ActionReplicateUpdated September 2026

How do I run a Replicate model?

Short answer: You can run replicate prediction in Replicate by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the Replicate Run Replicate Prediction action to a workflow, map its 3 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.

Run Replicate Prediction in Replicate — start free All 4 Replicate actions

Run Replicate Prediction in Replicate — start free

Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

Field	Type	Required	Description
Model Version model_version	string	Required	Full model version string: owner/model:version_hash
Input (JSON) input	string	Required	Model input parameters as JSON. Varies by model.
Wait for Result wait	options	Optional	Wait synchronously for the prediction to complete (up to 60s)

Sample request

{
  "model_version": "e.g. stability-ai/sdxl:abc123...",
  "input": "{\"prompt\": \"A photo of an astronaut riding a horse\"}",
  "wait": "{{trigger.wait}}"
}

Returns

{
  "id": "pred123",
  "output": [
    "https://replicate.delivery/output123.png"
  ],
  "status": "succeeded",
  "metrics": {
    "predict_time": 3.5
  }
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Run Replicate Prediction.

Any of these apps can fire this action as part of a workflow.

Google Sheets → Replicate

2 Google Sheets triggers

HubSpot → Replicate

18 HubSpot triggers

FAQ

Questions about Run Replicate Prediction.

What does the Run Replicate Prediction action do in Replicate?

Submits an inference request against any model on Replicate. Returns prediction ID immediately; poll Get Prediction or use webhook for completion notification.

What inputs does Run Replicate Prediction require?

Required: Model Version, Input (JSON). Every input accepts a static value or a variable from any upstream node in your workflow.

Can I use dynamic inputs from earlier workflow nodes?

Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.

What happens if Replicate returns an error?

The run history shows the failed step with its input and the error message Replicate returned, so you can fix the input and run the workflow again. Automatic retries are built into HTTP steps only, where you can also set your own retry count and delay.

Does Run Replicate Prediction support batch operations?

Run Run Replicate Prediction inside a loop to process each item in an array. TinyCommand does not throttle calls for you, so for large arrays add a Delay step if you need to stay within Replicate's rate limits.

More actions

Other Replicate actions.

Action

Cancel Replicate Prediction

Aborts an in-progress prediction. For "user cancelled the request → stop the long-running model" workflows that save GPU compute costs.

Action

Get Replicate Prediction

Polls a prediction by ID; returns status (starting/processing/succeeded/failed) and output URLs when complete. Configure webhook on Run Prediction for push notification.

Action

List Replicate Models

Returns the Replicate catalog. Useful for model discovery — Replicate hosts many niche specialised models (face restoration, voice cloning, etc.) alongside the common foundation models.

Run Replicate Prediction in Replicate — start free