Minimum Learning Cost
Drag, drop, ship. Build the way you’d sketch it on a canvas.
No new concepts to learn.
Cloud
The Managed Platform for Building Production AI Applications.
Build, ship, and scale AI applications without starting from scratch. Built so you can confidently share what you build.
Everything ready.
Day one.
Maximum Harness
Confidence to share what you build.
Visual logic you can inspect, test, and trust before it goes to your team.
Team-Ready
Built for your team, not just for you.
Shared workspaces, team roles, and activity logs out of the box.
From Idea to Production.
All in One Place.
Build
Visual workflow builder. Drag, drop, and wire AI capabilities into reliable workflows.
Connect
Connect global LLMs, your knowledge data, and tools from the Dify Marketplace. Model-agnostic — swap providers anytime.
Ship
Test and publish in one click. Available as a webapp, website embed, API, or MCP server.
Monitor
Usage, latency, cost, errors — visible at a glance. Iterate based on what’s actually running.
Built for Every Builder.
Every Approach.
No Code
- Start with a template.
- Customize without complex coding — or just edit the prompt directly to make it yours.
Low Code
- Add forms to collect inputs.
- Use variables to pass values between steps.
- No full code required.
Code
- Drop into a code node for specific business logic.
- Full flexibility, when you need it.
Everything You Need.
Already Plugged In.
Models
Connect any LLM provider — proprietary or open-source. OpenAI (ChatGPT), Anthropic (Claude), Google (Gemini), xAI (Grok), and more.
Tools
Plug in tools from the Dify Marketplace. Slack, Perplexity, ComfyUI, Firecrawl, and 200+ more.
Knowledge
Bring your own data — PDFs, web pages, databases. Or pull from the Dify Marketplace’s data sources and pre-process with tools like Tavily Search.
Built to Grow with What You Build.
Bill Annually Save 17%
Sandbox
For trying out Dify's core features.
Start for FreeFree
- 200 message creditsMessage credits are provided to help you easily try out different models from OpenAI, Anthropic, Gemini, xAI, DeepSeek, Tongyi in Dify. Credits are consumed based on the model type. Once they're used up, you can switch to your own API key.
- 1 Team Workspace
- 1 Team Member
- 5 Apps
- 50 Knowledge DocumentsQuota on the number of documents imported from the Knowledge Data Source.
- 50MB Knowledge Data StorageDocuments with the High Quality indexing mode will consume Knowledge Data Storage resources. When Knowledge Data Storage reaches the limit, new documents will not be uploaded.
- 10 Knowledge Request/minSpecifies the total number of actions a workspace can perform per minute within the knowledge base, including dataset creation, deletion, updates, document uploads, modifications, archiving, and knowledge base queries. This metric is used to evaluate the performance of knowledge base requests. For example, if a Sandbox user performs 10 consecutive hit tests within one minute, their workspace will be temporarily restricted from performing the following actions for the next minute: dataset creation, deletion, updates, and document uploads or modifications.
- Standard Document Processing
- 3,000 Trigger EventsThe number of events that automatically start workflows through Plugin, Schedule, or Webhook triggers.
- Up to 2 Triggers/workflow
- Standard Workflow ExecutionWorkflow execution queue priority and speed.
- 10 Annotation Quota LimitsManual editing and annotation of responses provides customizable high-quality question-answering abilities for apps. (Applicable only in Chat apps)
- 30 Days Log History
- 5,000 API Rate Limit/month
- 200 message credits
Professional
PopularFor independent developers and small teams building production AI apps.
Start Building$590per workspace / year- 5,000 message credits / monthMessage credits are provided to help you easily try out different models from OpenAI, Anthropic, Gemini, xAI, DeepSeek, Tongyi in Dify. Credits are consumed based on the model type. Once they're used up, you can switch to your own API key.
- 1 Team Workspace
- 3 Team Members
- 50 Apps
- 500 Knowledge DocumentsQuota on the number of documents imported from the Knowledge Data Source.
- 5GB Knowledge Data StorageDocuments with the High Quality indexing mode will consume Knowledge Data Storage resources. When Knowledge Data Storage reaches the limit, new documents will not be uploaded.
- 100 Knowledge Request Rate Limit/minSpecifies the total number of actions a workspace can perform per minute within the knowledge base, including dataset creation, deletion, updates, document uploads, modifications, archiving, and knowledge base queries. This metric is used to evaluate the performance of knowledge base requests. For example, if a Sandbox user performs 10 consecutive hit tests within one minute, their workspace will be temporarily restricted from performing the following actions for the next minute: dataset creation, deletion, updates, and document uploads or modifications.
- Priority Document Processing
- 20,000 Trigger Events / monthThe number of events that automatically start workflows through Plugin, Schedule, or Webhook triggers.
- Unlimited Triggers / workflow
- Faster Workflow ExecutionWorkflow execution queue priority and speed.
- 2,000 Annotation Quota LimitsManual editing and annotation of responses provides customizable high-quality question-answering abilities for apps. (Applicable only in Chat apps)
- Unlimited Log History
- No Dify API Rate Limit
- 5,000 message credits / month
Team
For medium-sized teams needing collaboration and higher throughput.
Get Started$1590per workspace / year- 10,000 message credits / monthMessage credits are provided to help you easily try out different models from OpenAI, Anthropic, Gemini, xAI, DeepSeek, Tongyi in Dify. Credits are consumed based on the model type. Once they're used up, you can switch to your own API key.
- 1 Team Workspace
- 50 Team Members
- 200 Apps
- 1,000 Knowledge DocumentsQuota on the number of documents imported from the Knowledge Data Source.
- 20GB Knowledge Data StorageDocuments with the High Quality indexing mode will consume Knowledge Data Storage resources. When Knowledge Data Storage reaches the limit, new documents will not be uploaded.
- 1,000 Knowledge Request Rate Limit/minSpecifies the total number of actions a workspace can perform per minute within the knowledge base, including dataset creation, deletion, updates, document uploads, modifications, archiving, and knowledge base queries. This metric is used to evaluate the performance of knowledge base requests. For example, if a Sandbox user performs 10 consecutive hit tests within one minute, their workspace will be temporarily restricted from performing the following actions for the next minute: dataset creation, deletion, updates, and document uploads or modifications.
- Top Priority Document Processing
- Unlimited Trigger EventsThe number of events that automatically start workflows through Plugin, Schedule, or Webhook triggers.
- Unlimited Triggers / workflow
- Priority Workflow ExecutionWorkflow execution queue priority and speed.
- 5,000 Annotation Quota LimitsManual editing and annotation of responses provides customizable high-quality question-answering abilities for apps. (Applicable only in Chat apps)
- Unlimited Log History
- No Dify API Rate Limit
- 10,000 message credits / month
What Teams are Shipping in Their Words.
“Dify allows our teams to prototype and deploy AI applications to the market much faster compared to building everything from scratch. It is the best tool for agile initial prototyping.”
Alex Chan
AI Engineer Lead
“As a decision-maker who evaluates AI platforms, we demand absolute control over token costs and system architecture, while simultaneously needing to bridge existing data silos. Dify perfectly balances both. It gives us the security of complete architectural control, while serving as an exceptional AI middleware hub. Its orchestration capabilities seamlessly integrate AI with our current internal databases and workflows, safely turning our enterprise AI strategy into reality.”
Stephen Thorne
Head of Architecture
“Our go-to-market teams always have incredible ideas for AI automations, but were lost in translation. Dify bridges that gap perfectly. It allows us to turn complex business logic into highly functional workflows without starting everything from scratch. Now, our go-to-market teams can bring their imagination to life.”
Emily Carter
Sales Director
Start Building Today.
Ship your first AI app in minutes.