Replicate

Run AI models with cloud API

Integrate with Replicate to run thousands of AI models including image generation, LLMs, speech recognition, and more. Deploy custom models without managing infrastructure using API token authentication.

Toolsreplicate

Usage

01Add the block to your workflow and connect it to the upstream step.
02Configure any required credentials or tokens in the inputs.
03Fill in required inputs and optional parameters for the run.
04Run a test execution, inspect outputs, and iterate before deploying.
05Deploy the replicate block with monitoring enabled in production.

Inputs (UI)

Replicate API Token

short-input

Placeholder: Enter your Replicate API token

Layout: full

Operation

dropdown

Layout: full

Options: Run Prediction, Get Prediction, List Models, Get Model

Model

short-input

Placeholder: owner/model-name:version or owner/model-name

Layout: full

Condition: operation = ["run_prediction","get_model"]

Model Input (JSON)

long-input

Placeholder: {"prompt": "a cat", "width": 512}

Layout: full

Condition: operation = "run_prediction"

Prediction ID

short-input

Placeholder: Enter prediction ID

Layout: full

Condition: operation = "get_prediction"

Inputs (API)

credential

string

Required

operation

string

Required

model

string

Optional

input

string

Optional

predictionId

string

Optional

Outputs

Primary response type:

{
  "data": "json"
}

Tool Access

replicate_api