gcloud beta ai endpoints direct-predict Stay organized with collections Save and categorize content based on your preferences.
- NAME
- gcloud beta ai endpoints direct-predict - run Vertex AI online direct prediction
- SYNOPSIS
gcloud beta ai endpoints direct-predict(ENDPOINT:--region=REGION)--json-request=JSON_REQUEST[GCLOUD_WIDE_FLAG …]
- DESCRIPTION
(BETA)gcloud beta ai endpoints direct-predictsends adirect prediction request to Vertex AI endpoint for the given instances. Therequest limit is 10MB.- EXAMPLES
- To direct predict against an endpoint
under project123in regionexample, run:us-central1gcloudbetaaiendpointsdirect-predict123--project=example--region=us-central1--json-request=input.json - POSITIONAL ARGUMENTS
- Endpoint resource - The endpoint to do online direct prediction. The argumentsin this group can be used to specify the attributes of this resource. (NOTE)Some attributes are not given arguments in this group but can be set in otherways.
To set the
projectattribute:- provide the argument
endpointon the command line with a fullyspecified name; - provide the argument
--projecton the command line; - set the property
core/project.
This must be specified.
ENDPOINT- ID of the endpoint or fully qualified identifier for the endpoint.
To set the
nameattribute:- provide the argument
endpointon the command line.
This positional argument must be specified if any of the other arguments in thisgroup are specified.
- provide the argument
--region=REGION- Cloud region for the endpoint.
To set the
regionattribute:- provide the argument
endpointon the command line with a fullyspecified name; - provide the argument
--regionon the command line; - set the property
ai/region; - choose one from the prompted list of available regions.
- provide the argument
- provide the argument
- Endpoint resource - The endpoint to do online direct prediction. The argumentsin this group can be used to specify the attributes of this resource. (NOTE)Some attributes are not given arguments in this group but can be set in otherways.
- REQUIRED FLAGS
--json-request=JSON_REQUEST- Path to a local file containing the body of a JSON request.
An example of a JSON request:
{"inputs":[{"dtype":"STRING",shape:[1],"string_val":["hello world"]},{"dtype":"INT32",shape:[1],"int_val":[42]}]}
This flag accepts "-" for stdin.
- GCLOUD WIDE FLAGS
- These flags are available to all commands:
--access-token-file,--account,--billing-project,--configuration,--flags-file,--flatten,--format,--help,--impersonate-service-account,--log-http,--project,--quiet,--trace-token,--user-output-enabled,--verbosity.Run
$gcloud helpfor details. - NOTES
- This command is currently in beta and might change without notice. Thesevariants are also available:
gcloudaiendpointsdirect-predictgcloudalphaaiendpointsdirect-predict
Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.
Last updated 2025-11-11 UTC.