run_prediction
Run an AI model prediction on Replicate. Provide either a **model** identifier (e.g. `stability-ai/sdxl`) or a specific **version** ID. You can also target a **deployment** for production workloads. Use this to generate images, text, audio, or any output supported by the model.
list_hardware
List available hardware options on Replicate. Use these SKU values when creating models or deployments.
create_model
Create a new model on Replicate. The model acts as a container for versions that will be created through training or pushing.
list_files
List files that have been uploaded to Replicate. Files are used as inputs to models (images, audio, documents, etc.).
delete_deployment
Delete a deployment. The deployment must be offline and unused for at least 15 minutes.
create_deployment
Create a new production deployment for a model on Replicate. Deployments provide dedicated infrastructure with configurable hardware and auto-scaling.
search_models
Search for public models, collections, and documentation on Replicate. Returns results ranked by relevance.
cancel_prediction
Cancel a running prediction. Only predictions that are still in progress (starting or processing) can be canceled.
get_account
Get information about the currently authenticated Replicate account, including username, name, and account type.
list_trainings
List recent training jobs for your account, sorted by creation time (newest first).
get_model
Get details about a specific model on Replicate, including its description, latest version, run count, and input/output schema.
delete_file
Delete an uploaded file from Replicate.
get_collection
Get details about a specific collection, including all models in the collection.
list_model_versions
List all versions of a specific model. Each version represents a different iteration of the model with its own input/output schema.
get_deployment
Get details about a specific deployment, including its current release configuration, hardware, and scaling settings.
get_file
Get metadata for a specific uploaded file, including its size, type, checksums, and expiration time.
list_collections
List curated collections of models on Replicate, grouped by use case (e.g. text-to-image, super-resolution).
list_deployments
List all deployments for your account.
update_model
Update metadata of an existing model on Replicate, such as its description, readme, or associated URLs.
delete_model
Delete a model from Replicate. The model must be private, have no versions, and be owned by the authenticated user.
create_training
Start a fine-tuning training job on Replicate. Takes an existing model version and your training data to create a new fine-tuned model version at the specified destination.
get_prediction
Retrieve the current status and results of a prediction. Use this to check if a prediction has completed and to fetch its output.
cancel_training
Cancel a running training job. Only trainings in progress (starting or processing) can be canceled.
list_predictions
List recent predictions for your account. Returns predictions sorted by creation time (newest first) with pagination support.
get_training
Retrieve the current status and results of a training job. Use this to monitor fine-tuning progress and check completion.
update_deployment
Update a deployment's configuration, including hardware, scaling, or the model version it runs. Each update creates a new release.
list_public_models
List public models on Replicate with sorting options. Use Search Models when you already have a query.
create_file
Upload a file to Replicate for use as model input. Files expire after 24 hours.
delete_model_version
Delete a private model version and its associated predictions and output files.
get_model_version
Get a specific model version, including the OpenAPI schema that describes its inputs and outputs.
list_model_examples
List example predictions saved by a model author to demonstrate a model's capabilities.
get_model_readme
Get a model's README content as a Markdown attachment.
get_webhook_signing_secret
Get the signing secret for Replicate's default webhook so incoming webhook payloads can be verified.
download_file
Download a Replicate file through a signed file download URL. Returns the file content as a Slate attachment.
Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.
Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Subscribe to webhooks for list and library change notifications. Retrieve site properties and search for sites across Microsoft 365.
Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Subscribe to real-time change events via Change Data Capture and Platform Events. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.
Create, read, update, and delete records in Airtable bases and tables. Manage base schemas including creating tables and fields. Filter records using formulas, sort by fields, and scope queries to specific views. Upsert records to find, create, or update in a single call. Upload attachments to records, read and write record comments, list accessible bases, and receive real-time base change events through webhooks.
Manage Git repositories, pull requests, and CI/CD pipelines on Bitbucket Cloud. Create, fork, and configure repositories within workspaces and projects. Create, review, approve, merge, and decline pull requests with inline code comments. Browse source code, list commits, and manage branches and tags. Track issues with the built-in issue tracker. Trigger, monitor, and manage Bitbucket Pipelines. List workspace members, configure repository default reviewers and branch restrictions, create and manage repository webhooks, and search code across repositories.
Deploy, manage, and scale applications on Heroku's cloud platform. Create and configure apps, scale dynos, provision add-ons (databases, caching, etc.), manage configuration variables, build and release code, add custom domains and SSL certificates, manage collaborators and team permissions, configure pipelines for continuous delivery, set up log drains, and sync data with Salesforce via Heroku Connect. Subscribe to webhooks for real-time notifications on app changes, builds, releases, dyno lifecycle events, and more.
Run, fine-tune, and deploy machine learning models via API. Create predictions on public or private AI models with synchronous or streaming output. Fine-tune existing models with custom training data. Manage model versions, deployments, and scaling configurations. Upload and manage files for model inputs. Browse curated model collections, search for public models, and discover available hardware options. Configure webhooks for prediction and training lifecycle events.
Common questions about connecting Replicate to AI agents with Metorial.
