Skip to main content

Run Model

Runs a model on the Replicate AI platform and waits for the prediction to complete, returning the result.

Common Properties​

  • Name - The custom name of the node.
  • Color - The custom color of the node.
  • Delay Before (sec) - Waits in seconds before executing the node.
  • Delay After (sec) - Waits in seconds after executing node.
  • Continue On Error - Automation will continue regardless of any error. The default value is false.
info

If the ContinueOnError property is true, no error is caught when the project is executed, even if a Catch node is used.

Inputs​

  • Connection Id - The identifier of the Replicate AI connection to use.
  • Version - The version identifier of the model to use for the prediction.
  • Input - An object containing the input parameters for the model. The structure depends on the specific model being used.

Options​

  • Model Name - The name of the model (required when using Robomotion Credits). Example: robomotionio/whisperx_tr

Output​

  • Prediction ID - The unique identifier of the created prediction.
  • Response - The output/result of the completed prediction.

How It Works​

The Run Model node integrates with the Replicate AI platform to run a model and wait for completion. When executed, the node:

  1. Validates the provided Connection Id, Version, and Input parameters
  2. Processes any file inputs that start with "@" symbol
  3. Creates a prediction either through the Replicate API directly or via Robomotion's gateway (depending on connection settings)
  4. Continuously polls the prediction status until it completes (succeeds, fails, or is canceled)
  5. Returns the Prediction ID and the prediction's output as the response

Requirements​

  • A valid Replicate AI account
  • A configured Replicate AI connection in Robomotion
  • The model version identifier
  • Valid input parameters for the specified model
  • Model Name (when using Robomotion Credits)

Error Handling​

The node will return specific errors in the following cases:

  • Empty or invalid Connection Id
  • Empty or invalid Version
  • Invalid input parameters for the model
  • Invalid connection credentials
  • Network issues when communicating with the Replicate API
  • API errors from the Replicate platform
  • Empty or invalid Model Name (when using Robomotion Credits)
  • Prediction failure or cancellation

Usage Notes​

  • The Input object structure varies depending on the model being used
  • Refer to the Replicate AI model documentation for the required input parameters
  • File inputs should be prefixed with "@" symbol in the Input object
  • This node blocks execution until the prediction completes, which may take some time
  • When using Robomotion Credits, the Model Name option is mandatory
  • The node automatically polls for prediction status every second
  • Predictions may take time to complete depending on the model and input complexity
  • Use the Create Prediction node if you don't want to wait for completion