LangChain

LangChain can talk to Aramm through the same OpenAI-compatible endpoint used by the SDK pages. Keep the setup minimal: one base URL, one API key, one model.

What you need

• An Aramm API key
• langchain-openai installed
• A model id such as openai/gpt-4o

Quick setup

import os
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="openai/gpt-4o",
    api_key=os.environ["ARAMM_API_KEY"],
    base_url="https://router.aramm.ai/v1",
)

print(llm.invoke("Say hi").content)

Model naming

Use provider/model ids in the model field.

Verify it works

Invoke one chat call and confirm the result is returned normally.

Troubleshooting

• 401 usually means the API key is missing or invalid.
• model not found usually means the model id does not exist in Aramm.
• If the client cannot connect, confirm the base URL includes /v1.