# ChatNVIDIADynamo

> **Class** in `langchain_nvidia_ai_endpoints`

📖 [View in docs](https://reference.langchain.com/python/langchain-nvidia-ai-endpoints/chat_models_dynamo/ChatNVIDIADynamo)

ChatNVIDIA subclass that injects ``nvext.agent_hints`` into requests
for Dynamo KV cache routing optimization.

A unique ``prefix_id`` is auto-generated for every request.

## Signature

```python
ChatNVIDIADynamo(
    self,
    *,
    model: Optional[str] = None,
    nvidia_api_key: Optional[str] = None,
    api_key: Optional[str] = None,
    base_url: Optional[str] = None,
    temperature: Optional[float] = None,
    max_completion_tokens: Optional[int] = None,
    top_p: Optional[float] = None,
    seed: Optional[int] = None,
    stop: Optional[Union[str, List[str]]] = None,
    default_headers: Optional[Dict[str, str]] = None,
    **kwargs: Any = {},
)
```

## Description

**Example:**

```python
from langchain_nvidia_ai_endpoints import ChatNVIDIADynamo

llm = ChatNVIDIADynamo(model="meta/llama3-8b-instruct")
# override per-invocation:
llm.invoke("Hello", osl=2048, iat=50)
```

## Extends

- `ChatNVIDIA`

## Properties

- `osl`
- `iat`
- `latency_sensitivity`
- `priority`

---

[View source on GitHub](https://github.com/langchain-ai/langchain-nvidia/blob/5bfb68d5b10aa0330a6b79a36375b9bc0c6acef7/libs/ai-endpoints/langchain_nvidia_ai_endpoints/chat_models_dynamo.py#L14)