Body

JSON request structures for various models

The request body should be passed using the -d option in the cURL command. Replace [data] with the actual JSON-formatted content you want to send for prediction. The structure and required fields depend on the specific model’s configuration.

The v2 request body uses a simplified, flat JSON structure. Each prediction row is represented as a single object containing direct key-value pairs, where:

• The keys are the exact column names used during model training

• The values are the inputs you want to use for prediction

---

v2 Example (Binary Classification / Multiclass Classification / Regression)

{
  "data": {
    "predict_values": [
      {
        "Lead ID": "21",
        "Lead Budget": 425.5130025,
        "Lead Source": "3",
        "Demo Request": 1,
        "Past Purchases": 0,
        "Website Visits": 1,
        "Email Open Rate": 49.38937152,
        "Interaction Score": 37.72859652,
        "Sales Rep Response Time": 10.99225024
      }
    ]
  }
}

This format is especially useful when exporting data from spreadsheets, CSV files, or databases. It eliminates the need to wrap each value in an alias/selectedValue structure, making it cleaner and easier to use in automated or programmatic scenarios.