Start free
ActionReplicateUpdated June 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.

FieldTypeRequiredDescription
Model Version
model_version
stringRequiredFull model version string: owner/model:version_hash
Input (JSON)
input
stringRequiredModel input parameters as JSON. Varies by model.
Wait for Result
wait
optionsOptionalWait 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.

Gmail → Replicate
1 Gmail triggers
Slack → Replicate
13 Slack triggers
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 workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.
Does Run Replicate Prediction support batch operations?
Yes. Run Run Replicate Prediction inside a Loop node to process arrays. TinyCommand handles Replicate's rate limits automatically so you don't have to throttle manually.
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