Replicate Create Prediction

JSON object of inputs for the model Keys and types must exactly match the deployment model's schema; consult REPLICATE_MODELS_README_GET or REPLICATE_MODELS_EXAMPLES_LIST first. For file inputs, verify file IDs via REPLICATE_FILES_LIST before submitting.

HTTPS URL to receive webhook callbacks

Seconds to wait for prediction completion; adds a 'Prefer: wait=<n>' header if provided Valid range is 1–60; if the prediction does not complete within this window, poll for status or use a webhook instead.

Name of the deployment. NOTE: This is the deployment name, NOT a public model name. Deployments are created via REPLICATE_DEPLOYMENTS_CREATE. To run public models like 'meta/llama-2-70b-chat', use REPLICATE_MODELS_PREDICTIONS_CREATE instead

Username or organization that owns the deployment. NOTE: This is for Replicate Deployments only, NOT public models. Deployments are persistent instances you create and manage separately. To run public models, use REPLICATE_MODELS_PREDICTIONS_CREATE instead

List of events to trigger webhook calls