Cancel Prediction
Tool 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.
ActionTry it
Integrate Replicate
with your AI CRM
Replicate allows users to run AI models via a cloud API without managing infrastructure.
Explore Triggers and Actions
Cancel Training
Tool to cancel an ongoing training operation in Replicate. Use when you need to stop a training job that is in progress.
ActionTry it
Create Deployment
Tool 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.
ActionTry it
Create File
Tool to create or upload a file to Replicate. Use when you need to upload file content with optional metadata.
ActionTry it
Create Model
Tool 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.
ActionTry it
Create Model Prediction
Tool 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 webhooks for async notifications.
ActionTry it
Create Prediction
Create a prediction for a Replicate Deployment using model inputs. Supports webhook notifications and an optional wait of up to 60 seconds for completion.
ActionTry it
Create Prediction
Tool 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 notifications.
ActionTry it
Create Training Job
Tool 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.
ActionTry it
Delete Deployment
Tool 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.
ActionTry it
Delete File
Delete a file by its ID. Returns a success message, including when the file is already absent.
ActionTry it
Download File
Download a stored file using Replicate's signed download fields. Replicate documents a limit of 3,000 requests per minute for non-prediction endpoints. Accounts with low credit balances can be throttled more aggressively.
ActionTry it
Get Account Information
Tool to get authenticated account information. Use when you need to retrieve details about the account associated with the API token.
ActionTry it
Get Deployment Details
Tool to get deployment details by owner and name. Use when you need information about a specific deployment including its release configuration and hardware settings.
ActionTry it
Get File Details
Tool 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 after retrieval.
ActionTry it
Get model collection
Tool to get a specific collection of models by its slug. Use when you need detailed information about a collection and its models.
ActionTry it
Get Model Details
Get details of a specific model by owner and name. The latest version and its input/output schema may be included when available.
ActionTry it
Get Model README
Tool 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 model inputs and returns 422 errors for incorrect keys or types. Use after retrieving model details when you want to view its documentation.
ActionTry it
Get Model Version
Tool to get a specific version of a model. Use when you need details about a particular model version including its schema and metadata.
ActionTry it
Get Prediction
Tool 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.
ActionTry it
Get Training
Get 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 aggressively.
ActionTry it
Get Webhook Signing Secret
Tool to get the signing secret for the default webhook. Use when you need to retrieve the secret key used to verify webhook authenticity.
ActionTry it
List All Predictions
Tool 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.
ActionTry it
List Available Hardware
Tool to list available hardware SKUs for models and deployments. Use when you need to see what hardware options are available on the Replicate platform.
ActionTry it
List deployments
List deployments associated with the account, including their latest release configurations. Results are paginated; use the next-page cursor to retrieve additional deployments.
ActionTry it
List Files
Tool 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: follow the next cursor until empty to retrieve all files. Limit requests to 1–2/second to avoid 429 Too Many Requests errors. Use to validate current file_ids before passing to prediction tools, as stale file_ids cause runtime errors.
ActionTry it
List model collections
Tool 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, slug, description), not individual models within each collection; use REPLICATE_MODELS_GET for per-model details. Response may include a non-null `next` field indicating additional pages; follow it to enumerate all collections.
ActionTry it
List model examples
List example predictions for a specific model, with cursor-based pagination. Example input or output may be absent if data has been removed.
ActionTry it
List Model Versions
List versions of a specific model, newest first, with cursor-based pagination.
ActionTry it
List Public Models
Tool to list public models with pagination and sorting. Use when you need to browse available models or find models sorted by creation date.
ActionTry it
List Training Jobs
Tool 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.
ActionTry it
Search Models and Collections
Tool 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.
ActionTry it
Update Model Metadata
Update a model's metadata, including its description, README, and associated URLs.
ActionTry it
How the Replicate integration works
The Replicate integration connects your Dench AI CRM directly to Replicate, so agents can read and act on your Replicate data as part of everyday work — answering questions in chat, keeping your CRM in sync, and running automations without anyone copying data between tools.
33 actions are available for agents to invoke on your behalf. Every call runs through Replicate's own authorization, scoped to the account you connect.
Set up Replicate in Dench
- 1
Sign in to your Dench workspace and open Integrations.
- 2
Find Replicate and click Connect — you'll authorize access through Replicate's own sign-in flow. No API keys or code required.
- 3
Ask an agent to use Replicate in chat, or call it from an automation.
- 4
Manage or disconnect the connection any time from workspace settings.
Frequently asked questions
How does the Replicate integration work with Dench?
The Dench Replicate integration connects your AI CRM to Replicate, so AI agents can work with your Replicate data as part of chats, automations, and CRM workflows. You connect your account once, and every agent in your workspace can use it — governed by your workspace permissions.
What actions can AI agents perform with Replicate via Dench?
The Replicate integration currently exposes 33 actions, including Cancel Prediction, Cancel Training, Create Deployment, Create File, Create Model, and Create Model Prediction. Agents invoke them on your behalf from chat or from automations.
Do I need to write code to connect Replicate to Dench?
No. You connect Replicate from your Dench workspace using Replicate's own sign-in and authorization flow — no API keys to copy, no glue code to maintain.
Is the Replicate integration secure?
Connections are authorized through Replicate's own authentication flow, and Dench stores only the authorization needed to act on your behalf. You can review and disconnect the Replicate connection from your workspace settings at any time.