API Reference

Endpoint: /v1/predict

Purpose: Generate real-time predictions using the deployed model.

Attribute Description Method POST Input Feature vector Output Prediction and metadata SLA < 100 ms

Error Semantics

400: Input validation failure

401: Authentication error

429: Rate limit exceeded

500: Model or infrastructure failure

Supported Clients

Python SDK

JavaScript SDK

Python Example client = MLClient(api_key="KEY") result = client.predict(features)