API documentation

This is a beta release and will likely change! Please share your feedback in our Discord server or email us at team@replicate.com. 🙌

Replicate's API lets you run machine learning models in the cloud from your own code, without having to set up any infrastructure. You can run models from apps, notebooks, evaluation scripts, or anywhere else you want to use machine learning.

You can run predictions on your own models, or other public models that have opted in (like pixray/text2image).



In case you need ideas or some example code, here are some things built with the API:


Are your models taking a while to start up? We spin them down after 10 minutes of inactivity, so they may take a bit of time to start back up. If you want your models to stay running so you get instant predictions, contact us!

Having any other trouble using the API? Let us know and we'll help. Chat with us in Discord or send us an email at team@replicate.com.

Replicate Reproducible machine learning