Batch prediction for Cloud Storage

This page describes how to get batch predictions using Cloud Storage.

1. Prepare your inputs

Batch for Gemini models accept one JSON Lines (JSONL) file stored in Cloud Storage as input data. Each line in the batch input data is a request to the model, following the same format for Gemini API.

For example:

{"request":{"contents": [{"role": "user", "parts": [{"text": "What is the relation between the following video and image samples?"}, {"fileData": {"fileUri": "gs://cloud-samples-data/generative-ai/video/animals.mp4", "mimeType": "video/mp4"}}, {"fileData": {"fileUri": "gs://cloud-samples-data/generative-ai/image/cricket.jpeg", "mimeType": "image/jpeg"}}]}], "generationConfig": {"temperature": 0.9, "topP": 1, "maxOutputTokens": 256}}}

Download the sample batch request file

Once you've prepared your input data, and uploaded it to Cloud Storage. Make sure the AI Platform Service Agent has permission to the Cloud Storage file.

2. Submit a batch job

You can create a batch job through the Google Cloud console, the Google Gen AI SDK, or the REST API.

Console

  1. In the Vertex AI section of the Google Cloud console, go to the Batch Inference page.

    Go to Batch Inference

  2. Click Create.

REST

To create a batch prediction job, use the projects.locations.batchPredictionJobs.create method.

Before using any of the request data, make the following replacements:

  • LOCATION: A region that supports Gemini models.
  • PROJECT_ID: Your project ID.
  • MODEL_PATH: the publisher model name, for example, publishers/google/models/gemini-2.5-flash; or the tuned endpoint name, for example, projects/PROJECT_ID/locations/LOCATION/models/MODEL_ID, where MODEL_ID is the model ID of the tuned model.
  • INPUT_URI: The Cloud Storage location of your JSONL batch prediction input such as gs://bucketname/path/to/file.jsonl.
  • OUTPUT_FORMAT: To output to a Cloud Storage bucket, specify jsonl.
  • DESTINATION: For BigQuery, specify bigqueryDestination. For Cloud Storage, specify gcsDestination.
  • OUTPUT_URI_FIELD_NAME: For BigQuery, specify outputUri. For Cloud Storage, specify outputUriPrefix.
  • OUTPUT_URI: For BigQuery, specify the table location such as bq://myproject.mydataset.output_result. The region of the output BigQuery dataset must be the same as the Vertex AI batch prediction job. For Cloud Storage, specify the bucket and directory location such as gs://mybucket/path/to/output.

HTTP method and URL: 

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/batchPredictionJobs

Request JSON body: 

{
  "displayName": "my-cloud-storage-batch-prediction-job",
  "model": "MODEL_PATH",
  "inputConfig": {
    "instancesFormat": "jsonl",
    "gcsSource": {
      "uris" : "INPUT_URI"
    }
  },
  "outputConfig": {
    "predictionsFormat": "OUTPUT_FORMAT",
    "DESTINATION": {
      "OUTPUT_URI_FIELD_NAME": "OUTPUT_URI"
    }
  }
}

To send your request, choose one of these options:

curl

Save the request body in a file named request.json, and execute the following command: 

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/batchPredictionJobs"

PowerShell

Save the request body in a file named request.json, and execute the following command: 

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/batchPredictionJobs" | Select-Object -Expand Content

You should receive a JSON response similar to the following.

The response includes a unique identifier for the batch job. You can poll for the status of the batch job using the BATCH_JOB_ID. For more information, see Monitor the job status. Note: Custom Service account, live progress, CMEK, and VPCSC reports are not supported.

Python

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True
 

import time

from google import genai
from google.genai.types import CreateBatchJobConfig, JobState, HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))
# TODO(developer): Update and un-comment below line
# output_uri = "gs://your-bucket/your-prefix"

# See the documentation: https://googleapis.github.io/python-genai/genai.html#genai.batches.Batches.create
job = client.batches.create(
    # To use a tuned model, set the model param to your tuned model using the following format:
    # model="projects/{PROJECT_ID}/locations/{LOCATION}/models/{MODEL_ID}
    model="gemini-2.5-flash",
    # Source link: https://storage.cloud.google.com/cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl
    src="gs://cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl",
    config=CreateBatchJobConfig(dest=output_uri),
)
print(f"Job name: {job.name}")
print(f"Job state: {job.state}")
# Example response:
# Job name: projects/%PROJECT_ID%/locations/us-central1/batchPredictionJobs/9876453210000000000
# Job state: JOB_STATE_PENDING

# See the documentation: https://googleapis.github.io/python-genai/genai.html#genai.types.BatchJob
completed_states = {
    JobState.JOB_STATE_SUCCEEDED,
    JobState.JOB_STATE_FAILED,
    JobState.JOB_STATE_CANCELLED,
    JobState.JOB_STATE_PAUSED,
}

while job.state not in completed_states:
    time.sleep(30)
    job = client.batches.get(name=job.name)
    print(f"Job state: {job.state}")
# Example response:
# Job state: JOB_STATE_PENDING
# Job state: JOB_STATE_RUNNING
# Job state: JOB_STATE_RUNNING
# ...
# Job state: JOB_STATE_SUCCEEDED

3. Monitor the job status and progress

After the job is submitted, you can check the status of your batch job using API, SDK and Cloud Console

Console

  1. Go to the Batch Inference page.

    Go to Batch Inference

  2. Select your batch job to monitor its progress.

REST

To monitor a batch prediction job, use the projects.locations.batchPredictionJobs.get method and view the CompletionStats field in the response.

Before using any of the request data, make the following replacements:

  • LOCATION: A region that supports Gemini models.
  • PROJECT_ID: .
  • BATCH_JOB_ID: Your batch job ID.

HTTP method and URL: 

GET https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/batchPredictionJobs/BATCH_JOB_ID

To send your request, choose one of these options:

curl

Execute the following command: 

curl -X GET \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/batchPredictionJobs/BATCH_JOB_ID"

PowerShell

Execute the following command: 

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method GET `
    -Headers $headers `
    -Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/batchPredictionJobs/BATCH_JOB_ID" | Select-Object -Expand Content

You should receive a JSON response similar to the following.

Python

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Gen AI SDK with Vertex AI: 

# Replace the `GOOGLE_CLOUD_PROJECT` and `GOOGLE_CLOUD_LOCATION` values
# with appropriate values for your project.
export GOOGLE_CLOUD_PROJECT=GOOGLE_CLOUD_PROJECT
export GOOGLE_CLOUD_LOCATION=global
export GOOGLE_GENAI_USE_VERTEXAI=True
 

import time

from google import genai
from google.genai.types import CreateBatchJobConfig, JobState, HttpOptions

client = genai.Client(http_options=HttpOptions(api_version="v1"))
# TODO(developer): Update and un-comment below line
# output_uri = "gs://your-bucket/your-prefix"

# See the documentation: https://googleapis.github.io/python-genai/genai.html#genai.batches.Batches.create
job = client.batches.create(
    # To use a tuned model, set the model param to your tuned model using the following format:
    # model="projects/{PROJECT_ID}/locations/{LOCATION}/models/{MODEL_ID}
    model="gemini-2.5-flash",
    # Source link: https://storage.cloud.google.com/cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl
    src="gs://cloud-samples-data/batch/prompt_for_batch_gemini_predict.jsonl",
    config=CreateBatchJobConfig(dest=output_uri),
)
print(f"Job name: {job.name}")
print(f"Job state: {job.state}")
# Example response:
# Job name: projects/%PROJECT_ID%/locations/us-central1/batchPredictionJobs/9876453210000000000
# Job state: JOB_STATE_PENDING

# See the documentation: https://googleapis.github.io/python-genai/genai.html#genai.types.BatchJob
completed_states = {
    JobState.JOB_STATE_SUCCEEDED,
    JobState.JOB_STATE_FAILED,
    JobState.JOB_STATE_CANCELLED,
    JobState.JOB_STATE_PAUSED,
}

while job.state not in completed_states:
    time.sleep(30)
    job = client.batches.get(name=job.name)
    print(f"Job state: {job.state}")
# Example response:
# Job state: JOB_STATE_PENDING
# Job state: JOB_STATE_RUNNING
# Job state: JOB_STATE_RUNNING
# ...
# Job state: JOB_STATE_SUCCEEDED

The status of the a given batch job can be any of the following:

  • JOB_STATE_PENDING: Queue for capacity. The job can be in queue state up to 72-hour before entering running state.
  • JOB_STATE_RUNNING: The input file was successfully validated and the batch is currently being run.
  • JOB_STATE_SUCCEEDED: The batch has been completed and the results are ready
  • JOB_STATE_FAILED: the input file has failed the validation process, or could not be completed within the 24-hour time window after entering RUNNING state.
  • JOB_STATE_CANCELLING: the batch is being cancelled
  • JOB_STATE_CANCELLED: the batch was cancelled

4. Retrieve batch output

When a batch prediction job completes, the output is stored in the Cloud Storage bucket that you specified when you created the job. For succeeded rows, model responses are stored in the response field. Otherwise, error details are stored in the status field for further inspection.

During long-running jobs, completed predictions are continuously exported to the specified output destination. If the batch prediction job is terminated, all completed rows are exported. You are only charged for completed predictions.

Output examples

Successful example

{
  "status": "",
  "processed_time": "2024-11-01T18:13:16.826+00:00",
  "request": {
    "contents": [
      {
        "parts": [
          {
            "fileData": null,
            "text": "What is the relation between the following video and image samples?"
          },
          {
            "fileData": {
              "fileUri": "gs://cloud-samples-data/generative-ai/video/animals.mp4",
              "mimeType": "video/mp4"
            },
            "text": null
          },
          {
            "fileData": {
              "fileUri": "gs://cloud-samples-data/generative-ai/image/cricket.jpeg",
              "mimeType": "image/jpeg"
            },
            "text": null
          }
        ],
        "role": "user"
      }
    ]
  },
  "response": {
    "candidates": [
      {
        "avgLogprobs": -0.5782725546095107,
        "content": {
          "parts": [
            {
              "text": "This video shows a Google Photos marketing campaign where animals at the Los Angeles Zoo take self-portraits using a modified Google phone housed in a protective case. The image is unrelated."
            }
          ],
          "role": "model"
        },
        "finishReason": "STOP"
      }
    ],
    "modelVersion": "gemini-2.0-flash-001@default",
    "usageMetadata": {
      "candidatesTokenCount": 36,
      "promptTokenCount": 29180,
      "totalTokenCount": 29216
    }
  }
}

Failed example

{
  "status": "Bad Request: {\"error\": {\"code\": 400, \"message\": \"Please use a valid role: user, model.\", \"status\": \"INVALID_ARGUMENT\"}}",
  "processed_time": "2025-07-09T19:57:43.558+00:00",
  "request": {
    "contents": [
      {
        "parts": [
          {
            "text": "Explain how AI works in a few words"
          }
        ],
        "role": "tester"
      }
    ]
  },
  "response": {}
}