Run Model Prediction Synchronously
Create a prediction and wait for the result. This compatibility endpoint is only supported for models with synchronous execution enabled; unsupported models return a bad request error.
Authorizations
API key passed as Authorization: Bearer <api_key>
Body
Model slug or identifier
"flux-1-1-pro"
Input parameters for the prediction
Optional opt-in to an enabled, saved fallback configuration for this organization and primary model. Use the configuration's slug, not a fallback model slug or ID. Set this at the top level of the request, not inside input. Saving a configuration alone does not enable fallback for a request: omitting this field runs only the primary model. Use 1-50 lowercase letters and digits separated by single hyphens.
1 - 50^[a-z0-9]+(?:-[a-z0-9]+)*$"quality-recovery"
Deprecated. This field is ignored. Kept for backwards compatibility.
"0.0.1"
Optional webhook URL to receive prediction result asynchronously
"https://your-app.com/webhook"
Optional secret used to sign webhook requests
"your-secret-key"
Response
Prediction completed or failed synchronously
Final terminal status of the synchronous prediction
success, failed, cancelled "success"
Human-readable message
"Prediction completed successfully"
Unique prediction identifier
"abc123-def456-ghi789"
Prediction output, when available
User-facing error message when the prediction failed
""