# Replicate

## Get Started

- [Run a model from Node.js](https://replicate.com/docs/get-started/nodejs): Get started with a few lines of JavaScript.
- [Run a model from Google Colab](https://replicate.com/docs/get-started/google-colab): Run any public Replicate model in a notebook on Google Colab.
- [Run a model from Python](https://replicate.com/docs/get-started/python): The language of the machine learning world.
- [Fine-tune an image model](https://replicate.com/docs/get-started/fine-tune-with-flux): Train your own fine-tuned FLUX model to generate new images of yourself.
- [Deploy a custom model](https://replicate.com/docs/get-started/deploy-a-custom-model): Learn to build, deploy, and scale your own custom model on Replicate.

## Topics

- [Billing](https://replicate.com/docs/topics/billing/index): Replicate is a pay-as-you-go platform. You are billed for the compute time used to run your models.
- [Deployments](https://replicate.com/docs/topics/deployments/index): Use deployments for more control over how your models run.
- [Models](https://replicate.com/docs/topics/models/index): A model is a trained, packaged, and published software program that accepts inputs and returns outputs.
- [Organizations](https://replicate.com/docs/topics/organizations/index): Organizations let you share access to models, API tokens, billing, dashboards, and more.
- [Predictions](https://replicate.com/docs/topics/predictions/index): Whenever you run a model, you're creating a prediction. Learn about inputs, outputs, files, and other aspects of the prediction lifecycle.
- [API tokens](https://replicate.com/docs/topics/security/api-tokens): API tokens are used to authenticate your requests to the Replicate API. Learn how to create, manage, and secure your tokens.
- [Subprocessors](https://replicate.com/docs/topics/site-policy/subprocessors): The Replicate subprocessor list identifies subprocessors authorized to subprocess customer or personal data on behalf of Replicate to provide our services.
- [Webhooks](https://replicate.com/docs/topics/webhooks/index): Webhooks provide real-time updates about your predictions.
- [Prepaid credit](https://replicate.com/docs/topics/billing/prepaid-credit): How prepaid credit works
- [Create a deployment](https://replicate.com/docs/topics/deployments/create-a-deployment): How to create your own custom model deployment
- [Run a model](https://replicate.com/docs/topics/models/run-a-model): Learn how to run a machine learning model in a web playground or with an API that uses Replicate.
- [Create a prediction](https://replicate.com/docs/topics/predictions/create-a-prediction): Learn how to create predictions on Replicate using the API.
- [Input files](https://replicate.com/docs/topics/predictions/input-files): How to use files as inputs when running a model
- [Set up webhooks](https://replicate.com/docs/topics/webhooks/setup-webhook): Set up webhooks to receive real-time updates about your predictions.
- [View deployments](https://replicate.com/docs/topics/deployments/view-deployments): How to view deployments you've created
- [Create a model](https://replicate.com/docs/topics/models/create-a-model): Details about creating models on Replicate
- [Output files](https://replicate.com/docs/topics/predictions/output-files): How to handle files that are generated by a model
- [Receive webhooks](https://replicate.com/docs/topics/webhooks/receive-webhook): Receive and manage webhooks from Replicate.
- [Monitor a deployment](https://replicate.com/docs/topics/deployments/monitor-a-deployment): Track deployment performance and health
- [Prediction lifecycle](https://replicate.com/docs/topics/predictions/lifecycle): How to check the status of a prediction, what different statuses mean, and how to monitor predictions.
- [Verify webhooks](https://replicate.com/docs/topics/webhooks/verify-webhook): Learn how to verify webhooks from Replicate.
- [Delete a deployment](https://replicate.com/docs/topics/deployments/delete-a-deployment): How to delete a deployment
- [Publish a model](https://replicate.com/docs/topics/models/publish-a-model): Best practices for publishing reliable, fast, and user-friendly models.
- [Model versions](https://replicate.com/docs/topics/models/versions): Changes to models are published as new versions
- [Share a prediction](https://replicate.com/docs/topics/predictions/share-a-prediction): How to share a prediction on Replicate
- [Test your webhook code](https://replicate.com/docs/topics/webhooks/testing-webhook-code): Learn how to set up local testing for webhooks from Replicate.
- [Model hardware](https://replicate.com/docs/topics/models/hardware): How to change the hardware for models and deployments.
- [Official models](https://replicate.com/docs/topics/models/official-models): Learn about official models on Replicate
- [Rate limits](https://replicate.com/docs/topics/predictions/rate-limits)
- [Community models](https://replicate.com/docs/topics/models/community-models): Learn about community models and how they differ from official models
- [Safety checking](https://replicate.com/docs/topics/predictions/safety-checking)
- [Private models vs. public models](https://replicate.com/docs/topics/models/private-models): Explanation of public vs. private models on Replicate, and considerations for changing a model from public to private and vice versa.
- [Data retention](https://replicate.com/docs/topics/predictions/data-retention): How Replicate handles data that you provide when running a model, including input parameters, input and output files, and logs.
- [Use a model as a training destination](https://replicate.com/docs/topics/models/models-as-training-destinations): Learn about models as training destinations for fine-tunes.
- [Secrets](https://replicate.com/docs/topics/predictions/secrets): Learn how to provide secret inputs when running models that require sensitive information like API keys and passwords.
- [Delete a model or model version](https://replicate.com/docs/topics/models/delete-a-model): Learn how to delete models and model versions.
- [Secrets](https://replicate.com/docs/topics/models/secrets): Learn how to create and use secret inputs in your Cog models to handle sensitive information like API keys and passwords securely.
- [Streaming output](https://replicate.com/docs/topics/predictions/streaming): Learn how to consume server-sent event streams (SSEs) from Replicate models.

## Guides

- [Dynamic image caching with Cloudflare Workers](https://replicate.com/docs/guides/extend/cloudflare-image-cache): Learn how to use Cloudflare and Replicate to build a fast and flexible hosting service for generated images.
- [Build a website with Next.js](https://replicate.com/docs/guides/run/nextjs): Build a Next.js web app that uses Replicate to run models and receive webhooks as they run.
- [Build a Discord bot with Python](https://replicate.com/docs/guides/run/discord-bot): Use Python to build and deploy a Discord chat bot application that uses Flux Schnell via Replicate to generate images from text prompts.
- [Build an app with SwiftUI](https://replicate.com/docs/guides/run/swiftui): Learn how to build a SwiftUI app that uses Replicate to run a machine learning model.
- [Push a model using GitHub Actions](https://replicate.com/docs/guides/build/push-a-model-using-github-actions): Learn how to use GitHub Actions to build and push your model to Replicate as part of your CI/CD pipeline.
- [Craft generative AI workflows with ComfyUI](https://replicate.com/docs/guides/extend/comfyui): Learn ComfyUI then run it with an API
- [Set up a CI/CD pipeline for your model](https://replicate.com/docs/guides/build/continuous-model-deployment): Set up a CI/CD pipeline for your Cog model so you can safely and easily publish new versions of your model as part of your GitHub-based development workflow.
- [Push your own model](https://replicate.com/docs/guides/build/push-a-model): Package your own custom model using Cog and push it to Replicate as a cloud API.
- [Push a Transformers model](https://replicate.com/docs/guides/build/push-a-transformers-model): Learn how to push a Hugging Face Transformers language model to Replicate.
- [Push a Diffusers model](https://replicate.com/docs/guides/build/push-a-diffusers-model): Learn how to push a Hugging Face Diffusers image generation model to Replicate as a scalable API.
- [Build a realtime speech app with OpenAI, Cloudflare, and Replicate](https://replicate.com/docs/guides/extend/openai-realtime): Use OpenAI's Realtime WebRTC API to do function calling right in your browser.
- [Optimize models with Pruna](https://replicate.com/docs/guides/build/optimize-models-with-pruna): Learn how to use Pruna AI's open-source framework to compress and optimize your models for faster inference and lower costs on Replicate.
- [Build a webhook notifier with Val Town](https://replicate.com/docs/guides/extend/build-a-webhook-notifier-with-val-town): Build a simple serverless cloud function to receive webhooks from Replicate and send notifications via email.
- [Get a GPU machine on Brev](https://replicate.com/docs/guides/build/get-a-gpu-on-brev): Learn how to get your own GPU machine in the cloud on Brev.dev, so you can iterate on your model and test it before pushing it to Replicate.
- [Get a GPU on Lambda Labs](https://replicate.com/docs/guides/build/get-a-gpu-on-lambda-labs): Learn how to get your own GPU machine in the cloud, so you can package your model and push it to Replicate.
- [Working with LoRAs](https://replicate.com/docs/guides/extend/working-with-loras): Use LoRAs to combine multiple styles in a single output image.
- [Best practices for Replicate models](https://replicate.com/docs/guides/build/model-best-practices): A guide to making a fast and usable model
- [Speed up models with torch.compile](https://replicate.com/docs/guides/build/torch-compile): Learn how to use PyTorch's torch.compile with Replicate to speed up your models.
- [Make art with Stable Diffusion](https://replicate.com/docs/guides/run/make-art-with-stable-diffusion): An exploration of Stable Diffusion and its applications
- [Upscale images with AI models](https://replicate.com/docs/guides/run/upscale-images-with-ai-models): Learn how to upscale images

## Reference

- [How does Replicate work?](https://replicate.com/docs/reference/how-does-replicate-work): 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.
- [Client libraries](https://replicate.com/docs/reference/client-libraries): Client libraries for using Replicate's API: Python, Node.js, Go, MCP, and more.
- [HTTP API](https://replicate.com/docs/reference/http): The API documentation for the API.
- [OpenAPI schema](https://replicate.com/docs/reference/openapi): The OpenAPI schema reference for Replicate's HTTP API.
- [llms.txt](https://replicate.com/docs/reference/llms-txt): A text file containing an overview of Replicate's documentation for Large Language Models.
- [Error codes](https://replicate.com/docs/reference/error-codes): A list of common error codes returned by Replicate's API
- [Replicate's MCP server](https://replicate.com/docs/reference/mcp): Connect tools like Claude Desktop, Claude Code, and Cursor to Replicate's HTTP API
- [Open source at Replicate](https://replicate.com/docs/reference/open-source): A collection of open-source projects and tools created and maintained by the Replicate team.