LangChain

LangChain can call OdiRouter through OpenAI-compatible chat model integrations. Set the API key, model, and Base URL on the ChatOpenAI client.

Requirements

Requirement	Value
Package	langchain-openai or the OpenAI integration used by your LangChain version
Base URL	https://www.odirouter.ai/v1
API Key	OdiRouter API key
Model	An OdiRouter LLM model ID

Install

pip install langchain-openai

Configure ChatOpenAI

import os

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="gpt-5.5",
    api_key=os.environ["ODIROUTER_API_KEY"],
    base_url="https://www.odirouter.ai/v1",
)

Invoke The Model

response = llm.invoke("Reply with a one-line LangChain integration test.")

print(response.content)

Use In A Chain

from langchain_core.prompts import ChatPromptTemplate

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a concise engineering assistant."),
    ("user", "{question}"),
])

chain = prompt | llm

result = chain.invoke({"question": "List two integration checks."})

print(result.content)

Troubleshooting

Symptom	Fix
LangChain calls OpenAI directly	Confirm base_url is set on the active ChatOpenAI instance
401 response	Set ODIROUTER_API_KEY in the process environment
Model not found	Copy the model ID from GET https://www.odirouter.ai/v1/models
Tool calling fails	Confirm the selected OdiRouter model supports the tool-calling behavior your chain requires