Connect CLōD to LangGraph

Build stateful multi-agent graphs with LangGraph — backed by CLōD's cheaper inference.

Overview

LangGraph is a library for building stateful, multi-actor applications with LLMs. Since CLōD is OpenAI-compatible, drop it in as the LLM backend for any LangGraph agent or workflow — tool calling, streaming, and structured output all work out of the box.

Prerequisites

• CLōD account — free at app.clod.io
• LangGraph installed
• CLōD API key (Dashboard → API Keys → Generate)

Setup

Step 1: Install dependencies

pip install langgraph langchain-openai openai

Step 2: Configure CLōD LLM

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-4o",
    api_key="your_clod_api_key",
    base_url="https://api.clod.io/v1",
)

Step 3: Build a LangGraph agent

from langgraph.graph import StateGraph, END
from typing import TypedDict, Annotated
import operator

class AgentState(TypedDict):
    messages: Annotated[list, operator.add]

def call_model(state):
    response = llm.invoke(state["messages"])
    return {"messages": [response]}

graph = StateGraph(AgentState)
graph.add_node("agent", call_model)
graph.set_entry_point("agent")
graph.add_edge("agent", END)

app = graph.compile()
result = app.invoke({"messages": [("user", "Plan a multi-step task")]})

Available Models

CLōD supports 50+ models. For agentic tools, use models that support tool calling / function calling.

Browse models →

Need help?

Discord · Docs