Replicate

http

Run machine learning models on the Replicate platform using an API token.

Install

npx

```bash

run_prediction Run a prediction on Replicate using a model version and input parameters
get_prediction Get the status and output of a prediction by its ID
cancel_prediction Cancel a running prediction by its ID
list_models List available models on Replicate with optional search query
get_model Get details of a specific model by its owner and name
list_collections List curated collections of models on Replicate
get_collection Get models in a specific collection by its slug

★ 95 GitHub stars