Reference

Create Prediction

Run machine learning models on your data by submitting inputs to a specific model version and receiving predictions. This lets you automate AI-powered tasks without managing your own infrastructure.

Get Account Information

Retrieve details about your authenticated Replicate account, including billing information, usage limits, and account settings. This helps you understand your account status and capacity for running AI model predictions.

Get Model Details

Retrieve detailed information about a specific AI model including its input requirements, available versions, and parameters needed to run predictions.

Get Prediction

Retrieve the current status and results of an AI prediction task by its unique ID, allowing you to check on in-progress jobs or collect completed outputs.

List All Predictions

Retrieve a paginated list of all predictions you've created, allowing you to review your AI model run history and track past results.

List Public Models

Browse and discover available AI models on Replicate with sorting and pagination options to find the right model for your project needs.

Cancel Prediction

Stop an in-progress prediction to free up resources and halt execution immediately.

Cancel Training

Stop an active training job on Replicate when you no longer need the results or want to avoid additional costs. This lets you halt model training operations mid-process without completing them.

Create Deployment

Deploy a machine learning model to production with automatic scaling, enabling you to run predictions at scale without manual infrastructure management.

Create File

Upload files to Replicate with optional metadata to use as inputs for AI model processing. This enables you to provide custom content for machine learning operations without managing external storage infrastructure.

Create Model

Create a new machine learning model on Replicate by specifying the owner, name, visibility settings, and required hardware. This sets up a destination model before training or deploying custom AI workflows.

Create Model Prediction

Run AI model inference on demand to generate predictions, transformations, or outputs from your data without managing servers or infrastructure.

Create Prediction

Submit a prediction request to your private Replicate Deployment to generate outputs based on your custom AI model, waiting for the results if needed. This is ideal when you want to use your own fine-tuned models rather than public ones.

Create Training Job

Create a custom training job to fine-tune an AI model with your own dataset, enabling you to adapt pre-trained models to your specific business needs. This lets you build specialized models that perform better on your unique use cases without starting from scratch.

Delete Deployment

Remove a deployment from your Replicate account when you no longer need it, helping you keep your infrastructure clean and organized. This allows you to delete deployments that are offline and meet the retention requirements.

Delete File

Removes a file from your Replicate storage by its ID, freeing up space and keeping your file library organized. Useful when you no longer need generated assets or want to clean up outdated content.

Get Deployment Details

Retrieve detailed information about a specific deployment including its configuration, release settings, and hardware specifications. This helps you monitor and manage your AI model deployments.

Get File Details

Retrieve detailed information about a file you've uploaded, including metadata and access URLs, so you can verify file properties before using them in other operations.

Get model collection

Retrieves detailed information about a specific collection of AI models, including all models within that collection. Use this to explore and understand available models in organized groups for your AI projects.

Get Model README

Retrieve the README documentation for an AI model in Markdown format to understand its capabilities, inputs, and how to use it before running predictions.

Get Model Version

Retrieve detailed information about a specific version of an AI model, including its schema, metadata, and configuration settings. Use this to understand what inputs a model version accepts and how to interact with it.

Get Webhook Signing Secret

Get the signing secret used to verify that webhook notifications from Replicate are authentic and haven't been tampered with. This is essential for securely processing webhook events in your application.

List Available Hardware

Retrieve all available hardware options (GPUs, TPUs, and other compute resources) that you can use to run AI models on Replicate, helping you choose the right infrastructure for your projects.

List deployments

Retrieve a list of all your model deployments and their current configurations to monitor what's running in production and track your deployed models.

List Files

Retrieve a paginated list of your uploaded files sorted by most recent first, allowing you to browse and manage all files in your account.

List model collections

Retrieve all available model collections from Replicate, which are curated groupings of related AI models organized by category or use case. Use this to explore what types of models are available and browse model organization without needing specific model names.

List model examples

Retrieve example predictions and sample inputs for a specific AI model to understand how it works and what outputs to expect. This helps you learn the correct format and requirements before running your own predictions.

List Model Versions

Retrieve all available versions of a specific AI model, sorted from newest to oldest, so you can see the complete version history and choose the right iteration for your needs.

List Training Jobs

Retrieve a complete list of all your AI model training jobs with pagination support, allowing you to review training history and monitor the progress of model training activities.

Search Models and Collections

Find AI models and collections on Replicate by searching with keywords or descriptions, helping you discover the right tools for your specific task. This lets you quickly identify available models without browsing through all options.

Update Model Metadata

Update your AI model's documentation, description, and links to keep information current and help users understand what your model does. This ensures your model is properly documented and discoverable with accurate information.