Replicate for AI agents
Agents read Replicate at once. Changes and sends are held for a person's approval by default.
About Replicate
Replicate allows users to run AI models via a cloud API without managing infrastructure.
What an agent can do in Replicate
Every Replicate action is classed by the platform as a read, a change or a send. Reads run at once. Changes and sends are held for a person by default.
Runs at once (reads)
Looks things up in Replicate without asking first. 20 actions.
- Get Deployment DetailsTool to get deployment details by owner and name. Use when you need information about a specific deployment including its release configuration and hardware settings.
- Get File DetailsTool to get details of a file by its ID. Use when you need to inspect uploaded file information before further operations. Returned URLs may be short-lived; download or persist needed files promptly a
- List FilesTool to retrieve a paginated list of uploaded files. Use to view all files created by the authenticated user or organization. Files are sorted with most recent first. Pagination is cursor-based: follo
- Get PredictionTool to get the status and output of a prediction by its ID. Use when you need to check on a running prediction or retrieve the results of a completed prediction.
- Get Model DetailsTool to get details of a specific model by owner and name. Consult the returned input schema before constructing any prediction request — each model defines its own required/optional fields (e.g., `pr
- List Public ModelsTool to list public models with pagination and sorting. Use when you need to browse available models or find models sorted by creation date.
- Get Model READMETool to get the README content for a model in Markdown format. Consult alongside REPLICATE_MODELS_EXAMPLES_LIST before calling REPLICATE_CREATE_PREDICTION — Replicate enforces strict JSON schemas on m
- Get Model VersionTool to get a specific version of a model. Use when you need details about a particular model version including its schema and metadata.
- List All PredictionsTool to list all predictions for the authenticated user or organization with pagination. Use when you need to retrieve prediction history or filter predictions by creation date.
- Search Models and CollectionsTool to search for models, collections, and docs using text queries (beta). Use when you need to find relevant models or collections based on keywords or descriptions.
- Get TrainingGet a training's current state, output, logs, and runtime metrics by ID. Replicate documents a limit of 3,000 requests per minute for non-prediction endpoints and may throttle low-credit accounts more
- List Training JobsTool to list all training jobs for the authenticated user or organization with pagination. Use when you need to retrieve training history or check the status of training jobs.
Show all 20
- Get Account InformationTool to get authenticated account information. Use when you need to retrieve details about the account associated with the API token.
- Get model collectionTool to get a specific collection of models by its slug. Use when you need detailed information about a collection and its models.
- List model collectionsTool to list all collections of models. Use when you need to retrieve available model collections. Collections are curated groupings of related models. Response includes only collection metadata (name
- List deploymentsTool to list all deployments associated with the account. Use when you need to retrieve deployment configurations and their latest releases.
- List Available HardwareTool to list available hardware SKUs for models and deployments. Use when you need to see what hardware options are available on the Replicate platform.
- List model examplesTool to list example predictions for a specific model. Use when you want to retrieve author-provided illustrative examples after identifying the model. Returned examples are minimal working payloads;
- List Model VersionsTool to list all versions of a specific model. Use when you need to see all available versions of a model, sorted by newest first.
- Get Webhook Signing SecretTool to get the signing secret for the default webhook. Use when you need to retrieve the secret key used to verify webhook authenticity.
Held for approval by default (changes and sends)
Held for a person's approval by default. The approval is recorded and the action is sent once, never twice, with 10 seconds to undo. 11 actions.
- Cancel PredictionTool to cancel a prediction that is still running. Use when you need to stop an in-progress prediction to free up resources or halt execution.
- Create ModelTool to create a new Replicate model with specified owner, name, visibility, and hardware. Use when you need to create a destination model before launching LoRA/fine-tune training.
- Create DeploymentTool to create a new deployment with specified model, version, hardware, and scaling parameters. Use when you need to deploy a model for production use with auto-scaling.
- Create Model PredictionTool to create a prediction using an official Replicate model. Use when you need to run inference with a specific model using its owner and name. Supports synchronous waiting (up to 60 seconds) and we
- Create PredictionTool to create a prediction to run a model by version ID. Use when you have a specific model version identifier and need to run inference with provided inputs. Supports synchronous waiting and webhook
- Create Training JobTool to create a training job for a specific model version. Use when you need to fine-tune a model with custom training data. Supports webhook notifications for training status updates.
- Create PredictionTool to create a prediction for a Replicate Deployment. IMPORTANT: This action ONLY works with Replicate Deployments (persistent instances you create and manage), NOT public models. Deployments are cr
- Delete DeploymentTool to delete a deployment from your account. Use when you need to remove a deployment. Deployments must be offline and unused for at least 15 minutes before deletion.
- Delete FileTool to delete a file by its ID. Use when you need to remove a file from storage. Returns 204 No Content on success.
- Cancel TrainingTool to cancel an ongoing training operation in Replicate. Use when you need to stop a training job that is in progress.
- Update Model MetadataTool to update metadata for a model including description, URLs, and README. Use when you need to modify a model's visibility, documentation, or associated links.
Changes wait in Needs you
Changes and sends in Replicate are held for a person's approval by default. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
Related connectors
Replicate questions
Can an agent change data in Replicate on its own?
Not by default. Changes and sends in Replicate are held for a person's approval. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.
What can an agent read in Replicate?
This connector lists 20 read actions. Reads run at once, without waiting for approval.
How does Replicate connect?
It connects with API key. Connectors are built and maintained by third-party developers; availability is confirmed during scoping.