Replicate

{/* Generated by scripts/generate-integration-catalog.mjs. Do not edit by hand. */}

At a glance

Credentials

Set these per environment. See Connect an integration.

VariableRequiredDescription
REPLICATE_API_TOKENYesReplicate API token (starts with r8_) Docs.

Setup

  1. Create a Replicate account: Go to https://replicate.com and sign up (GitHub sign-in supported). New accounts get a small amount of free usage before billing is required.
  2. Create an API token: Open https://replicate.com/account/api-tokens, give the token a descriptive name (e.g. 'Veryfront Integration'), and create it.
  3. Store the token: Copy the token and add it to your .env file as REPLICATE_API_TOKEN=r8_...
  4. Verify access: Run the List Models tool to confirm the token works. A 401 means the token is wrong or revoked.

Provider notes

  • Predictions are billed per second of compute - costs vary widely by model and hardware
  • Create Prediction sends Prefer: wait=60 to return synchronously when possible; long-running models still return status 'starting' or 'processing' - poll with Get Prediction
  • Use the version ID from Get Model's latest_version.id field when creating predictions

Provider API reference.

Tools

ToolAccessDescription
List Models<br /><code className="reference-identifier">replicate__list_models</code>ReadList public models
Get Model<br /><code className="reference-identifier">replicate__get_model</code>ReadGet model
Create Prediction<br /><code className="reference-identifier">replicate__create_prediction</code>WriteCreate prediction
Get Prediction<br /><code className="reference-identifier">replicate__get_prediction</code>ReadGet prediction
Cancel Prediction<br /><code className="reference-identifier">replicate__cancel_prediction</code>WriteCancel prediction

Verify the connection

Call a read tool such as replicate__list_models with arguments for your account. Confirm that the result comes from the intended account or workspace before enabling write tools.