# LangChain

> Use Kurrens models in LangChain through ChatOpenAI.

```bash
pip install langchain-openai
```

```python
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="zai-org/GLM-5.3",
    base_url="https://api.kurrens.ai/v1",
    api_key="<KURRENS_API_KEY>",
    temperature=0.4,
)

print(llm.invoke("What makes an inference provider fast?").content)
```

Tool binding (`llm.bind_tools(...)`) and structured output (`llm.with_structured_output(...)`) work with models that
support [tool calling](/docs/inference/tool-calling) and [structured outputs](/docs/inference/structured-outputs).