Required. The instances that are the input to the prediction call. A DeployedModel may have an upper limit on the number of instances it supports per request. In case of customer-created Models, the behaviour is as documented by that Model. The schema of any single instance may be specified on the Endpoint's DeployedModels.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-07-10 UTC."],[[["\u003cp\u003eThe JSON representation of a \u003ccode\u003ePredictionService.Predict\u003c/code\u003e request includes \u003ccode\u003eendpoint\u003c/code\u003e, \u003ccode\u003einstances\u003c/code\u003e, and \u003ccode\u003eparameters\u003c/code\u003e fields.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eendpoint\u003c/code\u003e field, a required string, specifies the Endpoint for the prediction and follows the format \u003ccode\u003eprojects/{project}/locations/{location}/endpoints/{endpoint}\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003einstances\u003c/code\u003e field, also required, contains the input data for the prediction call in \u003ccode\u003eValue\u003c/code\u003e format, with a possible limit on the number of instances per request.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eparameters\u003c/code\u003e field, in \u003ccode\u003eValue\u003c/code\u003e format, defines the prediction settings, and its schema can be specified on the Endpoint's DeployedModels.\u003c/p\u003e\n"]]],[],null,["# PredictRequest\n\n- [JSON representation](#SCHEMA_REPRESENTATION)\n\nRequest message for `PredictionService.Predict`."]]