Dify Docs home page
English
Search...
⌘K
Ask AI
Blog
Dify
Dify
Search...
Navigation
Models Integration
Integrate Open Source Models from Replicate
Documentation
Plugin Development
API Access
Resources
Getting Started
Welcome to Dify
Dify Community
Dify Cloud
Dify Premium on AWS
Dify for Education
API Access
Guide
Model Configuration
Application Orchestration
Workflow
Knowledge
Publishing
Annotation
Monitoring
Tools
Collaboration
Management
Workshop
Introduction
Basic
Intermediate
Community
Seek Support
Become a Contributor
Contributing to Dify Documentation
Plugins
Introduction
Quick Start
Manage Plugins
Schema Specification
Best Practice
Publish Plugins
FAQ
Development
Backend
Models Integration
Integrate Open Source Models from Hugging Face
Integrate Open Source Models from Replicate
Integrate Local Models Deployed by Xinference
Connecting to OpenLLM Local Deployed Models
Integrating with LocalAI for Local Model Deployment
Integrate Local Models Deployed by Ollama
Integrate Models on LiteLLM Proxy
Integrate Local Models Deployed by GPUStack
Integrate Models from AWS Bedrock
Migration
Learn More
Use Cases
Extended Reading
FAQ
Policies
License
User Agreement
Models Integration
Integrate Open Source Models from Replicate
Copy page
Dify supports accessing
Language models
and
Embedding models
on Replicate. Language models correspond to Dify’s reasoning model, and Embedding models correspond to Dify’s Embedding model.
Specific steps are as follows:
You need to have a Replicate account (
registered address
).
Get API Key (
get address
).
Pick a model. Select the model under
Language models
and
Embedding models
.
Add models in Dify’s
Settings > Model Provider > Replicate
.
The API key is the API Key set in step 2. Model Name and Model Version can be found on the model details page:
Edit this page
|
Report an issue
Was this page helpful?
Yes
No
Integrate Open Source Models from Hugging Face
Integrate Local Models Deployed by Xinference
Assistant
Responses are generated using AI and may contain mistakes.