How much RAM does LiteLLM need?

LiteLLM itself needs around 256 MB. PostgreSQL (for usage tracking and analytics) adds another 256–512 MB. A 1 GB VPS is the minimum for a comfortable single-user setup; 2 GB is recommended for team deployments with concurrent requests.

Does LiteLLM work air-gapped with local models only?

Yes. Configure only Ollama as a provider and remove any external API keys — all inference stays on your VPS. LiteLLM adds routing, load balancing and the dashboard on top of your local Ollama without any outbound connection requirement.

Support

Build, host and run AI solutions.

LiteLLM

Self-hosted LLM API gateway — route between Ollama, Anthropic and 100+ providers from a single OpenAI-compatible endpoint.

1 GB (2 GB recommended) RAM 2 vCPU Port 4000 Available

Source code

Tech stack

DockerPythonPostgreSQL 16

Minimum RAM1 GB (2 GB recommended)

Minimum CPU2 vCPU

Default port4000

Compatible OSubuntu-24.04

LiteLLM is an open-source LLM proxy that presents a unified OpenAI-compatible API for over 100 LLM providers. Your applications keep a single endpoint — and LiteLLM routes each request to Ollama on the same VPS, to Anthropic Claude, to Azure OpenAI, or to any other backend you configure — without a single line of application code changing.

Deployed on a ServOrbit VPS, LiteLLM gives your development team a private AI gateway with a built-in dashboard for usage analytics, per-key spend limits and rate limiting. It runs alongside Ollama for fully air-gapped inference, or in front of commercial APIs to centralize cost tracking across all your projects.

Key features

OpenAI-compatible REST API — drop-in replacement, works with every SDK that speaks OpenAI

100+ LLM providers: Ollama, Anthropic, OpenAI, Azure, Mistral, Cohere, Bedrock and more

Per-key rate limiting and budget caps — block runaway costs in multi-team or multi-project setups

Real-time spend analytics and cost dashboard with per-model and per-key breakdowns

Load balancing and automatic failover across provider endpoints

Apache 2.0 — fully auditable, no telemetry, air-gap capable with Ollama

When to use this solution?

Multi-model AI backend

Route cost-sensitive tasks to a local Ollama instance and complex reasoning requests to Anthropic Claude — all from the same OpenAI SDK call in your application. Change the routing in the LiteLLM config, never in app code.

Team AI budget control

Issue virtual API keys to each team or project with a monthly spend cap. When a key hits its budget, LiteLLM returns a 429 — no surprise cloud bill at the end of the month.

LLM provider migration

Switch your entire application from one provider to another by updating a config file. OpenAI-compatible surface means zero application changes — migrate from GPT-4 to Llama 3 on Ollama without touching a single import.

Deploy LiteLLM on your VPS

Guide optimized for ServOrbit Cloud VPS.

Order the VPS

A ServOrbit VPS with 1 GB of RAM is enough for individual use: LiteLLM itself uses around 256 MB, and PostgreSQL takes most of the rest. Allow 2 GB for a team sending requests in parallel. Plan for the domain through which the gateway will be reached as well: there is no other way to it.

Let the installation generate the secrets

You have nothing to craft by hand: the deployment generates the LITELLM_MASTER_KEY master key, the PostgreSQL database credentials and the admin interface password. The master key opens the dashboard and every administrative endpoint — treat it as a password and keep it off the server.

Log in for the first time

Open the admin interface at https://<your-domain>/ui: LiteLLM shows a username and password form. Enter admin and the password generated at install time, shown on the app's card in your client area, then create your virtual keys from the dashboard.

What the installation deploys

Two containers start together: the ghcr.io/berriai/litellm:main-latest gateway, published on 127.0.0.1:4000, and a postgres:16-alpine database. Data persists in two volumes, litellm_db for the database and litellm_config for the gateway configuration. Allow around thirty seconds for the first start.

Declare your first model

In the dashboard, open Models then Add. To route to an Ollama installed on the same machine, enter a model name such as ollama/llama3.1 with the base URL http://host.docker.internal:11434; for a remote provider, paste the matching API key, for anthropic/claude-3-5-haiku-20241022 for example. Check with curl -H "Authorization: Bearer <LITELLM_MASTER_KEY>" https://<your-domain>/v1/models: that same address, https://<your-domain>/v1, is the base URL to give your SDKs.

Issue keys to your teams

In the API Keys section of the dashboard, create one virtual key per team, with a max_budget where relevant — the cumulative budget, expressed in dollars —, a tpm_limit in tokens per minute and an rpm_limit in requests per minute. Your developers point their OpenAI SDK at the gateway, and spend is accounted for key by key.

Frequently asked questions

LiteLLM is an open-source LLM proxy (Apache 2.0) that exposes a unified OpenAI-compatible API for over 100 LLM providers — Ollama, Anthropic Claude, OpenAI GPT-4, Azure OpenAI, Mistral, Cohere and more. It sits between your applications and any LLM backend, handling routing, rate limiting and cost tracking.

Yes. Add Ollama as a provider in the LiteLLM dashboard — set the base URL to http://host.docker.internal:11434 (Docker adds this host automatically). Any app using the OpenAI SDK can then call your Ollama models through LiteLLM without changing a single import.

Create virtual API keys in the LiteLLM dashboard and set max_budget in USD. When a key's cumulative spend reaches the cap, LiteLLM returns a 429. You can also set tpm_limit (tokens per minute) and rpm_limit (requests per minute) per key for rate-based control.

Yes. LiteLLM ships a web UI at /ui on port 4000. It shows real-time spend by key and by model, request logs, latency breakdowns, and lets you manage models, virtual keys and team budgets — no separate deployment needed.

Embed the deploy button

Maintaining a project that uses LiteLLM? This button lets your readers deploy it on a VPS in one click, without reading Docker documentation.

Markdown

[![Deploy LiteLLM on ServOrbit](https://servorbit.com/brand/deploy/button.svg)](https://servorbit.com/vps-cloud?template=litellm&utm_source=deploy-badge&utm_medium=referral&utm_campaign=litellm)

HTML

<a href="https://servorbit.com/vps-cloud?template=litellm&utm_source=deploy-badge&utm_medium=referral&utm_campaign=litellm"><img src="https://servorbit.com/brand/deploy/button.svg" alt="Deploy LiteLLM on ServOrbit" height="40"></a>

The button points to a VPS order with the template preselected. The image is served from servorbit.com — nothing to host on your side.

Complementary solutions

Artificial Intelligence

Ollama

Run open-source LLMs locally via a dead-simple API. Pull Llama 3, Mistral, Qwen or DeepSeek in one command — OpenAI-compatible, zero per-token cost.

Artificial Intelligence

Open WebUI

Web interface to interact with your local or remote LLMs. Your data stays on your infrastructure — no third party involved.

Automation & Workflows

n8n

Automate your workflows across applications without code. Over 400 integrations, 100% self-hosted on your VPS.

Build, host and run AI solutions.

Activate LiteLLM on your infrastructure.

Dedicated Cloud VPS — IPv4 included, European datacenter, support included. Your data never leaves your server.

Recommended configuration: 1 GB (2 GB recommended) RAM · 2 vCPU

Need help?

Browse our help center and FAQ, or reach our team — callback, WhatsApp or email. Support in French, English and Arabic.

or write to us