[{"data":1,"prerenderedAt":109},["ShallowReactive",2],{"seo-verification":3,"marketplace-app-fr-litellm":6},{"google":4,"bing":5},"EycwPY2XMyTkVzas3n1ygeNJFGAH513qrMjfDljzsMQ","",{"slug":7,"name":8,"description":9,"phase":10,"docsUrl":11,"logo":12,"github":13,"tagline":14,"longDescription":15,"features":16,"useCases":23,"steps":33,"faq":49,"specs":68,"compatibleOs":76,"relatedApps":78,"relatedPosts":102,"category":106},"litellm","LiteLLM","Self-hosted OpenAI-compatible API gateway for 100+ LLMs — route between Ollama, Anthropic, Azure and more from a single endpoint, with per-key rate limits and spend tracking.",1,"https:\u002F\u002Fservorbit.com\u002Fblog\u002Fself-host-litellm-vps","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F132372032","https:\u002F\u002Fgithub.com\u002FBerriAI\u002Flitellm","Self-hosted LLM API gateway — route between Ollama, Anthropic and 100+ providers from a single OpenAI-compatible endpoint.","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.\n\nDeployed 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.",[17,18,19,20,21,22],"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",[24,27,30],{"title":25,"body":26},"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.",{"title":28,"body":29},"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.",{"title":31,"body":32},"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.",[34,37,40,43,46],{"title":35,"body":36},"Provision a VPS","Order a ServOrbit VPS with at least 1 GB RAM running Ubuntu 22.04. LiteLLM itself needs around 256 MB; PostgreSQL takes most of the remaining budget. Port 4000 must be reachable, or plan a reverse proxy on 80\u002F443.",{"title":38,"body":39},"Generate secrets","SSH into the VPS and run `openssl rand -hex 32` to generate LITELLM_MASTER_KEY — this is your admin API key that unlocks the dashboard and all administrative endpoints. Also set strong DB credentials. Keep the master key safe.",{"title":41,"body":42},"Deploy with Docker Compose","Create `\u002Fopt\u002Flitellm\u002F.env` with DB_NAME, DB_USER, DB_PASSWORD, LITELLM_MASTER_KEY, UI_USERNAME and UI_PASSWORD. Then create `\u002Fopt\u002Flitellm\u002Fdocker-compose.yml` with two services: LiteLLM (ghcr.io\u002Fberriai\u002Flitellm:main-latest, port 4000) and PostgreSQL 16. Run `docker compose up -d`. Allow 30 seconds for first boot.",{"title":44,"body":45},"Open the dashboard and add your first model","Navigate to `http:\u002F\u002F\u003Cvps-ip>:4000\u002Fui` and log in with your UI_USERNAME and UI_PASSWORD. Go to Models, click Add — enter a model name like `ollama\u002Fllama3.1` with base URL `http:\u002F\u002Fhost.docker.internal:11434` to route to a local Ollama, or paste an Anthropic API key for `anthropic\u002Fclaude-3-5-haiku-20241022`. Test with `curl -H \"Authorization: Bearer \u003CLITELLM_MASTER_KEY>\" http:\u002F\u002F\u003Cip>:4000\u002Fv1\u002Fmodels`.",{"title":47,"body":48},"Issue team API keys","In the dashboard under API Keys, create per-team virtual keys with optional `max_budget` (in USD), `tpm_limit` and `rpm_limit`. Share these keys with your developers — they point their OpenAI SDK at your LiteLLM gateway and the spend is tracked per key.",[50,53,56,59,62,65],{"q":51,"a":52},"What is LiteLLM?","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.",{"q":54,"a":55},"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.",{"q":57,"a":58},"Can LiteLLM work with my Ollama instance?","Yes. Add Ollama as a provider in the LiteLLM dashboard — set the base URL to `http:\u002F\u002Fhost.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.",{"q":60,"a":61},"How do I limit spending per team?","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.",{"q":63,"a":64},"Is there a built-in dashboard?","Yes. LiteLLM ships a web UI at `\u002Fui` 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.",{"q":66,"a":67},"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.",{"ram":69,"cpu":70,"stack":71,"port":75},"1 GB (2 GB recommended)","2 vCPU",[72,73,74],"Docker","Python","PostgreSQL 16","4000",[77],"ubuntu-24.04",[79,88,94],{"name":80,"slug":81,"categorySlug":82,"categoryName":83,"categoryColor":84,"logo":85,"tagline":86,"description":87},"Ollama","ollama","ia","Intelligence Artificielle","text-purple-400 bg-purple-500\u002F10","https:\u002F\u002Fcdn.simpleicons.org\u002Follama","Run open-source LLMs on your VPS — OpenAI-compatible API, zero per-token cost.","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.",{"name":89,"slug":90,"categorySlug":82,"categoryName":83,"categoryColor":84,"logo":91,"tagline":92,"description":93},"Open WebUI","open-webui",null,"Interface web pour vos LLMs — Ollama, OpenAI, Mistral — hébergée sur votre propre serveur.","Interface web pour interagir avec vos LLMs locaux ou distants. Vos données restent sur votre infrastructure — aucun tiers impliqué.",{"name":95,"slug":95,"categorySlug":96,"categoryName":97,"categoryColor":98,"logo":99,"tagline":100,"description":101},"n8n","automatisation","Automatisation & Workflows","text-brand-action bg-brand-action\u002F10","https:\u002F\u002Fcdn.simpleicons.org\u002Fn8n","Automatisez vos processus métier avec 400+ intégrations — 100 % auto-hébergé sur votre VPS.","Automatisez vos workflows entre applications sans code. Plus de 400 intégrations, 100 % auto-hébergé sur votre VPS.",[103,104,105],"self-host-litellm-vps","heberger-ollama-vps","deployer-dify-vps",{"key":82,"slug":82,"name":83,"objective":107,"icon":108,"color":84},"Créer, héberger et exploiter des solutions IA.","ai",1784126256461]