LiteLLM
LiteLLM is a lightweight OpenAI API-compatible proxy for managing multiple LLM providers with a single endpoint.
Deploy LiteLLM on Dokploy
- Install Dokploy on your server if you haven't already.
- In your Dokploy panel, open a project and click Create Service → Template.
- Search for LiteLLM and click Create — Dokploy configures domains, environment variables, and volumes for you.
Alternatively, create a Compose service, go to Advanced → Import from Base64, and paste this payload:
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
Configuration
The exact Docker Compose and template configuration this template deploys.
Related Templates
AnythingLLM
Version: latest
AnythingLLM is a private, self-hosted, and local document chatbot platform that allows you to chat with your documents using various LLM providers.
Arche
Version: latest
Arche is a self-hosted AI workspace platform that spawns per-user OpenCode coding containers backed by a shared Knowledge Base. Requires the `arche-internal` external Docker network and `/opt/arche/{kb-content,kb-config,users}` directories on the host before deploy. Images are linux/amd64 by default; override `ARCHE_WEB_IMAGE` and `ARCHE_WORKSPACE_IMAGE` to the `-arm64` tag variants for ARM64 hosts.
bolt.diy
Version: latest
Prompt, run, edit, and deploy full-stack web applications using any LLM you want!
Crawl4AI
Version: 0.7.3
Crawl4AI is a modern AI-powered web crawler with support for screenshots, PDFs, JavaScript execution, and LLM-based extraction. Includes an interactive playground and MCP (Model Context Protocol) integration.
Dify
Version: 1.15.0
Dify is an open-source LLM app development platform. Build AI workflows, RAG pipelines, agents and chatbots with a visual interface and publish them as APIs or web apps.
Flowise
Version: latest
Flowise is an open-source UI visual tool to build and run LLM-powered applications.
Self-host LiteLLM in minutes
Dokploy is a free, open source deployment platform. Deploy LiteLLM and 499+ other templates on your own infrastructure with a single click.