Back to Directory
Replicate

Replicate

AI Models
Run thousands of open-source AI models via API — image generation, language models, speech recognition, video, and more. Pay only for what you use.
Available through Locus
MPP
WebsiteDocumentation

About Replicate

Review the Service identity, supported languages, protocol versions, and source metadata discovered by the directory.

Service details

Service Id
7d3c125e-fab8-47c2-ba6d-186fc3ba1e8e
Service origin
https://replicate.mpp.paywithlocus.com
ListedSeptember 24, 2026, 11:45 PM
Last checkedNovember 8, 2026, 11:15 PM

Protocol details

SourceOpenAPI

Endpoints

Endpoint details are saved from the OpenAPI document. Authentication requirements and prices are advertised information, not a verified payment or access guarantee. The document may contain additional endpoints.Open OpenAPI document
POST/replicate/get-model

Get Model

Retrieve metadata for a public Replicate model: description, hardware, latest version, run count, and links.
POST/replicate/get-prediction

Get Prediction

Retrieve the status and output of a prediction by ID. The provider lookup is free; Locus charges its $0.003 platform fee. Use this to check results for models that exceeded the 60s synchronous timeout in the run endpoint.
POST/replicate/list-models

List Models

Browse public Replicate models. Returns a paginated list with metadata. Use the cursor field for pagination.
POST/replicate/run

Run Model

Run any public Replicate model synchronously. The request blocks until the prediction completes (up to 60 seconds). Returns output directly in the response. If the model takes longer than 60s the response will include a prediction ID you can check with get-prediction.

Agent payments

These payment protocols and options are advertised by the Service for agent purchases.

MPP

Advertises MPP payments for one or more endpoints. Check the endpoint documentation for authentication requirements.