LangChain and LangGraph

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="moonshotai/kimi-k3",                          # a Nito catalog ID, fetch from GET /v1/models
    api_key="z_sk_your_key_here",              # your Nito API key
    base_url="https://app.trynito.ai/v1",  # Nito's OpenAI-compatible base URL
)

result = llm.invoke("Say hello in one short sentence.")
print(result.content)

The same llm binds tools (llm.bind_tools([...])) and drives an agent unchanged:

from langchain.agents import create_agent
agent = create_agent(model=llm, tools=[...])

create_agent returns a compiled LangGraph graph. langgraph.prebuilt.create_react_agent is deprecated since LangGraph 1.0 and points at the same function. Pass stream_usage=True to get token usage in streamed chunks (full.usage_metadata after summing the chunks).

model="z-ai/glm-5.2:confidential"

Privacy

Use a catalog ID, not an OpenAI name. For attested hardware use a :confidential variant; GET /v1/models lists their :confidential IDs. Encrypted needs client-side encryption and extra headers, which these frameworks do not add. See Privacy Levels.

Framework Integrations

The shared pattern.

OpenAI Compatibility

What differs.

Privacy Levels

The four levels.

Basics

Features

Server-Side Tools

Multimodal

Best Practices

SDKs

API Reference

LangChain and LangGraph

Privacy

Framework Integrations

OpenAI Compatibility

Privacy Levels

​Privacy

​Related

Framework Integrations

OpenAI Compatibility

Privacy Levels

Privacy

Related