Overview

Replicate is a cloud-based platform designed to simplify the deployment and scaling of machine learning models. It provides users with access to a vast library of open-source AI models, enabling developers to run and fine-tune these models with minimal coding effort. The platform aims to democratize machine learning by making it accessible to a broader audience, including software engineers, data scientists, and product managers.

Dify supports accessing Language models and Embedding models on Replicate. Language models correspond to Dify's reasoning model, and Embedding models correspond to Dify's Embedding model.

Configure

1. You need to have a Replicate account.
2. Get API Key.
3. Pick a model. Select the model under Language models and Embedding models.
4. Add models in Dify's Settings -> Model Provider -> Replicate.

The API key is the API Key set in step 2. Model Name and Model Version can be found on the model details page: