Replicate Docs

Replicate lets you run machine learning models with a cloud API, without having to understand the intricacies of machine learning or manage your own infrastructure.

You can run open-source models that other people have published, or bring your own training data to create fine-tuned models, or build and publish custom models from scratch.

Topics

Learn about the building blocks that make Replicate work

Models
Models

A model is a trained, packaged, and published software program that accepts inputs and returns outputs.

Predictions
Predictions

Whenever you run a model, you're creating a prediction. Learn about inputs, outputs, files, and other aspects of the prediction lifecycle.

Deployments
Deployments

Use deployments for more control over how your models run.

Webhooks
Webhooks

Webhooks provide real-time updates about your predictions.

Organizations
Organizations

Organizations let you share access to models, API tokens, billing, dashboards, and more.

Billing
Billing

Replicate is a pay-as-you-go platform. You are billed for the compute time used to run your models.

Guides

Ready to build something? Check out these guides to level up your AI skills

NextjsNextjs
Build a website with Next.js

Build a Next.js web app that uses Replicate to run models and receive webhooks as they run.

Discord botDiscord bot
Build a Discord bot with Python

Use Python to build and deploy a Discord chat bot application that uses Flux Schnell via Replicate to generate images from text prompts.

SwiftuiSwiftui
Build an app with SwiftUI

Learn how to build a SwiftUI app that uses Replicate to run a machine learning model.

Push a modelPush a model
Push your own model

Package your own custom model using Cog and push it to Replicate as a cloud API.

Push a diffusers modelPush a diffusers model
Push a Diffusers model

Learn how to push a Hugging Face Diffusers image generation model to Replicate as a scalable API.

Push a transformers modelPush a transformers model
Push a Transformers model

Learn how to push a Hugging Face Transformers language model to Replicate.

Videos

Prefer to learn by watching videos? Check out some recent demos from our YouTube channel

Thumbnail for FLUX.1 Schnell vs FLUX.1 Dev

FLUX.1 Schnell vs FLUX.1 Dev

Explore the differences between Flux Schnell and Flux Dev image generation models and learn how to enhance image quality effectively.

6 minutes

Thumbnail for David Attenborough is now narrating my life

David Attenborough is now narrating my life

Here's a GPT-4-vision + ElevenLabs python script so you can star in your own Planet Earth.

2 minutes

Thumbnail for Write your shell commands in English

Write your shell commands in English

Use language models like GPT-4o and Llama to write one-liner shell commands, then execute them.

4 minutes

Thumbnail for Introducing create-replicate-app

Introducing create-replicate-app

A quick and easy way to run Replicate models with Node.js

3 minutes

Thumbnail for Using webhooks with Replicate's API

Using webhooks with Replicate's API

Learn how to receive webhooks from Replicate's API when running predictions and trainings.

14 minutes

View more videos on YouTube