> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Replicate

> Replicate allows users to run AI models via a cloud API without managing infrastructure.

![Replicate logo](https://mintcdn.com/composio-preview/YYC5iurbUCUzEs77/images/toolkits/replicate.svg?fit=max\&auto=format\&n=YYC5iurbUCUzEs77\&q=85\&s=2633c18185c893572668bf43f05143a6)

* **Category:** artificial intelligence
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 33
* **Triggers:** 0
* **Slug:** `REPLICATE`
* **Version:** 20261101\_00

## Tools

> [accordion] Get Account Information
>
> **Slug:** `REPLICATE_ACCOUNT_GET`
>
> Tool to get authenticated account information. Use when you need to retrieve details about the account associated with the API token.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Cancel Prediction
>
> **Slug:** `REPLICATE_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.
>
> #### Input Parameters
>
> **prediction\_id** `string` *required*
>
> The ID of the prediction to cancel
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get model collection
>
> **Slug:** `REPLICATE_COLLECTIONS_GET`
>
> Tool to get a specific collection of models by its slug. Use when you need detailed information about a collection and its models.
>
> #### Input Parameters
>
> **collection\_slug** `string` *required*
>
> The slug identifier of the collection, e.g., 'super-resolution' or 'text-to-image'
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List model collections
>
> **Slug:** `REPLICATE_COLLECTIONS_LIST`
>
> 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.
>
> #### Input Parameters
>
> **cursor** `string`
>
> Cursor for pagination. Use the cursor from 'next' URL of previous response.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Model
>
> **Slug:** `REPLICATE_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.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> The name of the model. This must be unique among all models owned by the user or organization.
>
> **owner** `string` *required*
>
> 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.
>
> **hardware** `string` *required*
>
> The SKU for the hardware used to run the model. Possible values can be retrieved from the hardware.list endpoint.
>
> **paper\_url** `string`
>
> A URL for the model's paper
>
> **github\_url** `string`
>
> A URL for the model's source code on GitHub
>
> **visibility** `string` *required*
>
> Whether the model should be public or private. Public models are viewable and runnable by anyone; private models are restricted to owners.
>
> **description** `string`
>
> A description of the model
>
> **license\_url** `string`
>
> A URL for the model's license
>
> **cover\_image\_url** `string`
>
> A URL for the model's cover image. This should be an image file.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Prediction
>
> **Slug:** `REPLICATE_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.
>
> #### Input Parameters
>
> **input** `object` *required*
>
> 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.
>
> **webhook** `string`
>
> HTTPS URL to receive webhook callbacks
>
> **wait\_for** `integer`
>
> 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.
>
> **deployment\_name** `string` *required*
>
> 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
>
> **deployment\_owner** `string` *required*
>
> 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
>
> **webhook\_events\_filter** `array`
>
> List of events to trigger webhook calls
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Deployment
>
> **Slug:** `REPLICATE_DEPLOYMENTS_CREATE`
>
> 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.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> The deployment's identifier
>
> **model** `string` *required*
>
> Full model name in format owner/name
>
> **version** `string` *required*
>
> The 64-character model version ID to deploy
>
> **hardware** `string` *required*
>
> Hardware SKU from the hardware.list endpoint
>
> **max\_instances** `integer` *required*
>
> Maximum instances for auto-scaling
>
> **min\_instances** `integer` *required*
>
> Minimum instances for auto-scaling
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Deployment
>
> **Slug:** `REPLICATE_DEPLOYMENTS_DELETE`
>
> 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.
>
> #### Input Parameters
>
> **deployment\_name** `string` *required*
>
> The name of the deployment to delete. Deployment must be offline and unused for at least 15 minutes before deletion.
>
> **deployment\_owner** `string` *required*
>
> The username or organization that owns the deployment
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Deployment Details
>
> **Slug:** `REPLICATE_DEPLOYMENTS_GET`
>
> 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.
>
> #### Input Parameters
>
> **deployment\_name** `string` *required*
>
> The name of the deployment
>
> **deployment\_owner** `string` *required*
>
> The name of the user or organization that owns the deployment
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List deployments
>
> **Slug:** `REPLICATE_DEPLOYMENTS_LIST`
>
> List deployments associated with the account, including their latest release configurations. Results are paginated; use the next-page cursor to retrieve additional deployments.
>
> #### Input Parameters
>
> **cursor** `string`
>
> Cursor for pagination. Use the cursor from 'next' URL of previous response.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create File
>
> **Slug:** `REPLICATE_FILES_CREATE`
>
> Tool to create or upload a file to Replicate. Use when you need to upload file content with optional metadata.
>
> #### Input Parameters
>
> **content** `object` *required*
>
> File to upload.
>
> **metadata** `object`
>
> User-provided metadata associated with the file (must be valid JSON)
>
> **content\_type** `string`
>
> The content/MIME type for the file
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete File
>
> **Slug:** `REPLICATE_FILES_DELETE`
>
> Delete a file by its ID. Returns a success message, including when the file is already absent.
>
> #### Input Parameters
>
> **file\_id** `string` *required*
>
> The unique identifier of the file to delete
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Download File
>
> **Slug:** `REPLICATE_FILES_DOWNLOAD`
>
> 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.
>
> #### Input Parameters
>
> **owner** `string` *required*
>
> The user or organization that owns the file, from the signed download URL.
>
> **expiry** `integer` *required*
>
> The positive Unix expiry timestamp from the signed download URL.
>
> **file\_id** `string` *required*
>
> The Replicate file ID returned by a file or prediction action.
>
> **file\_name** `string`
>
> Optional output filename. If omitted, a safe filename is derived from the file ID.
>
> **signature** `string` *required*
>
> The base64-encoded HMAC-SHA256 signature from the signed download URL. It is sent unchanged.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get File Details
>
> **Slug:** `REPLICATE_FILES_GET`
>
> 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.
>
> #### Input Parameters
>
> **file\_id** `string` *required*
>
> 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** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Files
>
> **Slug:** `REPLICATE_FILES_LIST`
>
> 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.
>
> #### Input Parameters
>
> **cursor** `string`
>
> Cursor for pagination. Use the cursor from 'next' URL of previous response.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Prediction
>
> **Slug:** `REPLICATE_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.
>
> #### Input Parameters
>
> **prediction\_id** `string` *required*
>
> The ID of the prediction to get
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Available Hardware
>
> **Slug:** `REPLICATE_HARDWARE_LIST`
>
> 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.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List model examples
>
> **Slug:** `REPLICATE_MODELS_EXAMPLES_LIST`
>
> List example predictions for a specific model, with cursor-based pagination. Example input or output may be absent if data has been removed.
>
> #### Input Parameters
>
> **cursor** `string`
>
> Cursor for pagination. Use the cursor from 'next' URL of previous response.
>
> **model\_name** `string` *required*
>
> The name of the model to list examples for. Must exactly match the Replicate URL slug (case-sensitive).
>
> **model\_owner** `string` *required*
>
> The name of the user or organization that owns the model. Must exactly match the Replicate URL slug (case-sensitive).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Model Details
>
> **Slug:** `REPLICATE_MODELS_GET`
>
> Get details of a specific model by owner and name. The latest version and its input/output schema may be included when available.
>
> #### Input Parameters
>
> **model\_name** `string` *required*
>
> 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'.
>
> **model\_owner** `string` *required*
>
> 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** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Public Models
>
> **Slug:** `REPLICATE_MODELS_LIST`
>
> Tool 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
>
> **cursor** `string`
>
> Pagination cursor for navigating through results. Use the 'next' URL from previous responses to fetch the next page of results.
>
> **sort\_by** `string ("model_created_at" | "latest_version_created_at")`
>
> 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** `string ("asc" | "desc")`
>
> Sort direction - 'asc' for ascending or 'desc' for descending. Defaults to 'desc' (newest first) if not specified.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Model Prediction
>
> **Slug:** `REPLICATE_MODELS_PREDICTIONS_CREATE`
>
> 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.
>
> #### Input Parameters
>
> **input** `object` *required*
>
> 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
>
> **webhook** `string`
>
> HTTPS URL to receive POST requests when prediction updates occur
>
> **wait\_for** `integer`
>
> Seconds to wait for prediction completion (1-60); adds a 'Prefer: wait=\<n>' header to block and wait synchronously
>
> **model\_name** `string` *required*
>
> 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}
>
> **model\_owner** `string` *required*
>
> 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'
>
> **cancel\_after** `string`
>
> Maximum execution duration with optional unit suffixes (s/m/h); minimum 5 seconds. Example: '60s' or '5m'
>
> **webhook\_events\_filter** `array`
>
> Filter webhook triggers by event type: 'start', 'output', 'logs', or 'completed'
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Model README
>
> **Slug:** `REPLICATE_MODELS_README_GET`
>
> 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.
>
> #### Input Parameters
>
> **model\_name** `string` *required*
>
> The name of the model, e.g., 'hello-world'
>
> **model\_owner** `string` *required*
>
> The username or organization that owns the model, e.g., 'replicate' Must exactly match the Replicate URL slug (case-sensitive).
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Model Version
>
> **Slug:** `REPLICATE_MODELS_VERSIONS_GET`
>
> Tool 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
>
> **model\_name** `string` *required*
>
> The name of the model, e.g., 'hello-world'
>
> **version\_id** `string` *required*
>
> The 64-character identifier of the version
>
> **model\_owner** `string` *required*
>
> The name of the user or organization that owns the model, e.g., 'replicate'
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Model Versions
>
> **Slug:** `REPLICATE_MODELS_VERSIONS_LIST`
>
> List versions of a specific model, newest first, with cursor-based pagination.
>
> #### Input Parameters
>
> **cursor** `string`
>
> Cursor for pagination. Use the cursor from 'next' URL of previous response.
>
> **model\_name** `string` *required*
>
> The name of the model, e.g., 'hello-world'
>
> **model\_owner** `string` *required*
>
> The username or organization that owns the model, e.g., 'replicate'
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Prediction
>
> **Slug:** `REPLICATE_PREDICTIONS_CREATE`
>
> 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.
>
> #### Input Parameters
>
> **input** `object` *required*
>
> 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)
>
> **stream** `boolean`
>
> Deprecated. Streaming availability is now included in response urls
>
> **version** `string` *required*
>
> Model version identifier. Accepts formats: \{owner}/\{name}, \{owner}/\{name}:\{version\_id}, or \{version\_id} alone
>
> **webhook** `string`
>
> HTTPS URL to receive POST requests when prediction updates occur. Body mirrors the get prediction response
>
> **wait\_for** `integer`
>
> Seconds (1-60) to hold connection open until model finishes. Adds 'Prefer: wait=\<n>' header
>
> **cancel\_after** `string`
>
> Maximum runtime before automatic cancellation. Accepts durations with optional suffixes (s/m/h). Minimum: 5 seconds. Examples: '30s', '5m', '1h30m45s'
>
> **webhook\_events\_filter** `array`
>
> Controls webhook triggers. Options: 'start', 'output', 'logs', 'completed'. Output/logs events throttled to once per 500ms
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List All Predictions
>
> **Slug:** `REPLICATE_PREDICTIONS_LIST`
>
> 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.
>
> #### Input Parameters
>
> **cursor** `string`
>
> Cursor for pagination. Use the cursor from 'next' URL of previous response.
>
> **created\_after** `string`
>
> 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.
>
> **created\_before** `string`
>
> 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** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Search Models and Collections
>
> **Slug:** `REPLICATE_SEARCH`
>
> 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.
>
> #### Input Parameters
>
> **limit** `integer`
>
> Maximum number of model results to return. Must be between 1 and 50. Defaults to 20 if not specified.
>
> **query** `string` *required*
>
> The search query string to execute. Can search across models, collections, and documentation.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Cancel Training
>
> **Slug:** `REPLICATE_TRAININGS_CANCEL`
>
> Tool to cancel an ongoing training operation in Replicate. Use when you need to stop a training job that is in progress.
>
> #### Input Parameters
>
> **training\_id** `string` *required*
>
> The identifier of the training operation to be terminated
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Training Job
>
> **Slug:** `REPLICATE_TRAININGS_CREATE`
>
> 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.
>
> #### Input Parameters
>
> **name** `string` *required*
>
> Name of the model to train
>
> **input** `object` *required*
>
> JSON object containing inputs to the Cog model's train() function. Schema varies by model
>
> **owner** `string` *required*
>
> Name of the user or organization owning the model
>
> **webhook** `string`
>
> HTTPS URL to receive POST requests when training updates occur
>
> **version\_id** `string` *required*
>
> The 64-character model version identifier to use for training
>
> **destination** `string` *required*
>
> Destination model to push to in format \{owner}/\{name}
>
> **webhook\_events\_filter** `array`
>
> List of event types that trigger webhook calls. Options: 'start', 'output', 'logs', 'completed'
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Training
>
> **Slug:** `REPLICATE_TRAININGS_GET`
>
> 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.
>
> #### Input Parameters
>
> **training\_id** `string` *required*
>
> The training ID returned by a training create or list action
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Training Jobs
>
> **Slug:** `REPLICATE_TRAININGS_LIST`
>
> 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.
>
> #### Input Parameters
>
> **cursor** `string`
>
> Cursor for pagination. Use the cursor from 'next' URL of previous response.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Model Metadata
>
> **Slug:** `REPLICATE_UPDATE_MODELS`
>
> Update a model's metadata, including its description, README, and associated URLs.
>
> #### Input Parameters
>
> **readme** `string`
>
> The README content of the model
>
> **paper\_url** `string`
>
> A URL for the model's paper
>
> **github\_url** `string`
>
> A URL for the model's source code on GitHub
>
> **model\_name** `string` *required*
>
> The name of the model to update
>
> **description** `string`
>
> A description of the model
>
> **license\_url** `string`
>
> A URL for the model's license
>
> **model\_owner** `string` *required*
>
> The name of the user or organization that owns the model
>
> **weights\_url** `string`
>
> A URL for the model's weights
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Webhook Signing Secret
>
> **Slug:** `REPLICATE_WEBHOOKS_SECRET_GET`
>
> Tool 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** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
