Back to Integrations
LangGraph markProtocol Compatibility

DEVUP AI for LangGraph

Build LangGraph agents on DEVUP AI models. Point langchain-openai's ChatOpenAI at DEVUP AI once, and every node, tool loop and conversation thread runs on DEVUP AI.

System Architecture

How LangGraph Connects to DEVUP AI

1. App Layer
Your graph
Nodes, edges, tools and a checkpointer
2. Gateway
DEVUP OpenAI-compatible API
POST /v1/chat/completions
3. Inference
Models
DeepSeek-V4-Pro, gpt-5.4-mini or any catalog ID
4. Output
Response
Answers, tool calls and streamed tokens

Configuration

Two Settings That Matter

Base URL

https://api.devupai.com/v1

Pass it as base_url of ChatOpenAI.

Model

deepseek-ai/DeepSeek-V4-Pro

Any catalog model ID, written exactly as listed.

Quick Start

Configure Once, Build Any Graph

devup_config.py

python
import os

from langchain_openai import ChatOpenAI


def devup_model(model: str = "deepseek-ai/DeepSeek-V4-Pro") -> ChatOpenAI:
    return ChatOpenAI(
        model=model,
        base_url="https://api.devupai.com/v1",
        api_key=os.environ["DEVUP_API_KEY"],
    )

basic_graph.py

python
from langgraph.graph import END, START, MessagesState, StateGraph

from devup_config import devup_model

model = devup_model()


def chatbot(state: MessagesState):
    return {"messages": [model.invoke(state["messages"])]}


builder = StateGraph(MessagesState)
builder.add_node("chatbot", chatbot)
builder.add_edge(START, "chatbot")
builder.add_edge("chatbot", END)
graph = builder.compile()

result = graph.invoke({"messages": [{"role": "user", "content": "Reply with exactly: Salam DEVUP"}]})
print(result["messages"][-1].content)

Capabilities

Supported Capabilities

Tool loops

ToolNode runs the tools the model calls, and tools_condition routes the graph back to the model until it answers.

Token streaming

stream_mode="messages" streams the model's tokens as each node runs.

Conversation memory

Compile with a checkpointer and pass a thread_id, and later calls continue from the saved state.

Local DZD billing

Metered billing in Algerian Dinar with BaridiMob, Edahabia, and CIB local payment support.

FAQ

LangGraph and DEVUP AI

Does LangGraph work with DEVUP AI?

Yes. Create ChatOpenAI from langchain-openai with base_url https://api.devupai.com/v1 and your DEVUP AI key. Graph nodes, tool loops, token streaming and checkpointer memory then run on DEVUP AI models.

Which API does LangGraph use with DEVUP AI?

ChatOpenAI sends its requests to the Chat Completions API, POST /v1/chat/completions, with the model ID exactly as written.

Which models can my graphs use?

Any model ID from the DEVUP AI catalog, written exactly as listed, such as deepseek-ai/DeepSeek-V4-Pro or openai/gpt-5.4-mini.

Ready to Build Graphs on DEVUP AI?