The control plane for your AI stack
Route, track, replay, and eval every LLM call through one gateway. Start in the managed cloud in minutes — or run it in your own infrastructure. Switch models without fear, and ship AI you can actually trust.
Free to start. No credit card. Self-host anytime.
- Cost Move checkout to gpt-5-mini save ~$890/mo · replay match 98%
- Reliability Add OpenAI failover on messages Anthropic p95 latency +32% this hour
- Quality Promote claude-sonnet-4.6 +6% on your eval set
Ship AI fast. With visibility and control.
You built observability for everything else in the stack. It's time LLM calls got the same treatment.
The invoice nobody can explain
AI spend is the fastest-growing line item in your P&L, and nobody can say which team, feature, or experiment is driving it. Every call should be attributable.
One provider goes down, everything stops
Your entire product hangs on a single API endpoint you don't control. When it fails at 2am, your customers find out before you do.
Can't test a model switch on real traffic
A new model looks great in the playground. Validating it offline isn't the same as running it live — prove it against real production traffic before you commit.
No CI for AI
You test every code change before it ships. But your LLM outputs — the ones customers actually see — go to production with no scoring, no regression checks, no safety net.
See it in action
Cost tracking, request logs, and replay results — the dashboard your team actually opens.
No SDK to adopt. No code to rewrite.
Point any client at the gateway and every request comes back with token counts and real dollar costs — in the response headers, or straight from the Python library.
See more examples# Point any SDK at the gateway — costs come back in the response headers
curl http://localhost:6560/v1/chat/completions \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "X-Majordomo-Key: your-key" \
-d '{"model": "gpt-4o", "messages": [{"role": "user", "content": "Hello!"}]}'
# X-Majordomo-Input-Cost: 0.000125
# X-Majordomo-Output-Cost: 0.000250
# X-Majordomo-Total-Cost: 0.000375from majordomo_llm import get_llm_instance
llm = get_llm_instance("openai", "gpt-4o")
response = await llm.get_response("Explain async/await in Python.")
print(f"Cost: ${response.total_cost:.6f}")
print(f"Tokens: {response.input_tokens} in / {response.output_tokens} out")Powering AI at
Everything you need to run LLMs in production
One gateway. Full visibility. Complete control.
Intelligent Routing
Reach every provider and model through a single endpoint. Split traffic for experiments, retire deprecated models automatically, and translate between OpenAI and Anthropic formats — all without changing application code.
Cost & Usage Tracking
Every request logged with input tokens, output tokens, and cost. Attribute spend by API key, team, feature, or any custom metadata. Daily breakdowns and trend analysis.
Replay
Take your real production traffic and replay it against a different model. Compare cost, latency, and output quality side by side. Use an LLM judge to score equivalence automatically.
Evals
Build evaluation sets from your logged requests. Define custom scoring criteria. Run evaluations against any model and get aggregate quality scores before you ship.
Experiments
Run live A/B tests across model variants without touching application code. Split traffic by weight, compare cost, latency, and error rates per arm, and use sticky assignment to keep users on a consistent variant.
Your prompt content never lands in our database.
Enterprise security reviews ask where your data goes. Majordomo gives you a clean answer: request and response bodies go to storage you own, and our control plane keeps only metadata. Not via policies or contracts — by architecture. Need zero egress? Self-host the gateway in your own VPC.
Content to storage you control
Request and response bodies are written straight to your own S3 or GCS bucket — in the managed cloud or self-hosted. You own the data, control access, and set retention.
Metadata only, by design
Majordomo's control plane sees tokens, cost, latency, model name, and your custom attributes — never prompt or completion content. The entire dashboard runs on metadata.
Or run it entirely in your VPC
Self-host the gateway and prompts never leave your network at all. The proxy runs on your servers, on your cloud account — the same dashboard, zero data egress.
Built for teams that sell to enterprise.
If your customers operate under HIPAA, GDPR, FedRAMP, or strict internal data policies, their security team will scrutinize every vendor in your stack. Observability tools that store prompts in a third-party database are an automatic disqualification.
Majordomo keeps content out of its database in every deployment — and when a review demands zero egress, self-host the gateway inside your own VPC. Full observability either way — cost attribution, replay, evals — plus the data-flow diagram that closes the deal.
Up and running in minutes
Connect
Point your SDK or HTTP client at Majordomo — the managed cloud endpoint or your own gateway. One line of config, no code changes.
Observe
Every request is logged with tokens, cost, latency, and your custom metadata. See exactly where your AI budget is going.
Test offline
Replay production traffic against a different model. Compare cost, latency, and output quality using an LLM judge before you touch production.
Validate live
Run a production A/B experiment. Split real traffic across model variants, monitor per-arm metrics in real time, and ship the winner with confidence.
Two ways to deploy. Same product.
Start on the managed cloud and move to your own infrastructure whenever you need — the gateway, dashboard, and features are identical either way.
Managed Cloud
Fastest startWe run the gateway, dashboard, and control plane. Point your SDK at the hosted endpoint and you are live in minutes — nothing to deploy or operate.
- Sign up and send your first request in minutes
- Managed gateway at gateway.gomajordomo.com
- Request bodies stream to a bucket you own — we keep only metadata
- Automatic upgrades, no infrastructure to run
Self-hosted
Your infrastructureRun the platform in your own VPC with Docker or Kubernetes. Prompts never leave your network — the ideal answer for strict data-residency and security reviews.
- Deploy with Docker Compose, Kubernetes, or standalone Docker
- Connects to your own PostgreSQL and object storage
- Zero data egress — the proxy runs entirely on your servers
- The same dashboard, cost analytics, replays, and evals as the cloud
Looking for the free, standalone open-source gateway? See the majordomo-gateway project.
Ready to take control of your AI stack?
Spin up Majordomo Cloud and start routing, tracking, and optimizing your LLM calls in minutes — or self-host it in your own infrastructure.