Flex PayGo Stay organized with collections Save and categorize content based on your preferences.

Python

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Google 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_ENTERPRISE=True

Initialize your GenAI client to use Flex PayGo. After performing this step, you won't need to make further adjustments to your code to interact with the Gemini API using Flex PayGo on the same client.

from google import genai
from google.genai.types import HttpOptions
client = genai.Client(
  vertexai=True, project='your_project_id', location='global',
  http_options=HttpOptions(
    api_version="v1",
      headers={
        "X-Vertex-AI-LLM-Shared-Request-Type": "flex"
      },
    # timeout = 600000  # Timeout in milliseconds
  )
)

REST

After you set up your environment, you can use REST to test a text prompt. The following sample sends a request to the publisher model endpoint.

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

• PROJECT_ID: Your [project ID](/resource-manager/docs/creating-managing-projects#identifiers). .
• MODEL_ID: The model ID of the model for which you want to initialize Flex PayGo. For a list of models that support Flex PayGo, see Model versions.
• PROMPT_TEXT: The text instructions to include in the prompt. JSON.

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json; charset=utf-8" \
  -H "X-Server-Timeout: 600" \
  -H "X-Vertex-AI-LLM-Shared-Request-Type: flex" \
  "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/MODEL_ID:generateContent" -d \
  $'{
      "contents": {
        "role": "model",
        "parts": { "text": "PROMPT_TEXT" }
    }
  }'

You should receive a JSON response similar to the following.

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Response to sample request."
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 3,
    "candidatesTokenCount": 900,
    "totalTokenCount": 1957,
    "trafficType": "ON_DEMAND_FLEX",
    "thoughtsTokenCount": 1054
  }
}

• Use the generateContent method to request that the response is returned after it's fully generated. To reduce the perception of latency to a human audience, stream the response as it's being generated by using the streamGenerateContent method.
• The multimodal model ID is located at the end of the URL before the method (for example, gemini-3.5-flash). This sample might support other models as well.
• When you use a regional API endpoint (for example, us-central1), the region from the endpoint URL determines where the request is processed. Any conflicting location in the resource path is ignored.

Python

Install

pip install --upgrade google-genai

To learn more, see the SDK reference documentation.

Set environment variables to use the Google 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_ENTERPRISE=True

Initialize your GenAI client to use Flex PayGo. After performing this step, you won't need to make further adjustments to your code to interact with the Gemini API using Flex PayGo on the same client.

from google import genai
from google.genai.types import HttpOptions
client = genai.Client(
  vertexai=True, project='your_project_id', location='global',
  http_options=HttpOptions(
    api_version="v1",
      headers={
        "X-Vertex-AI-LLM-Request-Type": "shared",
        "X-Vertex-AI-LLM-Shared-Request-Type": "flex"
      },
    # timeout = 600000  # Timeout in milliseconds
  )
)

REST

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

• PROJECT_ID: Your [project ID](/resource-manager/docs/creating-managing-projects#identifiers). .
• MODEL_ID: The model ID of the model for which you want to initialize Flex PayGo. For a list of models that support Flex PayGo, see Model versions.
• PROMPT_TEXT: The text instructions to include in the prompt. JSON.

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json; charset=utf-8" \
  -H "X-Server-Timeout: 600" \
  -H "X-Vertex-AI-LLM-Request-Type: shared" \
  -H "X-Vertex-AI-LLM-Shared-Request-Type: flex" \
  "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/MODEL_ID:generateContent" -d \
  $'{
      "contents": {
        "role": "model",
        "parts": { "text": "PROMPT_TEXT" }
    }
  }'

You should receive a JSON response similar to the following.

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Response to sample request."
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 3,
    "candidatesTokenCount": 900,
    "totalTokenCount": 1957,
    "trafficType": "ON_DEMAND_FLEX",
    "thoughtsTokenCount": 1054
  }
}

• Use the generateContent method to request that the response is returned after it's fully generated. To reduce the perception of latency to a human audience, stream the response as it's being generated by using the streamGenerateContent method.
• The multimodal model ID is located at the end of the URL before the method (for example, gemini-3.5-flash). This sample might support other models as well.
• When you use a regional API endpoint (for example, us-central1), the region from the endpoint URL determines where the request is processed. Any conflicting location in the resource path is ignored.

Python

You can verify whether Flex PayGo was utilized for a request from the traffic_type field in the response. If your request was processed using Flex PayGo, the traffic_type field is set to ON_DEMAND_FLEX.

sdk_http_response=HttpResponse(
  headers=
) candidates=[Candidate(
  avg_logprobs=-0.539712212302468,
  content=Content(
    parts=[
      Part(
        text="""Response to sample request.
        """
      ),
    ],
    role='model'
  ),
  finish_reason=
)] create_time=datetime.datetime(2025, 12, 3, 20, 32, 55, 916498, tzinfo=TzInfo(0)) model_version='gemini-2.5-flash' prompt_feedback=None response_id='response_id' usage_metadata=GenerateContentResponseUsageMetadata(
  candidates_token_count=1408,
  candidates_tokens_details=[
    ModalityTokenCount(
      modality=,
      token_count=1408
    ),
  ],
  prompt_token_count=5,
  prompt_tokens_details=[
    ModalityTokenCount(
      modality=,
      token_count=5
    ),
  ],
  thoughts_token_count=1356,
  total_token_count=2769,
  traffic_type=
) automatic_function_calling_history=[] parsed=None

REST

You can verify whether Flex PayGo was utilized for a request from the trafficType field in the response. If your request was processed using Flex PayGo, the trafficType field is set to ON_DEMAND_FLEX.

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Response to sample request."
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 3,
    "candidatesTokenCount": 900,
    "totalTokenCount": 1957,
    "trafficType": "ON_DEMAND_FLEX",
    "thoughtsTokenCount": 1054
  }
}