Self-hosted LiteLLM,
fully managed.
One API gateway for 100+ LLM providers: unified OpenAI-format calls, spend tracking, rate limits, and failover, self-hosted.
Billed yearly on a 1 GB server, or $6 month to month. LiteLLM itself is $0.
- Daily snapshots
- Free migration
- 500% SLA
- 4.4 on Trustpilot
- 500% SLA credited automatically
- Engineers 24/7, real humans
- Free migration of your LiteLLM
- Since 2001, independent
At a glance
LiteLLM here, in four lines.
What it is, what we install, what management covers and what it needs. The rest of this page is detail.
- What it is
- LiteLLM is the traffic controller for AI APIs: one self-hosted gateway that speaks OpenAI format and routes to 100+ providers, with per-key spend tracking, rate limits, retries, and failover. Point every app at one URL and manage the chaos in one place.
- What we install
- Our playbook deploys the LiteLLM proxy with a PostgreSQL-backed key store, HTTPS issued and forced, and an admin key generated for you. Add provider keys, mint virtual keys per app or teammate, done.
- What managed covers
- Server updates, snapshots, optional Dual Backups, monitoring, firewall, and humans on call. Your provider keys stay in your database on your server.
- What it needs
- 1 GB RAM
Fits on SC-1GB, from $5/mo. Bigger sizes leave room for the apps you stack beside it.
Your options
Three ways to run LiteLLM.
Installing LiteLLM is the easy part. The real question is who keeps it running.
| Do it yourselfOn any unmanaged VPS | One-click imageAt most clouds | RemarkableCloudManaged LiteLLM, from $5/mo | |
|---|---|---|---|
| Installing LiteLLM | You: dependencies, database, HTTPS | Preinstalled once, then it is yours | Deployed by a tested playbook, database and HTTPS wired |
| Updates | You | You | Us, with a snapshot first |
| Monitoring and security | You | You | Us, 24/7: monitoring, firewall and IDS |
| Backups | You | Usually a paid add-on | Daily snapshots included, Dual Backups optional |
| Other apps on the server | Yours to wire up | One app per server | As many as fit, $0 each |
| When something breaks | You fix it | You fix it | Our engineers fix it, day or night |
Built for
What people run on LiteLLM here.
On your own server, using it more never costs more.
One API key for every model
Your apps call one OpenAI-compatible endpoint; LiteLLM routes to any provider behind it.
Spend control across providers
Budgets, rate limits and usage logs per key, so AI costs stop being a mystery.
Provider failover
When one API degrades, routing rules fail over to another without touching app code.
Team key management
Hand each project a virtual key with its own limits instead of sharing raw provider keys.
Stack it
LiteLLM works better with company.
Everything here can run on the same server as LiteLLM, at $0 per app. The server only needs the room.
Pick your server
Choose the size. LiteLLM is $0.
LiteLLM needs 1 GB. Bigger servers leave room for the apps you stack beside it. Every size is fully managed, and you can resize in minutes.
SC-1GB
The right size for LiteLLM
$6 month to monthSave 17% yearly
- 1 GB RAM
- 1 vCPU
- 25 GB NVMe
- 2.5 TB transfer
SC-2GB
LiteLLM plus a few more apps
$8 month to monthSave 17% yearly
- 2 GB RAM
- 1 vCPU
- 50 GB NVMe
- 5 TB transfer
SC-4GB
A fuller stack beside LiteLLM
$16 month to monthSave 17% yearly
- 4 GB RAM
- 2 vCPU
- 100 GB NVMe
- 10 TB transfer
Prefer to self-host? The exact LiteLLM image we deploy is public and free to pull, with a full production guide.
The details
LiteLLM here, in plain words.
Straight answers to what people ask before they choose where to run it.
Why put a gateway in front of AI providers?
Because five apps with five hardcoded API keys is how spend surprises and outages happen. LiteLLM gives each app a virtual key with its own spend limit and rate limit, tracks spend per key, and fails over to a second provider when the first one has a bad day.
What does OpenAI-compatible actually mean?
Any tool that can talk to OpenAI's API can talk to your LiteLLM URL unchanged, while the gateway translates to Anthropic, Google, Mistral, Ollama, or a hundred others behind the scenes. Switching providers becomes a config line, not a code change.
How much server does LiteLLM need?
It is the lightest app in our AI shelf: 1 GB runs the proxy for personal and small-team traffic. It almost always shares a server with the apps that call it, which is exactly what the cart meter is for.
Does LiteLLM see my prompts?
Requests pass through your gateway on your server on the way to the provider you chose; nothing is logged beyond what you enable. That is the point of self-hosting the control plane.
FAQ
LiteLLM hosting, answered.
Still deciding? These are the questions we hear most.
Who should run LiteLLM?
Anyone with more than one AI-consuming app or more than one teammate holding raw provider keys. It is the natural companion to LibreChat, Flowise, and OpenClaw on the same server, all $0 here.
Does the gateway add latency?
Single-digit milliseconds on the same server, which disappears next to model inference time measured in seconds. Failover and retries typically save far more time than the hop costs.
What does LiteLLM hosting cost?
The app is $0; a 1 GB server starts at $5/mo on annual billing and runs it with room to spare, fully managed, Dual Backups optional. Provider usage bills with each provider through your own keys.
Does it work with my existing OpenAI-client code?
Yes, that is the point: point the base URL at your LiteLLM and existing OpenAI SDK code runs unchanged while gaining routing, budgets and logs.
Can it route to local models too?
Yes, Ollama and other local endpoints register as providers alongside the commercial APIs, so the same key can serve private and hosted models by rule.
Is this LiteLLM on a VPS or on shared hosting?
A VPS. LiteLLM runs on your own private virtual server with dedicated, non-oversold resources and its own IP. You get real isolation and performance, with the setup, TLS and hardening handled for you.
Can I run other apps on the same server?
Yes. Add any other catalog app to this server from your client area, one click each, no per-app charge. How much fits is a question of RAM, and resizing is minutes.
Do you migrate my existing LiteLLM?
Yes, migration help is free. Open a ticket with access to the current setup and we move it, verify it, and hand it back running. Nothing switches until you approve.
Can I upgrade or downgrade the plan later?
Anytime. Plans resize from the client area in minutes, annual billing keeps its flat 17% discount at every size, and there is never a fee to change tiers.
LiteLLM runs. You sleep.
Managed LiteLLM from $5/mo, free migration and a 30-day money-back guarantee.