MaaS Standard API V1

Constraints

This function is only available in the CN-Hong Kong region.

API Information

Supported Models

You can log in to the MaaS console and enable the following models on the Model Inference > Real-Time Inference > Built-in Services page. On the model details page in the Model Square, you can view detailed information about the models.

Creating a Chat Request

• Authentication description

  MaaS inference services support API key authentication. The authentication header is in the following format:

  'Authorization': 'Bearer API key of the region where the service is deployed'

• The request and response parameters are as follows.

  Table 2 Request parameters

  Parameter	Mandatory	Default Value	Type	Description
  model	Yes	None	Str	Model to call. For details about the value, see Table 1.
  messages	Yes	N/A	Array	Input question. role shows the role, and content shows the dialog content. Example: "messages": [ {"role": "system","content": "You are a helpful AI assistant."}, {"role": "user","content": "Which number is larger, 9.11 or 9.8?"} ] For more information, see Table 3.
  messages.prefix	No	false	Boolean	Controls whether to enable continuation mode. In this mode, the user provides a message starting with assistant, and the model completes the rest based on that beginning and the input instruction. To use this feature, ensure that the last message in the messages list has the role set to assistant and the prefix parameter set to true. Example: messages = [ {"role": "user", "content": "Write a snippet of Python code"}, {"role": "assistant", "content": "```python\n", "prefix": True} ]
  stream_options	No	None	Object	Specifies whether to display the number of used tokens during streaming output. This parameter is only valid when stream is set to True. You need to set stream_options to {"include_usage": true} to print the number of tokens used. For more information, see Table 4.
  max_tokens	No	None	Int	Maximum number of tokens that can be generated for the current task, including tokens generated by the model and reasoning tokens for deep thinking.
  top_k	No	-1	Int	The candidate set size determines the sampling range during generation. For example, setting it to 50 means only the top 50 scoring tokens are sampled at each step. A larger size increases randomness; a smaller one makes the output more predictable.
  top_p	No	1.0	Float	Nucleus sampling. It keeps only the words with combined probabilities above the threshold p and removes the rest. These selected words are then normalized and sampled again. Lower settings reduce word options, making outputs focused and cautious. Higher settings expand word choices, creating varied and creative outputs. Adjust either temperature or top_p separately for best results, not both at once. Value range: 0 to 1. The value 1 indicates that all tokens are considered.
  temperature	No	1.0	Float	Model sampling temperature. The higher the value, the more random the model output; the lower the value, the more deterministic the output. Adjust either temperature or top_p separately for best results, not both at once. Recommended value of temperature: 0.6 for DeepSeek-V3 and Qwen3 series, and 0.2 for Qwen2.5-VL series.
  stop	No	None	None/Str/List	A list of strings used to stop generation. The output does not contain the stop strings. For example, if the value is set to ["You," "Good"], text generation will stop once either You or Good is reached.
  stream	No	False	Bool	Controls whether to enable streaming inference. The default value is False, indicating that streaming inference is disabled.
  n	No	1	Int	Number of responses generated for each input message. If beam_search is not used, the recommended value range of n is 1 ≤ n ≤10. If n is greater than 1, ensure that greedy_sample is not used for sampling, that is, top_k is greater than 1 and temperature is greater than 0. If beam_search is used, the recommended value range of n is 1 < n ≤ 10. If n is 1, the inference request will fail. NOTE: For optimal performance, keep n at 10 or below. Large values of n can significantly slow down processing. Inadequate video RAM may cause inference requests to fail. You cannot set n higher than 1 for and DeepSeek-V3.
  use_beam_search	No	False	Bool	Controls whether to use beam_search to replace sampling. When this parameter is used, the following parameters must be configured as required: n: > 1 top_p: 1.0 top_k: -1 temperature: 0.0 NOTE: You cannot set n higher than 1 for and DeepSeek-V3.
  presence_penalty	No	0.0	Float	Applies rewards or penalties based on the presence of new words in the generated text. The value range is [-2.0,2.0].
  frequency_penalty	No	0.0	Float	Applies rewards or penalties based on the frequency of each word in the generated text. The value range is [-2.0,2.0].
  length_penalty	No	1.0	Float	Imposes a larger penalty on longer sequences in a beam search process. When this parameter is used, the following parameters must be configured as required: top_k: -1 use_beam_search: true best_of: > 1 NOTE: You cannot set length_penalty for DeepSeek-V3.
  thinking	No	object	-	Controls whether to enable or disable the deep thinking mode for a model. Default value: N/A
  thinking.type	Yes	string	-	enabled: The thinking mode is enabled. The model must think before answering. disabled: The thinking mode is disabled. The model directly answers questions without thinking. Default value: The default value varies depending on the model. You can log in to the MaaS console and view the description of the deep thinking mode in the Version area on the Model Square > Model Details page. Figure 1 Checking the deep thinking mode

  Table 3 Request parameter messages

  Parameter	Mandatory	Default Value	Type	Description
  role	Yes	None	Str	Different roles correspond to different message types. system: developer-entered instructions like response formats and roles for the model to follow. user: user-entered messages including prompts and context information. assistant: responses generated by the model. tool: information returned by the tool when the model calls it.
  content	Yes	None	Str	When role is set to system, this parameter indicates the AI model's personality. { "role": "system", "content": "You are a helpful AI assistant." } When role is set to user, this parameter indicates the question asked by the user. Text-based dialogue: { "role": "user", "content": "Which one is larger, 9.11 or 9.8?" } Image understanding: Supported image formats: PNG, JPEG, JPG, WEBP, BMP, and TIFF. Supported input methods: You can use either the Base64-encoded content of the image or a publicly accessible image URL. Below are code examples for both methods: Using Base64-encoded image content: { "role": "user", "content": [ { "type": "image_url", "image_url": { "url": f"data:image/png;base64,{base64_image}" } }, { "type": "text", "text": "What does the image show?" } ] } The Base64-encoded image format (image/{format}) must match the Content Type in the supported image list. The f denotes a string formatting method used to embed the Base64-encoded image data into the URL. Example: # PNG image f"data:image/png;base64,{base64_image}" # JPEG image f"data:image/jpeg;base64,{base64_image}" # WEBP image: f"data:image/webp;base64,{base64_image}" Using a publicly accessible image URL: { "role": "user", "content": [ { "type": "image_url", "image_url": { "url": "https://example.com/xxx.jpeg" } }, { "type": "text", "text": "What does the image show?" } ] } When role is set to assistant, this parameter indicates the content output by the AI model. {"role": "assistant","content": "9.11 is larger than 9.8."} When role is set to tool, this parameter indicates the responses returned by the tool when the model calls it. {"role": "tool", "content": "The weather in Shanghai is sunny today. The temperature is 10°C."}

  Table 4 Request parameter stream_options

  Parameter	Mandatory	Default Value	Type	Description
  include_usage	No	true	Bool	Specifies whether the streaming response outputs token usage information. true: Each chunk outputs a usage field that shows the total token usage. false: The token usage is not displayed.

  Table 5 Response parameters

  Parameter	Type	Description
  id	Str	Unique ID of the request.
  object	Str	chat.completion type: Multi-turn dialogs are returned.
  created	Int	Timestamp.
  model	Str	Model to call.
  choices	Array	Model output, including the index and message parameters. In message: content is the model's final reply. reasoning content is the model's deep thinking content (for DeepSeek models only).
  usage	Object	Statistics on tokens consumed by the request: This parameter is returned by default for non-streaming requests. This parameter is returned by default for streaming requests. Each chunk outputs a usage field that shows the token usage. Parameters: prompt tokens: number of input tokens. completion tokens: number of output tokens. total tokens: total number of tokens.
  prompt_logprobs	Float	Log probability. You can use this to measure the model's confidence in its output or to explore other options the model provides.

DeepSeek-V3 Text Generation (Non-Streaming) Request Example

This section demonstrates the basic non-streaming usage of a text generation model, using the DeepSeek-V3 model as an example to request a text response via a Python script, cURL command, or OpenAI SDK.

• Python request example:

  import requests
  import json
  
  if __name__ == '__main__':
      url = "https://api-ap-southeast-1.modelarts-maas.com/v1/chat/completions" # API address
      api_key = "MAAS_API_KEY"  # Replace MAAS_API_KEY with the obtained API key.
  
      # Send a request.
      headers = {
          'Content-Type': 'application/json',
          'Authorization': f'Bearer {api_key}' 
      }
      data = {
          "model":"deepseek-v3", # Model name
          "messages": [
              {"role": "system", "content": "You are a helpful assistant."},
              {"role": "user", "content": "Hello"}
          ]
      }
      response = requests.post(url, headers=headers, data=json.dumps(data), verify=False)
  
      # Print result.
      print(response.status_code)
      print(response.text)

• cURL request example:

  curl -X POST "https://api-ap-southeast-1.modelarts-maas.com/v1/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $MAAS_API_KEY" \
    -d '{ 
      "model": "deepseek-v3",
      "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello"}
      ]
  }'

• OpenAI SDK request example:

  from openai import OpenAI
  
  base_url = "https://api-ap-southeast-1.modelarts-maas.com/v1" # API address
  api_key = "MAAS_API_KEY" # Replace MAAS_API_KEY with the obtained API key.
  
  client = OpenAI(api_key=api_key, base_url=base_url)
  
  response = client.chat.completions.create(
      model="deepseek-v3", # Model name
      messages=[
          {"role": "system", "content": "You are a helpful assistant"},
          {"role": "user", "content": "Hello"}
      ]
  )
  
  print(response.choices[0].message.content)

DeepSeek-V3 Text Generation (Streaming) Request Example

This section demonstrates the basic streaming usage of a text generation model, using the DeepSeek-V3 model as an example to request a text response via a Python script or cURL command.

• Python request example:

  from openai import OpenAI
  
  base_url = "https://api-ap-southeast-1.modelarts-maas.com/v1" # API address
  api_key = "MAAS_API_KEY" # Replace MAAS_API_KEY with the obtained API key.
  
  client = OpenAI(api_key=api_key, base_url=base_url)
  
  response = client.chat.completions.create(
      model="deepseek-v3", # Model name
      messages=[
          {"role": "system", "content": "You are a helpful assistant"},
          {"role": "user", "content": "Hello"}
      ],
      stream = True
  )
  
  for chunk in response:
      if not chunk.choices:
          continue
  
      print(chunk.choices[0].delta.content, end="")

• cURL request example:

  curl -X POST "https://api-ap-southeast-1.modelarts-maas.com/v1/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $MAAS_API_KEY" \
    -d '{ 
      "model": "deepseek-v3",
      "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello"}
      ],
      "stream": true,
      "stream_options": { "include_usage": true }
  }'

DeepSeek-V3.1 Text Generation (Non-Streaming) Request Example

This section demonstrates the basic non-streaming usage of a text generation model, using the DeepSeek-V3.1 model as an example to request a text response via a Python script, cURL command, or OpenAI SDK.

• Python request example:

  import requests
  import json
  
  if __name__ == '__main__':
      url = "https://api-ap-southeast-1.modelarts-maas.com/v1/chat/completions"  # API address
      api_key = "MAAS_API_KEY"  # Replace MAAS_API_KEY with the obtained API key.
  
      # Send a request.
      headers = {
          'Content-Type': 'application/json',
          'Authorization': f'Bearer {api_key}'
      }
      data = {
          "model": "deepseek-v3.1-terminus",  # Model
          "messages": [
              {"role": "system", "content": "You are a helpful assistant."},
              {"role": "user", "content": "Hello"}
          ],
          "chat_template_kwargs": {
              "thinking": True  # Specifies whether to enable deep thinking. It is disabled by default.
          }
      }
      response = requests.post(url, headers=headers, data=json.dumps(data), verify=False)
  
      # Print result.
      print(response.status_code)
      print(response.text)

• cURL request example:

  curl -X POST "https://api-ap-southeast-1.modelarts-maas.com/v1/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $MAAS_API_KEY" \
    -d '{
      "model": "deepseek-v3.1-terminus",
      "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello"}
      ],
       "chat_template_kwargs": {
         "thinking": true
       }
    }'

• OpenAI SDK request example:

  from openai import OpenAI
  
  base_url = "https://api-ap-southeast-1.modelarts-maas.com/v1"  # API address
      api_key = "MAAS_API_KEY"  # Replace MAAS_API_KEY with the obtained API key.
  
  client = OpenAI(api_key=api_key, base_url=base_url)
  
  response = client.chat.completions.create(
      model="deepseek-v3.1-terminus",  # Model
      messages=[
          {"role": "system", "content": "You are a helpful assistant"},
          {"role": "user", "content": "Hello"},
      ],
      extra_body={
          "chat_template_kwargs": {
              "thinking": True  # Specifies whether to enable deep thinking. It is disabled by default.
          }
      }
  )
  
  print(response.choices[0].message.content)

Response Example

{
    "id":"chat-71406e38b0d248c9b284709f8435****",
    "object":"chat.completion",
    "created":1740809549,
    "model":"deepseek-v3",
    "choices":[
        {
            "index":0,
            "message":{
                "role":"assistant",
                "content":"\n\n Compare 9.11 and 9.8.:\n\n1. **Compare the integer part**: The integer part of both is 9, which is equal.\n2. **Compare the tenths place**:\n - The tenths place of 9.11 is **1**\n - 9.8 can be considered as 9.80, and its tenths place is **8**\n - **8 > 1**, so 9.8 is larger.\n\n**Conclusion**:\n**9.8 > 9.11**\n(When comparing decimals, line up the digits and compare them directly.)",
                "reasoning_content": "Well, I now need to compare 9.11 and 9.8 which is larger. First of all, I have to recall the method of comparing decimals. When comparing decimals, start by comparing the integer parts. If the integer parts are the same, compare the tenths and hundredths of the decimal parts in sequence until the larger number is determined.\n\nThe integer parts of the two numbers are both 9, so they are the same. Next, compare the tenths. The tenth digit of 9.11 is 1, while the tenth digit of 9.8 is 8. This can be problematic, as some people might directly treat 9.8 as 9.80, or focus on comparing the digits in the tenths place.\n\nNow, comparing the tenths place, 9.8 has an 8, while 9.11 has a 1. Clearly, 8 is greater than 1. So, should we conclude that 9.8 is greater than 9.11? \n\n However, it is important to note that some people might incorrectly assume that the more decimal places a number has, the larger its value. But this is not true; for instance, 0.9 is greater than 0.8999. Thus, having more decimal places does not necessarily mean a larger value. \n\n Additionally, the decimal parts of the two numbers can be aligned to have the same number of digits for comparison. For instance, 9.8 can be written as 9.80, where the tenths place is 8 and the hundredths place is 0. On the other hand, for 9.11, the tenths place is 1 and the hundredths place is 1. Since 8 in the tenths place is greater than 1, 9.80 (which is 9.8) is greater than 9.11.\n\nTherefore, the final conclusion is that 9.8 is larger than 9.11.\n",
                "tool_calls":[]
                },
                "logprobs":null,
                "finish_reason":"stop",
                "stop_reason":null        
        }
    ],
    "usage":{
        "prompt_tokens":21,
        "total_tokens":437,
        "completion_tokens":416
        },
    "prompt_logprobs":null
}