Browse published operations

List example predictions made using the model. These are predictions that were saved by the model author as illustrative examples of the model's capabilities. If you want all the examples for a model, use this operation. If you just want the model's default example, you can use the models.get operation instead, which includes a default_example object. Example cURL request: The response will be a pagination object containing a list of example predictions: Each item in the results list is a prediction object.

Example cURL request: The response will be a model object in the following format: The model object includes the input and output schema for the latest version of the model. Here's an example showing how to fetch the model with cURL and display its input schema with jq: This will return the following JSON object: The coverimageurl string is an HTTPS URL for an image file. This can be: - An image uploaded by the model author. - The output file of the example prediction, if the model author has not set a cover image. - The input file of the example prediction, if the model author has not set a cover image and the example prediction has no output file. - A generic fallback image. The defaultexample object is a prediction created with this model. The latestversion object is the model's most recently pushed version.

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.

Get the README content for a model. Example cURL request: The response will be the README content as plain text in Markdown format:

Example cURL request: The response will be a JSON array of model version objects, sorted with the most recent version first:

Example cURL request: The response will be the version object: Every model describes its inputs and outputs with OpenAPI Schema Objects in the openapischema property. The openapischema.components.schemas.Input property for the replicate/hello-world model looks like this: The openapi_schema.components.schemas.Output property for the replicate/hello-world model looks like this: For more details, see the docs on Cog's supported input and output types

Start a new training of the model version you specify. Example request body: Example cURL request: The response will be the training object: As models can take several minutes or more to train, the result will not be available immediately. To get the final result of the training you should either provide a webhook HTTPS URL for us to call when the results are ready, or poll the get a training endpoint until it has finished. When a training completes, it creates a new version of the model at the specified destination. To find some models to train on, check out the trainable language models collection.

Search for public models, collections, and docs using a text query. For models, the response includes all model data, plus a new metadata object with the following fields: - generated_description: A longer and more detailed AI-generated description of the model - tags: An array of tags for the model - score: A score for the model's relevance to the search query Example cURL request: Note: This search API is currently in beta and may change in future versions.

Create a prediction using an official model. If you're not running an official model, use the predictions.create operation instead. Example cURL request: The request will wait up to 60 seconds for the model to run. If this time is exceeded the prediction will be returned in a "starting" state and need to be retrieved using the predictions.get endpoint. For a complete overview of the deployments.predictions.create API check out our documentation on creating a prediction which covers a variety of use cases.

Create a prediction for the model version and inputs you provide. Example cURL request: The request will wait up to 60 seconds for the model to run. If this time is exceeded the prediction will be returned in a "starting" state and need to be retrieved using the predictions.get endpoint. For a complete overview of the predictions.create API check out our documentation on creating a prediction which covers a variety of use cases.