The prediction input. Supports HTTP headers and arbitrary data payload.
A DeployedModel may have an upper limit on the number of instances it supports per request. When this limit it is exceeded for an AutoML model, the endpoints.rawPredict method returns an error. When this limit is exceeded for a custom-trained model, the behavior varies depending on the model.
You can specify the schema for each instance in the predictSchemata.instance_schema_uri field when you create a Model. This schema applies when you deploy the Model as a DeployedModel to an Endpoint and use the endpoints.rawPredict method.
Response body
If successful, the response is a generic HTTP response whose format is defined by the method.
[[["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.rawPredict\n\n**Full name**: projects.locations.endpoints.rawPredict\n\nPerform an online prediction with an arbitrary HTTP payload.\n\nThe response includes the following HTTP headers:\n\n- `X-Vertex-AI-Endpoint-id`: id of the [Endpoint](/vertex-ai/docs/reference/rest/v1/projects.locations.endpoints#Endpoint) that served this prediction.\n\n- `X-Vertex-AI-Deployed-Model-id`: id of the Endpoint's [DeployedModel](/vertex-ai/docs/reference/rest/v1/projects.locations.endpoints#DeployedModel) that served this prediction.\n\n### Endpoint\n\npost `https:``/``/{service-endpoint}``/v1``/{endpoint}:rawPredict` \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 `httpBody` `object (`[HttpBody](/vertex-ai/docs/reference/rest/Shared.Types/HttpBody)`)` \nThe prediction input. Supports HTTP headers and arbitrary data payload.\n\nA [DeployedModel](/vertex-ai/docs/reference/rest/v1/projects.locations.endpoints#DeployedModel) may have an upper limit on the number of instances it supports per request. When this limit it is exceeded for an AutoML model, the [endpoints.rawPredict](/vertex-ai/docs/reference/rest/v1/projects.locations.endpoints/rawPredict#google.cloud.aiplatform.v1.PredictionService.RawPredict) method returns an error. When this limit is exceeded for a custom-trained model, the behavior varies depending on the model.\n\nYou can specify the schema for each instance in the [predictSchemata.instance_schema_uri](/vertex-ai/docs/reference/rest/v1/PredictSchemata#FIELDS.instance_schema_uri) field when you create a [Model](/vertex-ai/docs/reference/rest/v1/projects.locations.models#Model). This schema applies when you deploy the `Model` as a `DeployedModel` to an [Endpoint](/vertex-ai/docs/reference/rest/v1/projects.locations.endpoints#Endpoint) and use the `endpoints.rawPredict` method. \n\n### Response body\n\nIf successful, the response is a generic HTTP response whose format is defined by the method."]]
