[[["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 2025-06-27 UTC."],[],[],null,["# Method: endpoints.directRawPredict\n\n**Full name**: projects.locations.endpoints.directRawPredict\n\nPerform an unary online prediction request to a gRPC model server for custom containers. \n\n### Endpoint\n\npost `https:``/``/{service-endpoint}``/v1beta1``/{endpoint}:directRawPredict` \nWhere `{service-endpoint}` is one of the [supported service endpoints](/vertex-ai/docs/reference/rest#rest_endpoints).\n\n### Path parameters\n\n`endpoint` `string` \nRequired. The name of the Endpoint requested to serve the prediction. Format: `projects/{project}/locations/{location}/endpoints/{endpoint}`\n\n### Request body\n\nThe request body contains data with the following structure:\nFields `methodName` `string` \nFully qualified name of the API method being invoked to perform predictions.\n\nFormat: `/namespace.Service/method/` Example: `/tensorflow.serving.PredictionService/endpoints.predict`\n`input` `string (`[bytes](https://developers.google.com/discovery/v1/type-format)` format)` \nThe prediction input.\n\nA base64-encoded string. \n\n### Response body\n\nResponse message for [PredictionService.DirectRawPredict](/vertex-ai/docs/reference/rest/v1beta1/projects.locations.endpoints/directRawPredict#google.cloud.aiplatform.v1beta1.PredictionService.DirectRawPredict).\n\nIf successful, the response body contains data with the following structure:\nFields `output` `string (`[bytes](https://developers.google.com/discovery/v1/type-format)` format)` \nThe prediction output.\n\nA base64-encoded string."]]
