Alibaba Cloud Model Studio:Model Deployment Overview

Billing by usage duration (Provisioned Throughput)

Cost = Usage Duration × (Input TPM Unit Price × Input TPM + Output TPM Unit Price × Output TPM)

• Upfront payment orders take effect immediately upon payment. The validity period ends at 23:59 on day N. If you place an order after 22:00, the expiration date automatically extends by one day.

• After an upfront payment order expires, the service stops after a 2 hour delay. Resources are retained for 14 hours after stopping, then they are released.

• Upfront payment orders cannot be terminated early.

• For pay-as-you-go billing, if your account has overdue payments, deployed resources are retained and continue to be billed for 24 hours, then they are automatically released.

If the model input exceeds the maximum input tokens or the purchased TPM (Tokens per Minute), calls automatically switch to pay-as-you-go model calls. Inference performance may decrease. Rate limiting occupies public traffic in the workspace. Costs are charged according to the pay-as-you-go model call standard.

• In this case, the API call return header includes the following:x-dashscope-ptu-overflow:true.

• For TPM statistics, go to Model Monitoring (Beijing).

Model types:

• Instruct - The model performs inference in non-thinking mode after deployment.

• Thinking - The model performs inference in thinking mode after deployment.

Billing by usage duration (Model Unit)

Cost = Usage Duration (hours) × Number of Model Units × Model Unit Price

• If you cancel an upfront purchase within the first month, the daily unit price is billed at 1.2 times the original rate.

DashScope

import os
import dashscope

messages = [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Who are you?"},
]
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'
response = dashscope.Generation.call(
    # If you have not set the environment variable, replace the next line with: api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-max-xxx-xxx",  # Replace with the model code from your successful deployment
    messages=messages,
    result_format="message",
    enable_thinking=False,
)
print(response)

OpenAI-compatible interface

import os
from openai import OpenAI


client = OpenAI(
    # If you have not set the environment variable, replace the next line with: api_key="sk-xxx"
    api_key=os.getenv('DASHSCOPE_API_KEY'),
    base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)

completion = client.chat.completions.create(
    model="qwen3-max-xxx-xxx",  # Replace with the model code from your successful deployment
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Who are you?"},
    ],
    extra_body={"enable_thinking": False},
)
print(completion)