gcloud ai-platform predict Stay organized with collections Save and categorize content based on your preferences.
- NAME
- gcloud ai-platform predict - run AI Platform online prediction
- SYNOPSIS
gcloud ai-platform predict--model=MODEL(--json-instances=JSON_INSTANCES|--json-request=JSON_REQUEST|--text-instances=TEXT_INSTANCES)[--region=REGION][--signature-name=SIGNATURE_NAME][--version=VERSION][GCLOUD_WIDE_FLAG …]
- DESCRIPTION
gcloud ai-platform predictsends a prediction request to AIPlatform for the given instances. This command will read up to 100 instances,though the service itself will accept instances up to the payload limit size(currently, 1.5MB). If you are predicting on more instances, you should usebatch prediction viagcloudai-platformjobssubmitprediction.- REQUIRED FLAGS
--model=MODEL- Name of the model.
- Exactly one of these must be specified:
--json-instances=JSON_INSTANCES- Path to a local file from which instances are read. Instances are in JSONformat; newline delimited.
An example of the JSON instances file:
{"images":[0.0,…,0.1],"key":3}{"images":[0.0,…,0.1],"key":2}…
This flag accepts "-" for stdin.
--json-request=JSON_REQUEST- Path to a local file containing the body of JSON request.
An example of a JSON request:
{"instances":[{"x":[1,2],"y":[3,4]},{"x":[-1,-2],"y":[-3,-4]}]}
This flag accepts "-" for stdin.
--text-instances=TEXT_INSTANCES- Path to a local file from which instances are read. Instances are in UTF-8encoded text format; newline delimited.
An example of the text instances file:
107,4.9,2.5,4.5,1.7100,5.7,2.8,4.1,1.3…
This flag accepts "-" for stdin.
- OPTIONAL FLAGS
--region=REGION- Google Cloud region of the regional endpoint to use for this command. For theglobal endpoint, the region needs to be specified as
global.Learn more about regional endpoints and see a list of available regions:https://cloud.google.com/ai-platform/prediction/docs/regional-endpoints
REGIONmust be one of:global,asia-east1,asia-northeast1,asia-southeast1,australia-southeast1,europe-west1,europe-west2,europe-west3,europe-west4,northamerica-northeast1,us-central1,us-east1,us-east4,us-west1. --signature-name=SIGNATURE_NAME- Name of the signature defined in the SavedModel to use for this job. Defaults toDEFAULT_SERVING_SIGNATURE_DEF_KEY inhttps://www.tensorflow.org/api_docs/python/tf/compat/v1/saved_model/signature_constants,which is "serving_default". Only applies to TensorFlow models.
--version=VERSION- Model version to be used.
If unspecified, the default version of the model will be used. To list modelversions run
gcloudai-platformversionslist
- 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
- These variants are also available:
gcloudalphaai-platformpredictgcloudbetaai-platformpredict
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 2025-07-22 UTC.