CIEL M2M Time Series Predict API

Choose this endpoint when you need a quick, pay-per-call time-series prediction without committing to a full ML infrastructure setup. It is well-suited for agents that occasionally need to forecast sequential data (sales, sensor readings, prices) and want to pay micro-amounts per call via USDC on Base (x402 protocol). Prefer alternatives if you need detailed model explainability, configurable forecasting horizons with explicit parameters, or guaranteed SLA and uptime from a named ML provider.

• Missing or malformed input data returns a generic error response
• Insufficient historical data points may yield low-accuracy or empty predictions
• Invalid property types in the input schema cause request rejection
• Service unavailability on the raw IP host may produce connection timeouts
• No detailed error schema documented — errors likely surface as generic JSON or HTTP status codes