Skip to main content
Majordomo is an LLM control plane that sits between your application and your AI providers. This page walks you through the Managed setup: create an account, point your SDK at the Majordomo gateway, and your requests start appearing in the dashboard immediately — no infrastructure to operate.
This guide covers the Managed setup — Majordomo runs the gateway. For self-hosted Steward in your own VPC, see Self-hosted Setup.
1

Create an account and API key

Sign up at app.gomajordomo.com. From the dashboard, navigate to API Keys and create your first key.Your key has the format mdm_sk_.... Store it in your secrets manager — it is shown only once at creation time.
2

Update your SDK configuration

Majordomo acts as a transparent proxy. Change the base URL and add one header. Your existing provider API key passes through unchanged.
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.gomajordomo.com/v1",
    api_key=os.environ["OPENAI_API_KEY"],
    default_headers={"X-Majordomo-Key": os.environ["MAJORDOMO_API_KEY"]},
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello"}],
)
Set the environment variable in your deployment environment:
MAJORDOMO_API_KEY=mdm_sk_your_key_here
The gateway returns responses identically to calling the provider directly — streaming, function calling, and all provider-specific parameters are passed through unchanged.
3

Verify in the dashboard

Open the Majordomo dashboard. Your request appears with model, token counts, cost, and latency as soon as it completes — no polling or additional setup required.From here you can manage API keys, tag requests for cost attribution, run replays against candidate models, and build eval sets from production traffic.

​
Next steps

Attribute costs by team or feature

Tag requests with custom metadata and break down spend across any dimension.

Test a model switch

Replay production traffic against a candidate model before committing to the change.

Self-hosted Steward

Run Steward in your own VPC. Prompts never leave your infrastructure.

All SDKs and frameworks

Integration examples for every supported SDK, including Pydantic AI and majordomo-llm.