LangChain (Python) · Laras Router Docs

This guide connects LangChain (Python) to Laras Router. Every step was checked against the LangChain (Python) documentation.

You need an API key (lr_live_…) and a topped-up balance. New to Laras Router? Start with the Quickstart.

Set up

Install the package

Install the integration package.

Shell

pip install -U langchain-openai

Set your API key

Put your key in an environment variable.

Shell

export LARAS_API_KEY="lr_live_your_key_here"

Create the model

Create ChatOpenAI with the Laras Router base URL.

Python

import os
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="deepseek-flash",
    base_url="https://api.larasrouter.com/v1",
    api_key=os.environ["LARAS_API_KEY"],
    use_responses_api=False,
)

message = llm.invoke("Hello!")
print(message.text)

Good to know

use_responses_api=False keeps ChatOpenAI on Chat Completions. Some parameters and built-in tools otherwise switch it to the Responses API, which Laras Router does not implement.
LangChain documents that ChatOpenAI follows the official OpenAI specification and does not keep non-standard response fields such as reasoning_content.

Settings and screens can change between versions. If something looks different, check the LangChain (Python) documentation. For other tools, see all integrations.