The Google Cloud Prediction API has been deprecated and will be shut down on April 30, 2018.

Trainedmodels: predict

Requires authorization

Submit model id and request a prediction. Try it now.


HTTP request



Parameter name Value Description
Required parameters
id string The unique name for the predictive model.
project string The project associated with the model.


This request requires authorization with at least one of the following scopes (read more about authentication and authorization).


Request body

In the request body, supply data with the following structure:

  "input": {
    "csvInstance": [
Property name Value Description Notes
input object Input to the model for a prediction.
input.csvInstance[] list A list of input features, these can be strings or doubles.


If successful, this method returns a response body with the following structure:

  "kind": "prediction#output",
  "id": string,
  "selfLink": string,
  "outputLabel": string,
  "outputMulti": [
      "label": string,
      "score": string
  "outputValue": string
Property name Value Description Notes
kind string What kind of resource this is - "prediction#output".
id string The unique name for the predictive model.
outputLabel string The most likely class label (Categorical models only).
outputMulti[] list A list of class labels with their estimated probabilities (Categorical models only).
outputMulti[].label string The class label.
outputMulti[].score string The probability of the class label.
outputValue string The estimated regression value (Regression models only).

Try it!

Use the APIs Explorer below to call this method on live data and see the response. Alternatively, try the standalone Explorer.

Send feedback about...

Prediction API Documentation