Flex PayGo

pip install --upgrade google-genai

# 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

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
  )
)

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" }
    }
  }'

{
  "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
  }
}

pip install --upgrade google-genai

# 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

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
  )
)

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" }
    }
  }'

{
  "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
  }
}

sdk_http_response=HttpResponse(
  headers=
) candidates=[Candidate(
  avg_logprobs=-0.539712212302468,
  content=Content(
    parts=[
      Part(
        text="""Response to sample request.
        """
      ),
    ],
    role='model'
  ),
  finish_reason=<FinishReason.STOP: 'STOP'>
)] 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=<MediaModality.TEXT: 'TEXT'>,
      token_count=1408
    ),
  ],
  prompt_token_count=5,
  prompt_tokens_details=[
    ModalityTokenCount(
      modality=<MediaModality.TEXT: 'TEXT'>,
      token_count=5
    ),
  ],
  thoughts_token_count=1356,
  total_token_count=2769,
  traffic_type=<TrafficType.ON_DEMAND_FLEX: 'ON_DEMAND_FLEX'>
) automatic_function_calling_history=[] parsed=None

{
  "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
  }
}