--- title: "Self-Host Dify.AI on a VPS: Install & Production Guide" description: "Install Dify.AI on a VPS in 20 minutes: Docker setup, SSL, Ollama for local models, and backups. From $21.24/mo vs. $59/mo on Dify Cloud. Full commands included." image: https://blog.ishosting.com/hubfs/blog/self-hosted-dify/self-hosted-dify.png --- [VPS](https://ishosting.com/en/vps) [Dedicated hosting](https://ishosting.com/en/dedicated) [VPN](https://ishosting.com/en/vpn) [Storage](https://ishosting.com/en/storage) [About us](https://ishosting.com/en/about) [Client area](https://my.ishosting.com/en/account) [is\*hosting Blog](https://blog.ishosting.com/en) - [News](https://blog.ishosting.com/en/tag/news) - [VPS](https://blog.ishosting.com/en/tag/vps) - [Hosting](https://blog.ishosting.com/en/tag/hosting) - [Technology](https://blog.ishosting.com/en/tag/technology) - [is\*ai](https://blog.ishosting.com/en/tag/isai) - Other - [Marketing](https://blog.ishosting.com/en/tag/marketing) - [Security](https://blog.ishosting.com/en/tag/security) [News](https://blog.ishosting.com/en/tag/news) Categories [Search](https://blog.ishosting.com/hs-search-results) Hosting Services [About Us](https://ishosting.com/en/about) [Client Area](https://my.ishosting.com/en/account) [News](https://blog.ishosting.com/en/tag/news) [VPS](https://blog.ishosting.com/en/tag/vps) [Hosting](https://blog.ishosting.com/en/tag/hosting) [Technology](https://blog.ishosting.com/en/tag/technology) [is\*ai](https://blog.ishosting.com/en/tag/isai) [Marketing](https://blog.ishosting.com/en/tag/marketing) [Security](https://blog.ishosting.com/en/tag/security) [VPS](https://ishosting.com/en/vps) [Dedicated hosting](https://ishosting.com/en/dedicated) [VPN](https://ishosting.com/en/vpn) [Storage](https://ishosting.com/en/storage) 1. [Blog](https://blog.ishosting.com/en) 2. [Technology](https://blog.ishosting.com/en/tag/technology) 3. How to Self-Host Your AI Workflow Platform: Dify.AI on a VPS Technology # How to Self-Host Your AI Workflow Platform: Dify.AI on a VPS Install Dify.AI on a VPS in 20 minutes: Docker setup, SSL, Ollama for local models, and backups. From $21.24/mo vs. $59/mo on Dify Cloud. Full commands included. [is\*hosting team](https://blog.ishosting.com/en/author/team-ishosting) 14 May 2026 8 min reading ![How to Self-Host Your AI Workflow Platform: Dify.AI on a VPS](https://blog.ishosting.com/hubfs/blog/self-hosted-dify/self-hosted-dify.png) Table of Contents - [What You Need Before You Start](https://blog.ishosting.com/en/self-hosted-dify#what-you-need) - [Install Dify.AI on a VPS](https://blog.ishosting.com/en/self-hosted-dify#install-dify) - [Production Setup](https://blog.ishosting.com/en/self-hosted-dify#production-setup) - [Build Your First AI Workflow](https://blog.ishosting.com/en/self-hosted-dify#first-ai-workflow) - [Dify Cloud vs. Self-Hosted: The Numbers](https://blog.ishosting.com/en/self-hosted-dify#cloud-vs-self-hosted) - [Troubleshooting](https://blog.ishosting.com/en/self-hosted-dify#troubleshooting) - [Next Steps](https://blog.ishosting.com/en/self-hosted-dify#next-steps) Dify Cloud Professional costs **$59/month**: run limits, credit quotas, and data on their servers. For **$21.24-$47.99** on a VPS, you get a self-hosted AI instance on a KVM server that you control via SSH. This guide covers installation, production hardening (SSL, secrets, backups), and your first AI workflow. On a clean server, setup takes 20-30 minutes. ## What You Need Before You Start Pick the plan that matches your workload: For Dify with external APIs only (OpenAI, Anthropic). Sufficient for the core Dify stack, but cannot run local AI models: - [Medium VPS](https://ishosting.com/en/vps/158_1y?city=us-dallas) - From $21.24/mo, with annual billing - **Specs:** 3 CPU / 4 GB RAM / 40 GB NVMe For entry-level local AI. Runs Dify combined with lightweight Ollama models (3B-4B) like Qwen or Phi-3. - [Premium VPS](https://ishosting.com/en/vps/159_1y?city=us-dallas) - From $31.99/mo, with annual billing - **Specs:** 4 CPU / 8 GB RAM / 50 GB NVMe For complete local AI. Runs Dify combined with larger local models up to 13B, like Llama 3 or Qwen. - [Elite VPS](https://ishosting.com/en/vps/160_1y?city=us-dallas) - From $47.99/mo, with annual billing - **Specs:** 6 CPU / 16 GB RAM / 80 GB NVMe ### Other requirements - Ubuntu 24.04 LTS. Check if Docker is already installed: docker --version — if it returns a version, skip the install step below. - [SSH access to your VPS](https://blog.ishosting.com/en/how-to-ssh-to-a-server) - A domain name is optional, but required for HTTPS - An API key from your model provider, or Ollama for local inference ## Install Dify.AI on a VPS Everything here is copy-paste ready. Placeholders are in ALL\_CAPS. This is the full [Dify](https://github.com/langgenius/dify) self-hosted guide for Ubuntu, from a blank server to a working Dify.AI dashboard. ### Step 1. Prepare the Server Connect and update: ``` # Connect ssh root@YOUR_SERVER_IP # Update the system apt update && apt upgrade -y # Open the ports Dify needs ufw allow OpenSSH ufw allow 80/tcp ufw allow 443/tcp ufw enable ``` ![UFW firewall setup on a VPS](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/1.png?width=786&height=272&name=1.png) *This keeps SSH open and exposes only HTTP/HTTPS. Everything else is blocked by default.* If Docker is not installed: ``` curl -fsSL https://get.docker.com | sh docker compose version ``` ![Docker Compose version output](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/2.png?width=657&height=98&name=2.png) *The second command confirms Docker Compose is available. If it returns an error, install it separately: `apt install docker-compose-plugin -y`* ### Step 2. Install Dify ``` # Clone the repository git clone https://github.com/langgenius/dify.git # Go to the Docker directory cd dify/docker # Create your config file cp .env.example .env # If your VPS runs a control panel (Ispmanager, Hestia, etc.), # ports 80 and 443 are already taken. Reassign Dify's ports now: sed -i 's/EXPOSE_NGINX_PORT=80/EXPOSE_NGINX_PORT=8090/g' .env sed -i 's/EXPOSE_NGINX_SSL_PORT=443/EXPOSE_NGINX_SSL_PORT=8443/g' .env # Start all services docker compose up -d ``` ![Cloning Dify repository from GitHub](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/3.png?width=786&height=141&name=3.png) *The first run pulls all Docker images (~2-4 GB). Expect 3-5 minutes on a 1 Gbps uplink.* ![Docker compose up output showing all Dify containers started](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/4.png?width=786&height=183&name=4.png) Verify the stack is up: ``` docker compose ps ```   All containers should show the status "running". If any show "exited," run: `docker compose logs SERVICE_NAME` ![Docker compose ps output showing all Dify containers running](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/5.png?width=786&height=309&name=5.png) ### Step 3. First Login Go to `http://YOUR_SERVER_IP:8090` (or port 80 if you skipped the port change step). The setup wizard will open. ![Dify setup wizard — creating an admin account](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/6.png?width=786&height=417&name=6.png) - Create your admin account. - Go to **Settings**, then **Model Provider**, and add your first AI model. - Paste your API key (OpenAI, Anthropic, Gemini, or any supported provider). Dify verifies the connection immediately. - The dashboard is ready. You can now build workflows. ![Dify Studio dashboard — ready to create apps](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/7.png?width=786&height=405&name=7.png) ![Dify Settings — Model Provider page with available AI providers](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/8.png?width=786&height=485&name=8.png) ### Step 4 (Optional). Add Ollama for Local Models *Skip this step if you're on Medium — it doesn't have enough RAM for local models. The instructions below assume Premium (8 GB) or higher. On Premium, lightweight models (3B-4B) like Qwen or Phi-3 run comfortably. For 7B+ models, use Elite (16 GB).* Ollama lets you run models like Llama, Qwen, and Gemma on the same server as Dify. ``` # Install Ollama curl -fsSL https://ollama.com/install.sh | sh # Pull a model (llama3 is ~4.7 GB) ollama pull llama3 # Confirm it loaded ollama list ``` ![Ollama installation output on a VPS](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/9.png?width=786&height=166&name=9.png) ![Ollama pull llama3 and ollama list output](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/10.png?width=595&height=311&name=10.png) The model downloads to `/usr/share/ollama/.ollama/models` by default. Check available disk space first with: `df -h` ### Fix Ollama Network Error Two things block the connection: Ollama only listens on localhost (so Docker can't reach it), and UFW blocks port 11434. Fix — expose Ollama to all interfaces via systemd override: ``` mkdir -p /etc/systemd/system/ollama.service.d echo '[Service]' > /etc/systemd/system/ollama.service.d/environment.conf echo 'Environment="OLLAMA_HOST=0.0.0.0"' >> /etc/systemd/system/ollama.service.d/environment.conf systemctl daemon-reload systemctl restart ollama ``` Ollama now listens on all interfaces. The override persists across reboots. Then open the port in UFW: ``` # Allow Ollama access only from Docker containers (not the public internet) ufw allow from 172.17.0.0/16 to any port 11434 # Ollama has no built-in authentication. # Do NOT use 'ufw allow 11434/tcp' — that exposes your models to anyone. ``` ### Connect Ollama to Dify Find your Docker bridge gateway IP: ``` ip route | grep docker | awk '{print $9}' # Typically returns: 172.17.0.1 ``` ![Docker bridge gateway IP output — 172.17.0.1](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/11.png?width=625&height=76&name=11.png) Using the bridge IP keeps traffic inside the host. If it fails, use `http://YOUR_SERVER_IP:11434` instead. Go to **Settings** → **Model Provider**, scroll to **Ollama**, and click **Add Model**. Fill in: ![Dify Model Provider — searching and installing Ollama](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/12.png?width=786&height=392&name=12.png) ![Ollama installed in Dify — Add Model button](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/13.png?width=786&height=165&name=13.png) - **Model Name:** llama3 - **Base URL:** http://172.17.0.1:11434 (the Docker bridge IP from the terminal above) - **Model Type:** LLM (default, leave as is) - **Authorization Name:** Leave blank - **Completion mode:** Chat (default) - **Model context size:** 8192 - **Upper bound for max tokens:** 4096 - **Vision support:** No - **Function call support:** No ![Dify Add Model form for Ollama](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/14.png?width=786&height=763&name=14.png) Click **Save**. A green **Active** badge will appear next to Ollama, confirming the connection. If the badge doesn't appear, confirm you ran both fix steps above: the systemd override and `ufw allow from 172.17.0.0/16 to any port 11434`Then try saving again. ## Production Setup ![self-hosted AI](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/01_en.png?width=1536&height=704&name=01_en.png) A self-hosted AI instance on port 8090 with default credentials is a test environment. Before it handles real AI workflow traffic, add SSL, hardened secrets, and backups. ### Reverse Proxy and SSL Confirm Dify is running on port 8090 (we set this in Step 2): ``` cd ~/dify/docker # Verify the port is already set from Step 2: grep EXPOSE_NGINX_PORT .env # Should return: EXPOSE_NGINX_PORT=8090 # If it still shows 80, run the reassignment now: sed -i 's/EXPOSE_NGINX_PORT=80/EXPOSE_NGINX_PORT=8090/g' .env sed -i 's/EXPOSE_NGINX_SSL_PORT=443/EXPOSE_NGINX_SSL_PORT=8443/g' .env docker compose down && docker compose up -d ``` After this, Dify runs on port 8090 internally. Your system Nginx will proxy from 80/443 to 8090. Now install Nginx and Certbot: ``` apt install nginx certbot python3-certbot-nginx -y ``` Create the Nginx config: ``` nano /etc/nginx/sites-available/dify ``` Paste this server block: ``` server { listen 80; server_name YOUR_DOMAIN; location / { proxy_pass http://127.0.0.1:8090; proxy_set_header Host $host; proxy_set_header X-Real-IP $remote_addr; proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for; proxy_set_header X-Forwarded-Proto $scheme; proxy_buffering off; proxy_read_timeout 3600s; client_max_body_size 100M; } } ``` `proxy_read_timeout 3600s` handles long AI inference requests. `client_max_body_size 100M` lets you upload large documents to the knowledge base. ``` # Enable the site ln -s /etc/nginx/sites-available/dify /etc/nginx/sites-enabled/ nginx -t && systemctl reload nginx # Get a free SSL certificate certbot --nginx -d YOUR_DOMAIN ``` Certbot configures Nginx for HTTPS automatically and sets up auto-renewal. After this, Dify is at https://YOUR\_DOMAIN ### Secrets Change all three before connecting any real data: ``` cd ~/dify/docker # Generate three separate secrets openssl rand -base64 32 # for SECRET_KEY openssl rand -base64 32 # for DB_PASSWORD openssl rand -base64 32 # for REDIS_PASSWORD # Edit the .env file and update these three lines: nano .env SECRET_KEY=YOUR_GENERATED_SECRET DB_PASSWORD=YOUR_GENERATED_DB_PASSWORD REDIS_PASSWORD=YOUR_GENERATED_REDIS_PASSWORD ``` Run each openssl command separately and paste the output into the corresponding line. Do not reuse the same value across fields. ``` # Restart to apply new secrets docker compose down && docker compose up -d # Block direct access to Dify's internal port ufw deny 8090/tcp ``` ### Backups is\*hosting runs weekly infrastructure backups, which cover the server itself. **Dify's application data** — workflows, knowledge bases, uploaded documents, and vector embeddings — lives in the dify/docker/volumes/ directory. Back that up separately. ``` #!/bin/bash # Dify backup script # Save as /home/backup_dify.sh # chmod +x /home/backup_dify.sh DATE=$(date +%Y%m%d_%H%M%S) BACKUP_DIR="/home/dify_backups" DIFY_DIR="/root/dify/docker" mkdir -p $BACKUP_DIR # Back up the full volumes directory tar czf $BACKUP_DIR/dify_volumes_$DATE.tar.gz \ -C $DIFY_DIR volumes/ echo "Backup done: dify_volumes_$DATE.tar.gz" ``` Backs up the full volumes/ directory: DB, file storage, and vector store. DB-only backups will not restore knowledge base files on recovery. ``` # Schedule daily backups at 2 AM crontab -e # Add this line: 0 2 * * * /bin/bash /home/backup_dify.sh >> /var/log/dify_backup.log 2&1 ``` ## Build Your First AI Workflow ![AI workflow to build with Dify.AI](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/02_en.png?width=1536&height=704&name=02_en.png) The most useful first AI workflow to build with [Dify.AI](http://dify.ai) is a RAG chatbot that answers from your documents, not its training data. This is how you build your own generative AI chatbot that knows your product. ### Create a Knowledge Base - Go to **Knowledge** → **Create Knowledge**. - Upload your documents: PDF, DOCX, TXT, or Markdown. - Pick an embedding model. OpenAI text-embedding-3-small works for most cases. - Wait for indexing to finish. The dashboard shows chunk count and status. ### Build the Chatflow - Go to **Studio** → **Create App** → **Chatflow**. - Add a **Knowledge Retrieval** node and connect it to your knowledge base. - Add an **LLM** node after it; this is where the model generates the response. - Set the system prompt: ![Dify Studio — Create from Blank](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/15.png?width=786&height=413&name=15.png) ![Dify Create from Blank — selecting Chatflow app type](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/16.png?width=786&height=329&name=16.png) ``` Answer questions based ONLY on the context below. If the answer is not in the context, say so. Do not make things up. Context: {{#context#}} Question: {{#sys.query#}} ``` {{#context#}} is automatically replaced with retrieved chunks from your knowledge base. This keeps answers grounded in your actual documents. ### Publish - Click **Publish**. Dify gives you an embeddable chat widget and a REST API endpoint. - Embed the widget on your site or call the API from your app. - Your documents are now queryable by anyone you give access to — all running on your own VPS. ![Dify Chatflow editor with LLM node and publish options](https://blog.ishosting.com/hs-fs/hubfs/blog/self-hosted-dify/17.png?width=786&height=400&name=17.png) ## Dify Cloud vs. Self-Hosted: The Numbers | **Criteria** | **Dify Cloud (Professional)** | **Self-hosted on is\*hosting** | | --- | --- | --- | | Monthly cost | $59/mo ($49/mo annual) | From $21.24/mo (annual billing) | | Workflow run limits | Platform quotas apply | No platform-imposed quotas | | Message credits | Limited per plan | No credit system | | Your data | Stored on Dify's servers | Your VPS, your jurisdiction | | Local models | Not supported | Yes, via Ollama | | API key routing | Through Dify's platform | Direct to your provider | | Customization | Limited by SaaS constraints | Full access (open source) | | SSL | Included | Free via Let's Encrypt | The cost gap is **$11-38/mo, depending on the plan**. Add Ollama and the savings compound: one-time compute cost, no per-token fees, no platform quotas on your AI workflow. The real argument for self-hosting is data residency. As an open-source LLMOps platform, Dify gives you full control: customer data, legal docs, and compliance requirements stay on your server, not Dify's. ###### VPS KVM-powered VPS with NVMe storage in 40+ locations. Full root access, dedicated resources, and up to 256 IPv4 addresses per plan. [Compare VPS plans](https://ishosting.com/en/vps) ## Troubleshooting Five issues most people run into the first time they run Dify.AI on a VPS: ### Dify Won't Start Check the logs for the service that failed: ``` docker compose logs --tail=50 api ``` Two causes cover most cases: RAM below 4 GB, or a port conflict. **Port conflict error:** `failed to bind host port 0.0.0.0:80/tcp` or `443/tcp: address already in use` A system web server or control panel (Ispmanager, Hestia) owns those ports. Don't stop it; shift Dify's ports instead: ``` docker compose down sed -i 's/EXPOSE_NGINX_PORT=80/EXPOSE_NGINX_PORT=8090/g' .env sed -i 's/EXPOSE_NGINX_SSL_PORT=443/EXPOSE_NGINX_SSL_PORT=8443/g' .env docker compose up -d ``` After this, Dify runs on port 8090. Check with: `docker compose ps` ### Ollama Network Error in Dify Dify can't reach Ollama. Two things cause this: - **Ollama only listens on localhost** by default; Docker containers can't reach it. - **UFW blocks port 11434**, so the connection never gets through. Fix both: ``` # Step 1 - expose Ollama to all interfaces mkdir -p /etc/systemd/system/ollama.service.d echo '[Service]' > /etc/systemd/system/ollama.service.d/environment.conf echo 'Environment="OLLAMA_HOST=0.0.0.0"' >> /etc/systemd/system/ollama.service.d/environment.conf systemctl daemon-reload systemctl restart ollama # Step 2 - open the port for Docker only ufw allow from 172.17.0.0/16 to any port 11434 ``` If the Docker bridge IP (172.17.0.1) still fails in Dify after this, use your public server IP instead: `http://YOUR_SERVER_IP:11434` ### Models Not Connecting Test outbound connectivity from the VPS, then check the worker logs: ``` curl -I https://api.openai.com docker compose logs --tail=30 worker ``` Some providers block outbound traffic to certain IP ranges by default. If curl returns nothing, check your firewall and VPS provider network settings. ### Slow Performance Check live resource usage across containers: ``` docker stats --no-stream ``` Consistent high memory on the API or worker container means RAM is the bottleneck. **Medium (4 GB)** handles API models fine. **Dify + Ollama** needs 12-16 GB — Elite plan territory. ### 502 Bad Gateway Nginx is up, but it can't reach Dify. Verify the backend is running, and the proxy target is correct: ``` # Check which port Dify is actually on docker compose ps # Test direct connection curl -I http://127.0.0.1:8090 ``` If the direct connection works but Nginx returns 502, the proxy\_pass in your Nginx config points to the wrong port. Match it to the port shown in docker compose ps output. ## Next Steps **Medium (4 GB RAM)** runs **Dify.AI** with API models comfortably — the core stack stays under 3 GB. For Ollama, start with **Premium (8 GB)** for lightweight models (3B-4B), or **Elite (16 GB)** for 7B-13B models. All plans include **KVM, NVMe storage, and 40+ locations**. The full self-hosted AI starter kit from this guide works on any of them — the difference is how many models you can run locally. Start with the Premium plan for local AI workflows, or [compare all VPS plans](https://ishosting.com/en/vps). {{ include\_custom\_fonts({"Whitney":\["Bold","Bold Italic","Light","Light Italic","Medium","Medium Italic","Regular","Semi Bold","Semi Bold Italic"\]}) }} ###### Dedicated Server When VPS is not enough. [From $66.67/mo](https://ishosting.com/en/dedicated) Table of Contents - [What You Need Before You Start](https://blog.ishosting.com/en/self-hosted-dify#what-you-need) - [Install Dify.AI on a VPS](https://blog.ishosting.com/en/self-hosted-dify#install-dify) - [Production Setup](https://blog.ishosting.com/en/self-hosted-dify#production-setup) - [Build Your First AI Workflow](https://blog.ishosting.com/en/self-hosted-dify#first-ai-workflow) - [Dify Cloud vs. Self-Hosted: The Numbers](https://blog.ishosting.com/en/self-hosted-dify#cloud-vs-self-hosted) - [Troubleshooting](https://blog.ishosting.com/en/self-hosted-dify#troubleshooting) - [Next Steps](https://blog.ishosting.com/en/self-hosted-dify#next-steps) ## Related articles ![Odysseus on VPS: How to Self-Host Your AI Workspace](https://blog.ishosting.com/hubfs/blog/odysseus-on-vps/odysseus-on-vps.png) Hosting ### Odysseus on VPS: How to Self-Host Your AI Workspace A step-by-step guide to self-hosting the Odysseus AI workspace on a VPS. Set up Docker, model providers, agent mode,... is\*hosting team 17 Jun 2026 7 min reading ![Astro on a VPS: Full Deployment Guide (Static + SSR)](https://blog.ishosting.com/hubfs/blog/astro-on-vps/astro-on-vps.png) How to ### Astro on a VPS: Full Deployment Guide (Static + SSR) Full guide to self-hosting an Astro site on a VPS. Set up static or SSR deployment with Nginx, Node.js 22, PM2, and... is\*hosting team 25 Jun 2026 8 min reading ![Docmost on VPS: Self-Hosted Wiki for Teams That Need Data Control](https://blog.ishosting.com/hubfs/blog/docmost-self-hosted-wiki-vps/docmost-self-hosted-wiki-vps.png) Technology ### Docmost on VPS: Self-Hosted Wiki for Teams That Need Data Control Deploy Docmost, an open-source self-hosted wiki, on your VPS with Docker. Full data control, real-time editing, and a... is\*hosting team 7 May 2026 8 min reading ## Subscribe to Newsletter The latest news, profitable discounts, and informative articles - subscribe to the is\*hosting blog and be the first to receive a useful newsletter. - **Services** Services - [Virtual Private Servers](https://ishosting.com/en/vps) - [Dedicated Servers](https://ishosting.com/en/dedicated) - [Storage](https://ishosting.com/en/storage) - [VPN](https://ishosting.com/en/vpn) - [Special Offers](https://ishosting.com/en/special-offers) - --- - **Company** Company - [About Us](https://ishosting.com/en/about) - [Data Centers](https://ishosting.com/en/datacenters) - [Blog](https://blog.ishosting.com/en) - [Contacts](https://ishosting.com/en/about#offices) - --- - **Information** Information - [Knowledge Base](https://help.ishosting.com/en) - [Support](https://ishosting.com/en/support) - [Payments Methods](https://ishosting.com/en/payment-methods) - --- - **Account** Account - [Create Account](https://my.ishosting.com/en/register) --- © 2026 WEBRAIN OÜ, Harju maakond, Tallinn, Kesklinna linnaosa, Endla tn 4, 10142 - [![](https://blog.ishosting.com/hs-fs/hubfs/raw_assets/public/ishosting-theme/images/rating-sm.png?width=328&height=70&name=rating-sm.png) ![](https://blog.ishosting.com/hs-fs/hubfs/raw_assets/public/ishosting-theme/images/rating.png?width=421&height=70&name=rating.png)](https://hostadvice.com/hosting-company/ishosting-reviews/#main-info) --- - [Terms of Use](https://ishosting.com/en/terms-of-use) - [Privacy Policy](https://ishosting.com/en/privacy-policy) - [KYC Policy](https://ishosting.com/en/kyc-policy) - [SLA](https://ishosting.com/en/service-level-agreement) - [AUP](https://ishosting.com/en/acceptable-use-policy) - en - [en](https://blog.ishosting.com/en) - [ru](https://blog.ishosting.com/ru/self-hosted-dify) ```json { "@context" : "https://schema.org", "@type" : "BlogPosting", "abstract" : "Install Dify.AI on a VPS in 20 minutes: Docker setup, SSL, Ollama for local models, and backups. From $21.24/mo vs. $59/mo on Dify Cloud. Full commands included.", "alternativeHeadline" : "Self-Host Dify.AI on a VPS: Install & Production Guide", "articleSection" : "Technology", "author" : { "@type" : "Organization", "name" : "is*hosting team", "sameAs" : [ "https://www.linkedin.com/company/is-hosting", "https://twitter.com/ishostingcom", "https://www.instagram.com/is.hosting" ], "url" : "https://blog.ishosting.com/en/author/team-ishosting" }, "dateModified" : "2026-07-21T07:32:31.000Z", "datePublished" : "2026-05-14T08:00:00.000Z", "description" : "Install Dify.AI on a VPS in 20 minutes: Docker setup, SSL, Ollama for local models, and backups. From $21.24/mo vs. $59/mo on Dify Cloud. Full commands included.", "headline" : "How to Self-Host Your AI Workflow Platform: Dify.AI on a VPS", "image" : [ { "@type" : "ImageObject", "height" : 1348, "name" : "How to Self-Host Your AI Workflow Platform: Dify.AI on a VPS", "url" : "https://25913237.fs1.hubspotusercontent-eu1.net/hubfs/25913237/blog/self-hosted-dify/self-hosted-dify.png", "width" : 2396 } ], "inLanguage" : "en", "mainEntityOfPage" : { "@id" : "https://blog.ishosting.com/en/self-hosted-dify", "@type" : "WebPage" }, "publisher" : { "@type" : "Organization", "address" : [ { "@type" : "PostalAddress", "addressCountry" : "EE", "addressLocality" : "Tallinn", "addressRegion" : "Harju maakond", "postalCode" : "10120", "streetAddress" : "Kesklinna linnaosa, Tuukri tn 19-315" }, { "@type" : "PostalAddress", "addressCountry" : "GB", "addressLocality" : "London", "addressRegion" : "England", "postalCode" : "W1W 7LT", "streetAddress" : "85 Great Portland Street, First Floor" } ], "description" : "is*hosting is an IaaS provider since 2005. We provide VPS, VPN, dedicated servers and data storage to help you achieve your biggest dreams.", "email" : "sales@ishosting.com", "foundingDate" : "2005", "legalName" : "WEBRAIN OÜ", "logo" : { "@type" : "ImageObject", "height" : 26, "url" : "https://help.ishosting.com/hubfs/logo-ishosting.png", "width" : 138 }, "name" : "is*hosting" }, "thumbnailUrl" : "https://25913237.fs1.hubspotusercontent-eu1.net/hubfs/25913237/blog/self-hosted-dify/self-hosted-dify.png", "timeRequired" : "PT8M", "url" : "https://blog.ishosting.com/en/self-hosted-dify", "wordCount" : 2818 } ``` ```json { "@context" : "https://schema.org", "@type" : "BreadcrumbList", "itemListElement" : [ { "@type" : "ListItem", "item" : "https://blog.ishosting.com/en", "name" : "Blog", "position" : 1 }, { "@type" : "ListItem", "item" : "https://blog.ishosting.com/en/tag/technology", "name" : "Technology", "position" : 2 }, { "@type" : "ListItem", "item" : "https://blog.ishosting.com/en/self-hosted-dify", "name" : "How to Self-Host Your AI Workflow Platform: Dify.AI on a VPS", "position" : 3 } ] } ``` ```json { "@context" : "https://schema.org", "@type" : "BlogPosting", "author" : { "@type" : "Person", "name" : "is*hosting team", "url" : "https://blog.ishosting.com/en/author/team-ishosting" }, "dateModified" : "2026-07-21T07:32:31.733Z", "datePublished" : "2026-05-14T08:00:00.000Z", "headline" : "Self-Host Dify.AI on a VPS: Install & Production Guide", "image" : [ "https://blog.ishosting.com/hubfs/blog/self-hosted-dify/self-hosted-dify.png" ], "mainEntityOfPage" : { "@id" : "https://blog.ishosting.com/en/self-hosted-dify", "@type" : "WebPage" }, "publisher" : { "@type" : "Organization", "logo" : { "@type" : "ImageObject", "url" : "https://blog.ishosting.com/hubfs/logo-ishosting.png" }, "name" : "WEBRAIN OÜ" } } ```