Replicate · Ai Models

Replicate HTTP API / Create a model

Create a model. Example cURL request: The response will be a model object in the following format: Note that there is a limit of 1,000 models per account. For most purposes, we recommend using a single model and pushing new versions of the model as you make changes to it.

Private Gateway connection

Data below comes from the configured private Gateway. Provider activation remains governed by its evidence and policy gates.

unverifiedRequest shape unavailableUnverified

Published API evidence

Public metadata only. Response bodies, credentials, and internal review notes are never displayed.

No verification date is claimed. No response capture is claimed.

Request parameters

cover_image_url body · optional
A URL for the model's cover image. This should be an image file.
description body · optional
A description of the model. Example: "Detect hot dogs in images"
github_url body · optional
A URL for the model's source code on GitHub. Example: "https://github.com/alice/hot-dog-detector"
hardware body · required
The SKU for the hardware used to run the model. Possible values can be retrieved from the `hardware.list` endpoint. Example: "cpu"
license_url body · optional
A URL for the model's license.
name body · required
The name of the model. This must be unique among all models owned by the user or organization. Example: "hot-dog-detector"
owner body · required
The name of the user or organization that will own the model. This must be the same as the user or organization that is making the API request. In other words, the API token used in the request must belong to this user or organization. Example: "alice"
paper_url body · optional
A URL for the model's paper. Example: "https://arxiv.org/abs/2504.17639"
visibility body · required
Whether the model should be public or private. A public model can be viewed and run by anyone, whereas a private model can be viewed and run only by the user or organization members that own the model. Example: "public"

Provider docs How to run it