Platform For AI:Call services over the Internet or a private network through a gateway

Choose a gateway type

EAS offers shared and dedicated gateways. The differences are outlined below:

Recommendations:

• Use a Shared Gateway for development and testing environments.

• Use a dedicated gateway for production environments.

Choose an access method

How to call a service

Calling an EAS service requires three key elements:

• Service endpoint

• Authorization token

• A request structured according to the model's API specification

Invocation example

To call the DeepSeek-R1-Distill-Qwen-7B model service deployed with vLLM, you need the following elements:

• Method: POST

• Request path: <EAS_ENDPOINT>/v1/chat/completions (chat API)

• Headers:

  • Authorization: <Token>

  • Content-Type: application/json

• Request body:

  {
      "model": "DeepSeek-R1-Distill-Qwen-7B",
      "messages": [
      {
          "role": "system",
          "content": "You are a helpful assistant."
      },
      {
          "role": "user",
          "content": "hello!"
      }
      ]
  }

Code example:

Assume <EAS_ENDPOINT> is http://16********.cn-hangzhou.pai-eas.aliyuncs.com/api/predict/test.

curl http://16********.cn-hangzhou.pai-eas.aliyuncs.com/api/predict/test/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: *********5ZTM1ZDczg5OT**********" \
-X POST \
-d '{
    "model": "DeepSeek-R1-Distill-Qwen-7B",
    "messages": [
    {
        "role": "system",
        "content": "You are a helpful assistant."
    },
    {
        "role": "user",
        "content": "hello!"
    }
    ]
}' 

import requests

# Replace with your actual endpoint.
url = 'http://16********.cn-hangzhou.pai-eas.aliyuncs.com/api/predict/test/v1/chat/completions'
# The value of Authorization in the header is your actual token.
headers = {
    "Content-Type": "application/json",
    "Authorization": "*********5ZTM1ZDczg5OT**********",
}
# Construct the service request based on the data format required by the specific model.
data = {
    "model": "DeepSeek-R1-Distill-Qwen-7B",
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "hello!"
        }
    ]
}
# Send the request.
resp = requests.post(url, json=data, headers=headers)
print(resp)
print(resp.content)

For more information about calling Large Language Model (LLM) services, see LLM service invocation.

More scenarios

• Models deployed from the Model Gallery: The Overview page for these models usually provides API call examples, including the full URL path and request format.

  cURL command

  Basic syntax: curl [options] [URL]

  Common parameters (options):

  • -X: Specifies the HTTP method, such as -X POST.

  • -H: Adds a request header, such as -H "Content-Type: application/json".

  • -d: Adds a request body, such as -d '{"key": "value"}'.

  

  Python code

  The following Python code uses the Qwen3-Reranker-8B model as an example. Note that its URL and request body are different from the cURL command example. Be sure to refer to the corresponding model introduction.

  

• Scenario-based deployments:

  • ComfyUI API calls

  • SDWebUI API calls

  • TensorFlow Serving service calls

  • Triton service calls

• Services deployed using a generic processor, including TensorFlow, Caffe, and PMML: For more information, see Construct a service request based on a generic processor.

• Other custom services: The request format is determined by the data input format you define in your custom image or code.

• Models you trained yourself: The calling method is the same as for the original model.

FAQ

For common questions and solutions related to service invocation, see Service Invocation FAQ.