```python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.yuhuanstudio.com/v1"
)

response = client.chat.completions.create(
    model="model-id",
    messages=[{"role": "user", "content": "Hello!"}]
)

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

Available Models [#available-models]

Use the [Models API](/docs/models-api) to query available models:

```bash
curl https://api.yuhuanstudio.com/v1/models?provider=nvidia \
  -H "Authorization: Bearer YOUR_API_KEY"
```

<Callout type="info">
  Models and pricing are synced automatically from NVIDIA. Check the dashboard for current availability and rates.
</Callout>

Official Resources [#official-resources]

* [NVIDIA Build](https://build.nvidia.com)
* [API Documentation](https://docs.api.nvidia.com)
* [Model Catalog](https://catalog.ngc.nvidia.com)