Replicate logo
Explore
Pricing
Docs
Blog
Changelog
Menu
Dashboard
Explore
Pricing
Docs
Blog
Changelog
Docs
Search documentation
⌘
K
Get started
Collapse sidebar
Run a model from Node.js
Run a model from Python
Run a model from Google Colab
Build a website with Next.js
Build an app with SwiftUI
Build a Discord bot
Guides
Deploy a custom model
Fine-tune a language model
Fine-tune an image model
What is fine-tuning?
Get a GPU machine
Push a Diffusers model
Push a model using GitHub Actions
Push a model to Replicate
Push a Transformers model
Reference
Client libraries
Deployments
How does Replicate work?
HTTP API
Streaming
Webhooks
Docs
Replicate makes it easy to run machine learning models in the cloud from your own code.
Run models
Run a model from Node.js
– Get started with a few lines of JavaScript
Run a model from Python
– The language of the machine learning world
Run a model from Google Colab
– Cloud-hosted Jupyter notebooks
Build a website with Next.js
– React + Node.js for rapid development
Build an app with SwiftUI
– Develop for macOS, iOS, and (soon) visionOS
Build a Discord bot
– Chat-based image generation
Push models
Push a model
– Use Cog to build and push your own models
Deploy a custom model
– Collaborate privately with your team
Fine-tune an image model
– Train a new model on faces or styles
Get a GPU machine
– Access powerful cloud compute
Push a Diffusers model
– Stable Diffusion and countless others
Push a Transformers model
– Attention is all you need
Push a model using GitHub Actions
– Continuous model deployment
Learn more
How does Replicate work?
– A guide to core concepts
Using Webhooks
– Get realtime updates about your predictions
Client libraries
– JavaScript, Python, Ruby, Swift, Elixir
HTTP API reference