Thousands of businesses are building their AI products on Replicate. Your team can deploy an AI feature in a day and scale to millions of users, without having to be machine learning experts.

Nov 20, 2025 · Discover and share machine learning models that you can run in the cloud using Replicate.

You can package your own restoration model with Cog and push it to Replicate. This lets you set up inputs, outputs, and configuration while deciding whether to keep it private or share it with others.

You only pay for what you use on Replicate. Some models are billed by time, others by input and output.

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.

Explore Replicate's "Try for Free" collection. Access top AI models for video generation, image creation, and photo restoration without a credit card.

Deploy a custom model Learn to build, deploy, and scale your own custom model on Replicate.

We're a bunch of hackers, engineers, researchers, and artists. We obsess about the details of API design and the right words for things. We're defining how AI works so we'd better get it right. We …

Prerequisites Step 1: Create a GitHub Actions workflow Step 2: Set a Replicate API token Step 3: Set a Cog API token Step 4: Set an Anthropic API key Step 5: Run the workflow Step 6 (Optional): …

This model costs approximately $0.0029 to run on Replicate, or 344 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.