Replicate allows users to run AI models via a cloud API without managing infrastructure.
Replicate allows users to run AI models via a cloud API without managing infrastructure. On Nagent, Replicate is exposed as a fully-configurable artificial intelligence integration that any agent can call — 31 actions, and API key authentication. No code is required to wire Replicate into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Replicate to automate the kinds of tasks artificial intelligence teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Replicate into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Replicate, with input parameters and output schema. Drop these into any step of an agent built in Helix.
REPLICATE_ACCOUNT_GETTool to get authenticated account information. Use when you need to retrieve details about the account associated with the API token.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_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.
Input parameters
The ID of the prediction to cancel
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_COLLECTIONS_GETTool to get a specific collection of models by its slug. Use when you need detailed information about a collection and its models.
Input parameters
The slug identifier of the collection, e.g., 'super-resolution' or 'text-to-image'
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_COLLECTIONS_LISTTool 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.
Input parameters
Cursor for pagination. Use the cursor from 'next' URL of previous response.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_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.
Input parameters
The name of the model. This must be unique among all models owned by the user or organization.
The name of the user or organization that will own the model. This must be the same as the user or organization making the API request.
The SKU for the hardware used to run the model. Possible values can be retrieved from the hardware.list endpoint.
A URL for the model's paper
A URL for the model's source code on GitHub
Whether the model should be public or private. Public models are viewable and runnable by anyone; private models are restricted to owners.
A description of the model
A URL for the model's license
A URL for the model's cover image. This should be an image file.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_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 created via REPLICATE_DEPLOYMENTS_CREATE. To run public models (e.g., 'meta/llama-2-70b-chat', 'stability-ai/sdxl'), use REPLICATE_MODELS_PREDICTIONS_CREATE instead. Use 'wait_for' to wait until the prediction completes.
Input parameters
JSON object of inputs for the model Keys and types must exactly match the deployment model's schema; consult REPLICATE_MODELS_README_GET or REPLICATE_MODELS_EXAMPLES_LIST first. For file inputs, verify file IDs via REPLICATE_FILES_LIST before submitting.
HTTPS URL to receive webhook callbacks
Seconds to wait for prediction completion; adds a 'Prefer: wait=<n>' header if provided Valid range is 1–60; if the prediction does not complete within this window, poll for status or use a webhook instead.
Name of the deployment. NOTE: This is the deployment name, NOT a public model name. Deployments are created via REPLICATE_DEPLOYMENTS_CREATE. To run public models like 'meta/llama-2-70b-chat', use REPLICATE_MODELS_PREDICTIONS_CREATE instead
Username or organization that owns the deployment. NOTE: This is for Replicate Deployments only, NOT public models. Deployments are persistent instances you create and manage separately. To run public models, use REPLICATE_MODELS_PREDICTIONS_CREATE instead
List of events to trigger webhook calls
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_DEPLOYMENTS_CREATETool 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.
Input parameters
The deployment's identifier
Full model name in format owner/name
The 64-character model version ID to deploy
Hardware SKU from the hardware.list endpoint
Maximum instances for auto-scaling
Minimum instances for auto-scaling
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_DEPLOYMENTS_DELETETool 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.
Input parameters
The name of the deployment to delete. Deployment must be offline and unused for at least 15 minutes before deletion.
The username or organization that owns the deployment
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_DEPLOYMENTS_GETTool to get deployment details by owner and name. Use when you need information about a specific deployment including its release configuration and hardware settings.
Input parameters
The name of the deployment
The name of the user or organization that owns the deployment
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_DEPLOYMENTS_LISTTool to list all deployments associated with the account. Use when you need to retrieve deployment configurations and their latest releases.
Input parameters
Cursor for pagination. Use the cursor from 'next' URL of previous response.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_FILES_CREATETool to create or upload a file to Replicate. Use when you need to upload file content with optional metadata.
Input parameters
File to upload.
User-provided metadata associated with the file (must be valid JSON)
The content/MIME type for the file
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_FILES_DELETETool to delete a file by its ID. Use when you need to remove a file from storage. Returns 204 No Content on success.
Input parameters
The unique identifier of the file to delete
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_FILES_GETTool 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.
Input parameters
The ID of the file to retrieve Must originate from a prior upload or prediction output. Use REPLICATE_FILES_LIST to confirm the ID exists before calling this tool.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_FILES_LISTTool 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.
Input parameters
Cursor for pagination. Use the cursor from 'next' URL of previous response.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_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.
Input parameters
The ID of the prediction to get
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_HARDWARE_LISTTool to list available hardware SKUs for models and deployments. Use when you need to see what hardware options are available on the Replicate platform.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_MODELS_EXAMPLES_LISTTool 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; cross-reference with REPLICATE_MODELS_README_GET before calling REPLICATE_CREATE_PREDICTION to satisfy strict input validation.
Input parameters
Cursor for pagination. Use the cursor from 'next' URL of previous response.
The name of the model to list examples for. Must exactly match the Replicate URL slug (case-sensitive).
The name of the user or organization that owns the model. Must exactly match the Replicate URL slug (case-sensitive).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_MODELS_GETTool 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., `prompt`, `aspect_ratio`, `version`); missing or unknown keys cause validation errors. Model schemas and available versions may change over time; recheck before production use.
Input parameters
The name of the model, e.g., 'hello-world' Must be an exact, case-sensitive Replicate slug (lowercase, hyphenated); e.g., use 'hello-world' not 'Hello World'.
The username or organization that owns the model, e.g., 'replicate' Must be an exact, case-sensitive Replicate slug (lowercase, hyphenated); e.g., use 'replicate' not 'Replicate'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_MODELS_LISTTool to list public models with pagination and sorting. Use when you need to browse available models or find models sorted by creation date.
Input parameters
Pagination cursor for navigating through results. Use the 'next' URL from previous responses to fetch the next page of results.
Field to sort models by. Options are 'model_created_at' (when model was created) or 'latest_version_created_at' (when latest version was created). Defaults to 'latest_version_created_at' if not specified.
Sort direction - 'asc' for ascending or 'desc' for descending. Defaults to 'desc' (newest first) if not specified.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_MODELS_PREDICTIONS_CREATETool 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.
Input parameters
Model inputs as JSON object. Schema varies by model - each model has its own set of required fields, optional parameters, and validation constraints (e.g., max dimensions for image models). IMPORTANT: Before making predictions, use the REPLICATE_MODELS_GET action to fetch the model's openapi_schema which contains all valid input parameters and their constraints. For image models like flux-1.1-pro, common constraints include max width/height limits (e.g., 1440px), valid aspect ratios, and output format options
HTTPS URL to receive POST requests when prediction updates occur
Seconds to wait for prediction completion (1-60); adds a 'Prefer: wait=<n>' header to block and wait synchronously
The name of the model as it appears on Replicate. Must be an exact match. Find valid model names by searching at replicate.com or using the search/models_list actions. The full model identifier is {model_owner}/{model_name}
The username or organization that owns the model on Replicate. Find valid owners by searching models at replicate.com or using the search/models_list actions. Examples: 'meta', 'stability-ai', 'black-forest-labs', 'bytedance', 'google'
Maximum execution duration with optional unit suffixes (s/m/h); minimum 5 seconds. Example: '60s' or '5m'
Filter webhook triggers by event type: 'start', 'output', 'logs', or 'completed'
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_MODELS_README_GETTool 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.
Input parameters
The name of the model, e.g., 'hello-world'
The username or organization that owns the model, e.g., 'replicate' Must exactly match the Replicate URL slug (case-sensitive).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_MODELS_VERSIONS_GETTool to get a specific version of a model. Use when you need details about a particular model version including its schema and metadata.
Input parameters
The name of the model, e.g., 'hello-world'
The 64-character identifier of the version
The name of the user or organization that owns the model, e.g., 'replicate'
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_MODELS_VERSIONS_LISTTool to list all versions of a specific model. Use when you need to see all available versions of a model, sorted by newest first.
Input parameters
Cursor for pagination. Use the cursor from 'next' URL of previous response.
The name of the model, e.g., 'hello-world'
The username or organization that owns the model, e.g., 'replicate'
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_PREDICTIONS_CREATETool 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.
Input parameters
Model inputs as JSON object. Schema varies by model. Files should be HTTP URLs (for files >256kb or reusable) or data URLs (for files ≤256kb)
Deprecated. Streaming availability is now included in response urls
Model version identifier. Accepts formats: {owner}/{name}, {owner}/{name}:{version_id}, or {version_id} alone
HTTPS URL to receive POST requests when prediction updates occur. Body mirrors the get prediction response
Seconds (1-60) to hold connection open until model finishes. Adds 'Prefer: wait=<n>' header
Maximum runtime before automatic cancellation. Accepts durations with optional suffixes (s/m/h). Minimum: 5 seconds. Examples: '30s', '5m', '1h30m45s'
Controls webhook triggers. Options: 'start', 'output', 'logs', 'completed'. Output/logs events throttled to once per 500ms
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_PREDICTIONS_LISTTool 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.
Input parameters
Cursor for pagination. Use the cursor from 'next' URL of previous response.
Include only predictions created at or after this date-time, in ISO 8601 format (e.g., '2024-01-01T00:00:00Z'). Useful for filtering recent predictions.
Include only predictions created before this date-time, in ISO 8601 format (e.g., '2024-12-31T23:59:59Z'). Useful for filtering older predictions.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_SEARCHTool 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.
Input parameters
Maximum number of model results to return. Must be between 1 and 50. Defaults to 20 if not specified.
The search query string to execute. Can search across models, collections, and documentation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_TRAININGS_CANCELTool to cancel an ongoing training operation in Replicate. Use when you need to stop a training job that is in progress.
Input parameters
The identifier of the training operation to be terminated
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_TRAININGS_CREATETool 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.
Input parameters
Name of the model to train
JSON object containing inputs to the Cog model's train() function. Schema varies by model
Name of the user or organization owning the model
HTTPS URL to receive POST requests when training updates occur
The 64-character model version identifier to use for training
Destination model to push to in format {owner}/{name}
List of event types that trigger webhook calls. Options: 'start', 'output', 'logs', 'completed'
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_TRAININGS_LISTTool 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.
Input parameters
Cursor for pagination. Use the cursor from 'next' URL of previous response.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_UPDATE_MODELSTool 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.
Input parameters
The README content of the model
A URL for the model's paper
A URL for the model's source code on GitHub
The name of the model to update
A description of the model
A URL for the model's license
The name of the user or organization that owns the model
A URL for the model's weights
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
REPLICATE_WEBHOOKS_SECRET_GETTool to get the signing secret for the default webhook. Use when you need to retrieve the secret key used to verify webhook authenticity.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 91 agents privately built on Nagent that already use Replicate.
Build on Nagent
Connect Replicate to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Replicate, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Replicate is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Replicate is connected, you configure its 31 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Replicate steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Replicate event fires, the agent kicks off automatically.
Every Replicate action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Replicate ships with 31 pre-built artificial intelligence actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Replicate together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Replicate-based workflows tailored to your business.