Help Center/ MaaS/ Model Calling/ ModelArts Studio (MaaS) API Call Specifications/ Sending a Chat Request (Chat/Post)/ OpenAI-compatible APIs

Updated on 2026-07-29 GMT+08:00

OpenAI-compatible APIs

Constraints

This function is only supported in CN-Hong Kong.

API Information

Parameter	Description	Example Value
API URL	API URL for calling the model service.	https://api-ap-southeast-1.modelarts-maas.com/openai/v1/chat/completions If the OpenAI SDK is used, set base_url to https://api-ap-southeast-1.modelarts-maas.com/openai/v1.
Authentication request header	Provides the server with identity authentication/authorization credentials.	"Authorization": "Bearer $MaaS_API_Key"

Parameter

Description

Example Value

API URL

API URL for calling the model service.

https://api-ap-southeast-1.modelarts-maas.com/openai/v1/chat/completions

If the OpenAI SDK is used, set base_url to https://api-ap-southeast-1.modelarts-maas.com/openai/v1.

Authentication request header

Provides the server with identity authentication/authorization credentials.

"Authorization": "Bearer $MaaS_API_Key"

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.

Model	Version	Supported Region	Value of model
GLM	GLM-5	CN-Hong Kong	glm-5
	GLM-5.1	CN-Hong Kong	glm-5.1
	GLM-5.2	CN-Hong Kong	glm-5.2
DeepSeek	DeepSeek-V4-Pro	CN-Hong Kong	deepseek-v4-pro
	DeepSeek-V4-Flash	CN-Hong Kong	deepseek-v4-flash
	DeepSeek-V3.1	CN-Hong Kong	deepseek-v3.1-terminus
	DeepSeek-V3	CN-Hong Kong	DeepSeek-V3
	DeepSeek-V3.2	CN-Hong Kong	deepseek-v3.2
	DeepSeek-R1-0528	CN-Hong Kong	deepseek-r1-250528

Request Parameters

Category	Parameter	Type	Mandatory	Description
General	model	string	Yes	Definition ID of the model used for generating content. For details about its value, see the model values in Supported models. Constraints N/A Range For details about its value, see the model values in Supported models. Default Value N/A
General	messages	object[]	Yes	Definition List of messages in a dialog. Different models support different types of messages. For details about the message structure, see the System message, User message, Assistant message, and Tool message. Constraints N/A
System message	messages.role	string	Yes	Definition Role that sends a message. Constraints N/A Range system: A message sent by the system. Default Value N/A
	messages.content	string/object[]	Yes	Definition Content of the message sent by the specified role. Constraints N/A
	messages.content.type	string	Yes	Definition Type of the message sent by the specified role. Constraints N/A Range text: Text message. Default Value N/A
	messages.content.text	string	Yes	Definition Content of a text message. Constraints N/A Range N/A Default Value N/A
User message	messages.role	string	Yes	Definition Role that sends a message. Constraints N/A Range user: A message sent by a user. Default Value N/A
	messages.content	string/object[]	Yes	Definition Content of the message sent by the specified role. Constraints N/A
	messages.content.type	string	Yes	Definition Type of the message sent by the specified role. Constraints N/A Range text: Text message. Default Value N/A
	messages.content.text	string	Yes	Definition Content of a text message. Constraints N/A Range N/A Default Value N/A
Assistant message	messages.role	string	Yes	Definition Role that sends a message. Constraints N/A Range assistant: A message returned by the model. Default Value N/A
	messages.content	string/object[]	Yes	Definition Content of the message sent by the specified role. Constraints N/A
	messages.tool_calls	array	No	Definition Tool call records from previous model responses in the dialog history. Constraints This parameter is mandatory when the value of messages.role is tool. Range N/A Default Value N/A
	messages.tool_calls.id	string	Yes	Definition ID of the tool called by the model. Constraints This parameter is mandatory when the value of messages.role is tool. Range N/A Default Value N/A
	messages.tool_calls.type	string	Yes	Definition Tool type. Constraints This parameter is mandatory when the value of messages.role is tool. Range function: Function calling. Default Value N/A
	messages.tool_calls.function	object	Yes	Definition Function information corresponding to the tool called by the model. Constraints N/A
	messages.tool_calls.function.arguments	string	Yes	Definition JSON parameters generated by the model for calling the function. Constraints This parameter is mandatory when the value of messages.role is tool. Range N/A Default Value N/A
	messages.tool_calls.function.name	string	Yes	Definition Name of the function to be called by the model. This is the user-defined function name. Constraints This parameter is mandatory when the value of messages.role is tool. Range N/A Default Value N/A
Tool message	messages.role	string	Yes	Definition Role that sends a message. Constraints N/A Range tool: A message sent by a function call. Default Value N/A
	messages.tool_call_id	string	Yes	Definition ID of the tool called by the model. Constraints This parameter is mandatory when the value of messages.role is tool. Range N/A Default Value N/A
	messages.content	string/object[]	Yes	Definition Content of the message sent by the specified role. Constraints N/A
Deep thinking control	chat_template_kwargs	dict[str, Any]	No	Definition Additional keyword parameters passed to the template renderer, which can be used to control whether the model enables deep thinking mode. For details, see Thinking Control for Deep Thinking Models. Constraints N/A
Model output behavior configuration	max_completion_tokens	integer/null	No
	max_tokens	integer/null	No
	continue_final_message	boolean	No	Definition Specifies whether to enable prefix continuation. Constraints To enable this function, set add_generation_prompt to false. Otherwise, an error is reported. Range true: Enable prefix continuation. false: Disable prefix continuation. Default Value false
	add_generation_prompt	boolean	No	Definition Whether to add the prompt generated by the model to the chat template. This is a parameter used by the chat template in the tokenizer configuration of the model. Constraints This parameter and continue_final_message are mutually exclusive and cannot be both set to true. Range true: Add the prompt generated by the model to the chat template. false: Do not add the prompt generated by the model to the chat template. Default Value true
	temperature	float/null	No	Definition Sampling temperature, used to control the randomness of the content generated by the model. A higher value (for example, greater than 1) will make the model output more random, divergent, and creative, while a lower value (for example, 0.1) will make the output more focused, deterministic, and conservative. Constraints It is recommended that you adjust either temperature or top_p. Range [0,2] Default Value DeepSeek-V3, DeepSeek-R1-0528, and DeepSeek-V4 apply special handling to inputs: DeepSeek-V3: If the temperature is less than or equal to 1, it is multiplied by 0.3. If the temperature is greater than 1, 0.7 is subtracted from it. If the temperature is empty, it defaults to 0.6. DeepSeek-R1-0528: Regardless of the user input, the value remains 0.6. DeepSeek-V4: In thinking mode, the value is always 1.0, regardless of the user input. For other models, the input is used if provided; otherwise, it defaults to 0.6.
	top_p	float/null	No	Definition Nucleus sampling probability threshold, used to control the diversity of the content generated by the model. Similar to the temperature parameter but operates differently, allowing finer control over the vocabulary range of the model's output. When set close to 0, the model samples from only the most probable tokens, resulting in very conservative and highly deterministic outputs. When set close to 1, there is virtually no restriction on the vocabulary, leading to more random and divergent outputs. Constraints It is recommended that you adjust either temperature or top_p. Range (0,1] Default Value DeepSeek-V4: In thinking mode, the value is always 1.0, regardless of the user input. Other models: 0.7
	top_k	integer	No	Definition Controls the model to select only from the top k most probable tokens during generation, influencing the randomness of the generated text. Higher values increase randomness, while lower values enhance determinism. Constraints N/A Range >=0 Default Value 20
	frequency_penalty	number/null	No	Definition Frequency penalty coefficient, which is an important parameter used to control the diversity of model outputs. The probability of a token reappearing decreases proportionally based on its frequency in the generated text. The more frequently a token appears, the lower its likelihood of being used again. Constraints DeepSeek-V4 series: This parameter is not supported. Range [-2,2] 0: No penalty is applied. Positive value: Increases the penalty. A larger value makes the model more likely to introduce new tokens and topics to avoid repetition. Negative value: Reduces the penalty (acting as a reward). The model becomes more inclined to reuse previously generated words, which often results in repetitive and verbose text (generally not recommended). Default Value 0
	presence_penalty	number/null	No	Definition Presence penalty coefficient, which is an important parameter used to control the diversity of model outputs. This reduces the probability that the model will repeatedly use previously mentioned tokens or topics, thereby encouraging it to generate new content. As long as a token has appeared at least once in the previously generated text, the model imposes a fixed penalty on it to reduce the probability of it being selected again. The model determines this penalty based solely on whether the token has appeared so far. A positive value increases the likelihood of the model generating novel content. Constraints DeepSeek-V4 series: This parameter is not supported. Range [-2,2] 0: No penalty is applied. Positive value: Increases the penalty. A larger value makes the model more likely to introduce new tokens and topics to avoid repetition. Negative value: Reduces the penalty (acting as a reward). The model becomes more inclined to reuse previously generated words, which often results in repetitive and verbose text (generally not recommended). Default Value 0
	logit_bias	map/null	No	Definition Logit bias. It adjusts the probability of a specified token appearing in the model's output. The input is a JSON object mapping tokens to bias values ranging from [-100, 100]. Lower values decrease the likelihood, while higher values increase the chance of selection. Example: {Token ID: Bias value, Token ID: Bias value, ...}. A token ID is the numeric identifier of a specific token. Constraints This parameter is not supported by models with deep thinking capabilities. Range [-100, 100] -100: Completely prevents the token from being selected. 100: Ensures only this token can be selected. Actual effects may vary by model. Default Value null
	logprobs	boolean/null	No	Definition Log probability. Controls whether the model returns the log probabilities of the output tokens. Constraints N/A Range true: Log probabilities are returned. false: Log probabilities are not returned. Default Value false
	top_logprobs	integer/null	No	Definition Number of log probabilities to return. If the value is N, the model returns the log probabilities of N output tokens. Constraints This parameter is valid only when logprobs is set to true. Range An integer from 0 to 20 Default Value 0
	stream	boolean/null	No	Definition Determines whether the response content is returned as a stream. Constraints N/A Range false: Returns results once all content has been generated by the model. true: Returns content piece by piece, ending with data: [DONE]. Default Value false
	stream_options	object/null	No	Definition Options for streaming responses. Constraints This parameter can be set only when stream is true.
	stream_options.include_usage	boolean	No	Definition Indicates whether to output token usage information of the current request before the streaming response ends. Constraints Currently, this feature cannot be disabled. Range true: An additional chunk is returned before data: [DONE]. In this chunk, the usage field displays the token usage of the entire request, and the choices field is an empty array. false: The token usage information of this request is not returned. Default Value true
	stop	string / string[] / null	No	Definition When the model encounters the string specified in the stop field, the generation stops and the string itself does not appear in the response. The stop token does not hit the token in the CoT, but only hits the part in the formal answer content. Constraints A maximum of four strings are supported. Range N/A Default Value N/A
	reasoning_effort	string	No	Definition Controls the reasoning intensity. Constraints This field takes effect only in thinking mode. Involved models: DeepSeek-V4 series and GLM-5.2 Range high Default Value high
Tool call	tools	object[]/null	No	Definition List of tools available for the model to call, which may be included in the model's response. Configure this structure when you require the model to specify the tools to be called. Constraints N/A
	tools.type	string	Yes	Definition Tool type. Constraints N/A Range function: Function calling. Default Value N/A
	tools.function	object	Yes	Definition Controls whether the model's response contains the tools to be called. Constraints N/A
	tools.function.name	string	Yes	Definition Name of the function to be called. Constraints N/A Range N/A Default Value N/A
	tools.function.description	string	No	Definition Description of the function to be called. The model will determine if the tool is needed for the current task based on this description. Constraints N/A Range N/A Default Value N/A
	tools.function.parameters	object	No	Definition Function request parameters, described in JSON format. Example: { "type": "object", "properties": { "parameter name": { "type": "string \| number \| boolean \| object \| array", "description": "Parameter description" } }, "required": ["Mandatory parameters"] } Parameters must conform to JSON specifications. Constraints N/A
	tool_choice	string/object	No	Definition Controls how the model calls tools. For details about the types supported by the model, see Tool Choices for Models. Constraints N/A Range none: Do not call any tool. auto: The model decides whether to call tools or not. named: The model must call the specified function, as defined by the tool_choice.type and tool_choice.function fields. Default Value If no tools are provided, the default value is none. If tools are provided, the default value is auto.
	tool_choice.type	string	Yes	Definition Type of the call, which should be function here. Constraints N/A Range function: Function calling. Default Value N/A
	tool_choice.function	object	Yes	Definition Information about the function to be called by the model. Constraints N/A
	tool_choice.function.name	string	Yes	Definition Name of the function to be called by the model. This function must be declared in the tools parameter list. Constraints N/A Range N/A Default Value N/A

Response Parameters (Non-Streaming)

Parameter	Type	Description
created	integer	Definition Unix timestamp (in seconds) indicating when the request was created. Range N/A
id	string	Definition Unique identifier of this request. Range N/A
model	string	Definition Model ID used in this request. Range Model ID used in this request.
object	string	Definition Model API type. Range chat.completion.
choices	object[]	Definition A list of model-generated completion choices for this request.
choices.finish_reason	string	Definition Reason why the model stopped generating: Range stop: The model output ended naturally or hit the field specified in the request parameter stop. length: The model output triggered the max_tokens limit (length limit of CoT + answer content). tool_calls: The model triggered tool calls.
choices.index	integer	Definition Index of the current element in the choices list. Range N/A
choices.message	object	Definition Content generated by the model.
choices.message.role	string	Definition The role of the author of this message. Range assistant: A message returned by the model. tool: A message sent by a function call.
choices.message.content	string	Definition Message content generated by the model. Range N/A
choices.message.reasoning_content	string/null	Definition CoT content generated by the model, only returned by deep thinking models. Range N/A
choices.message.tool_calls	object[]/null	Definition Tool call information generated by the model, returned only if tool calls were triggered.
choices.message.tool_calls.id	string	Definition ID of the called tool. Range N/A
choices.message.tool_calls.type	string	Definition Tool type. Range function: Function calling.
choices.message.tool_calls.function	object	Definition Function called by the model.
choices.message.tool_calls.function.name	string	Definition Name of the function called by the model. Range N/A
choices.message.tool_calls.function.arguments	string	Definition JSON input generated by the model for calling the function. Range N/A
choices.logprobs	object/null	Definition Log probability information for the content.
choices.logprobs.content	object[]/null	Definition Log probability information for each token in the generated message.
choices.logprobs.content.token	string	Definition Token in the generated message. Range N/A
choices.logprobs.content.logprob	float	Definition Log probability of the token in the generated message. Range N/A
choices.logprobs.content.bytes	integer[]/null	Definition List of integers representing the UTF-8 byte values of the token. This field is empty if the token does not have a valid UTF-8 representation.
choices.logprobs.content.top_logprobs	object[]	Definition List of the most likely candidate tokens at this position, along with their respective log probabilities.
choices.logprobs.content.top_logprobs.token	string	Definition Candidate token. Range N/A
choices.logprobs.content.top_logprobs.logprob	float	Definition Log probability of the candidate token. Range N/A
choices.logprobs.content.top_logprobs.bytes	integer[]/null	Definition List of integers representing the UTF-8 byte values of the candidate token. This field is empty if the token does not have a valid UTF-8 representation.
usage	object	Definition Token usage of this request.
usage.completion_tokens	integer	Definition The number of tokens consumed by the model to generate the completion response. Range N/A
usage.prompt_tokens	integer	Definition The number of tokens consumed by the model to process the input prompt. Range N/A
usage.total_tokens	integer	Definition The total number of tokens consumed by this request (including input and output tokens). Range N/A
usage.completion_tokens_details	object	Definition A detailed breakdown of the tokens consumed by the model's generated output.
usage.completion_tokens_details.reasoning_tokens	integer	Definition The number of tokens consumed by the model to generate the chain-of-thought output. Range N/A
usage.prompt_tokens_details	object	Definition A detailed breakdown of the input prompt tokens provided to the model..
usage.prompt_tokens_details.cached_tokens	integer	Definition Token usage of the cached input content. Range N/A
service_tier	string	Definition Service tier used for this request. Range default

Response Parameters (Streaming)

Parameter	Type	Description
created	integer	Definition Unix timestamp (in seconds) indicating when the request was created. Range N/A
id	string	Definition Unique identifier of this request. Range N/A
model	string	Definition Name and version of the model used in this request. Range Model ID used in this request.
object	string	Definition Fixed as chat.completion.chunk.
choices	object[]	Definition A list of model-generated completion choices for this request.
choices.finish_reason	string	Definition Reason why the model stops generating tokens. Range: reason why the model stops generating tokens. Range: stop: The model output ends naturally or is truncated due to matching the field specified in the stop request parameter. length: The model output is truncated because the model output limit is reached. tool_calls: The model calls tools.
choices.index	integer	Definition Index of the current element in the choices list. Range N/A
choices.delta	object	Definition Incremental output from the model.
choices.delta.role	string	Definition The role of the author of this message. Range system: A message sent by the system. user: A message sent by a user. assistant: A message returned by the model. tool: A message sent by a function call.
choices.delta.content	string	Definition Message content generated by the model. Range N/A
choices.delta.reasoning_content	string/null	Definition The model's CoT process. Range N/A
choices.delta.tool_calls	object[]/null	Definition Tool call information generated by the model.
choices.message.tool_calls.id	string	Definition ID of the called tool. Range N/A
choices.message.tool_calls.type	string	Definition Tool type. Currently, it only supports function. Range function: Function calling.
choices.message.tool_calls.function	object	Definition Function called by the model.
choices.message.tool_calls.function.name	string	Definition Name of the function called by the model. Range N/A
choices.message.tool_calls.function.arguments	string	Definition JSON parameters generated by the model for calling the function. The model does not always generate valid JSON, and may fabricate some parameters that are not defined in your function parameter specifications. Before calling a function, verify that these parameters are valid in your code. Range N/A
choices.logprobs	object/null	Definition Log probability information for the content.
choices.logprobs.content	object[]/null	Definition Log probability information for each token in the generated message.
choices.logprobs.content.token	string	Definition Token in the generated message. Range N/A
choices.logprobs.content.logprob	float	Definition Log probability of the token in the generated message. Range N/A
choices.logprobs.content.bytes	integer[]/null	Definition List of integers representing the UTF-8 byte values of the token. This field is empty if the token does not have a valid UTF-8 representation.
choices.logprobs.content.top_logprobs	object[]	Definition List of the most likely candidate tokens at this position, along with their respective log probabilities.
choices.logprobs.content.top_logprobs.token	string	Definition Candidate token. Range N/A
choices.logprobs.content.top_logprobs.logprob	float	Definition Log probability of the candidate token. Range N/A
choices.logprobs.content.top_logprobs.bytes	integer[]/null	Definition List of integers representing the UTF-8 byte values of the candidate token. This field is empty if the token does not have a valid UTF-8 representation.
usage	object	Definition Token usage of this request.
usage.completion_tokens	integer	Definition The number of tokens consumed by the model to generate the completion response. Range N/A
usage.prompt_tokens	integer	Definition The number of tokens consumed by the model to process the input prompt. Range N/A
usage.total_tokens	integer	Definition The total number of tokens consumed by this request (including input and output tokens). Range N/A
usage.completion_tokens_details	object	Definition A detailed breakdown of the tokens consumed by the model's generated output.
usage.completion_tokens_details.reasoning_tokens	integer	Definition The number of tokens consumed by the model to generate the chain-of-thought output. Range N/A
usage.prompt_tokens_details	object	Definition A detailed breakdown of the input prompt tokens provided to the model.
usage.prompt_tokens_details.cached_tokens	integer	Definition Token usage of the cached input content. Range N/A
service_tier	string	Definition Service tier used for this request. Range default
first_token_return_time	float	Definition Time when the model returned the first token of the chunk. Range N/A

Thinking Control for Deep Thinking Models

Model	Default Mode	Thinking Control
GLM-5.2 GLM-5.1 GLM-5	Deep thinking	"chat_template_kwargs": {"thinking": True}
DeepSeek-V4-Flash DeepSeek-V4-Pro	Deep thinking	"chat_template_kwargs": {"thinking": True}
DeepSeek-R1-0528	Deep thinking	Cannot be disabled.
DeepSeek-V3.1	Non-thinking	"chat_template_kwargs": {"thinking": True}
DeepSeek-V3.2	Non-thinking	"chat_template_kwargs": {"thinking": True}

Tool Choices for Models

Model	Supported Tool Choice
GLM-5.2 GLM-5.1	none auto named
GLM-5	none auto
DeepSeek-V4-Flash DeepSeek-V4-Pro DeepSeek-R1-0528 DeepSeek-V3.2	none auto named
DeepSeek-V3 DeepSeek-V3.1	auto named

Example 1: Streaming response

Example request:

Python
Curl

import requests
import json
if __name__ == '__main__':
        url = "https://api-ap-southeast-1.modelarts-maas.com/openai/v1/chat/completions" # API URL
    api_key = "MAAS_API_KEY"  # Replace MAAS_API_KEY with the obtained API key.

    # Send request.
    headers = {
        'Content-Type': 'application/json',
        'Authorization': f'Bearer {api_key}'
    }
    data = {
        "model": "glm-5.2",  # Model parameter. You can change the model parameter as required.
        "stream":True,
        "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)

Run the following commands in the Linux environment:

curl --request POST \
  --url https://api-ap-southeast-1.modelarts-maas.com/openai/v1/chat/completions \
  --header 'authorization: Bearer $MAAS_API_KEY' \
  --header 'content-type: application/json' \
  --data '{
  "model": "glm-5.2",
  "stream": true,
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

Example response:

data: {"id":"8697e7dad55f4ad5ae65f006ba18f2fc","object":"chat.completion.chunk","created":1782266611,"model":"glm-5.2","choices":[{"index":0,"delta":{"content":"Hello!"}}],"service_tier":"default","first_token_return_time":1.7822666148251362E9}

data: {"id":"8697e7dad55f4ad5ae65f006ba18f2fc","object":"chat.completion.chunk","created":1782266611,"model":"glm-5.2","choices":[{"index":0,"delta":{"content":" How"}}],"service_tier":"default","first_token_return_time":1.7822666148726385E9}

data: {"id":"8697e7dad55f4ad5ae65f006ba18f2fc","object":"chat.completion.chunk","created":1782266611,"model":"glm-5.2","choices":[{"index":0,"delta":{"content":"can I help"}}],"service_tier":"default","first_token_return_time":1.7822666149221663E9}

data: {"id":"8697e7dad55f4ad5ae65f006ba18f2fc","object":"chat.completion.chunk","created":1782266611,"model":"glm-5.2","choices":[{"index":0,"delta":{"content":"you"}}],"service_tier":"default","first_token_return_time":1.7822666149709113E9}

data: {"id":"8697e7dad55f4ad5ae65f006ba18f2fc","object":"chat.completion.chunk","created":1782266611,"model":"glm-5.2","choices":[{"index":0,"delta":{"content":"?"}}],"service_tier":"default","first_token_return_time":1.782266615021146E9}

data: {"id":"8697e7dad55f4ad5ae65f006ba18f2fc","object":"chat.completion.chunk","created":1782266611,"model":"glm-5.2","choices":[{"index":0,"delta":{"content":""},"finish_reason":"stop"}],"service_tier":"default","first_token_return_time":1.782266615021146E9}

data: {"id":"8697e7dad55f4ad5ae65f006ba18f2fc","object":"chat.completion.chunk","created":1782266611,"model":"glm-5.2","choices":[],"usage":{"prompt_tokens":20,"total_tokens":134,"completion_tokens":114,"prompt_tokens_details":{"cached_tokens":0},"completion_tokens_details":{"reasoning_tokens":105}},"service_tier":"default","first_token_return_time":1.7822666150211895E9}

data: [DONE]

Example 2: Prefix Continuation

Example request:

Python
Curl

import requests
import json
if __name__ == '__main__':
    url = "https://api-ap-southeast-1.modelarts-maas.com/openai/v1/chat/completions" # API URL
    api_key = "MAAS_API_KEY"  # Replace MAAS_API_KEY with the obtained API key.

    # Send request.
    headers = {
        'Content-Type': 'application/json',
        'Authorization': f'Bearer {api_key}'
    }
    data = {
        "model": "glm-5.2",
        "continue_final_message": True,
        "add_generation_prompt": False,
        "messages": [
        {
          "role": "user",
      "content": "You are a calculator. Please calculate: 1 + 1."
        },
        {
          "role": "assistant",
          "content": "="
        }
        ],
       "stream": False
    }
    response = requests.post(url, headers=headers, data=json.dumps(data), verify=False)
    # Print result.
    print(response.status_code)
    print(response.text)

Run the following commands in the Linux environment:

curl --request POST \
--url https://api-ap-southeast-1.modelarts-maas.com/openai/v1/chat/completions \
  --header 'authorization: Bearer $MAAS_API_KEY' \
  --header 'content-type: application/json' \
  --data '{
  "model": "glm-5.2",
  "continue_final_message": true,
  "add_generation_prompt": false,
  "messages": [
    {
      "role": "user",
      "content": "You are a calculator. Please calculate: 1 + 1."
    },
    {
      "role": "assistant",
      "content": "="
    }
  ],
  "stream": false
}'

Example response:

{
  "id": "784f6f4091a7430b993c561bc4f1d216",
  "object": "chat.completion",
  "created": 1782268057,
  "model": "glm-5.2",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": " 2"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 21,
    "total_tokens": 24,
    "completion_tokens": 3,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0
    }
  },
  "service_tier": "default"
}

Example 3: Multi-Turn Conversation

Example request:

Python
Curl

import requests
import json
if __name__ == '__main__':
    url = "https://api-ap-southeast-1.modelarts-maas.com/openai/v1/chat/completions" # API URL
    api_key = "MAAS_API_KEY"  # Replace MAAS_API_KEY with the obtained API key.

import requests
import json
if __name__ == '__main__':
    url = "https://api-ap-southeast-1.modelarts-maas.com/v2/chat/completions"  # API URL
    api_key = "MAAS_API_KEY"  # Replace MAAS_API_KEY with the obtained API key.

    # Send request.
    headers = {
        'Content-Type': 'application/json',
        'Authorization': f'Bearer {api_key}'
    }
    data = {
        "model": "glm-5.2",
        "messages": [
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
               "content": "Recommend a programming book for beginners."
            },
            {
                "role": "assistant",
               "content": "I recommend Python Crash Course: A Hands-On, Project-Based Introduction to Programming. It is perfect for beginners with no prior programming experience."
            },
            {
                "role": "user",
              "content": "I want to learn data analysis. Is this book suitable for that?"
            }
        ],
        "stream": False
    }
    response = requests.post(url, headers=headers, data=json.dumps(data), verify=False)
    # Print result.
    print(response.status_code)
    print(response.text)

Run the following commands in the Linux environment:

curl --request POST \
  --url https://api-ap-southeast-1.modelarts-maas.com/openai/v1/chat/completions \
  --header 'authorization: Bearer $MAAS_API_KEY' \
  --header 'content-type: application/json' \
  --data '{
  "model": "glm-5.2",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "Recommend a programming book for beginners."
    },
    {
      "role": "assistant",
               "content": "I recommend Python Crash Course: A Hands-On, Project-Based Introduction to Programming. It is perfect for beginners with no prior programming experience."
    },
    {
      "role": "user",
      "content": "I want to learn data analysis. Is this book suitable for that?"
    }
  ],
  "stream": false
}'

Example response:

{
  "id": "814f0581080f422bb06ccff00dc3ea51",
  "object": "chat.completion",
  "created": 1782269006,
  "model": "glm-5.2",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "That's a good choice. Python is the dominant language for data analysis, and the foundational chapters of this book will help you build a solid base. Once you finish it, you can move on to Python for Data Analysis to focus specifically on your data analysis skills."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 65,
    "total_tokens": 103,
    "completion_tokens": 38,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0
    }
  },
  "service_tier": "default"
}

Example 4: Tool Calling

Example request:

Python
Curl

import requests
import json
if __name__ == '__main__':
     url = "https://api-ap-southeast-1.modelarts-maas.com/openai/v1/chat/completions" # API URL
    api_key = "MAAS_API_KEY" # Replace MAAS_API_KEY with the obtained API key.

    # Send request.
    headers = {
        'Content-Type': 'application/json',
        'Authorization': f'Bearer {api_key}'
    }
    data = {
        "model": "glm-5.2",
        "messages": [
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            {
                "role": "user",
            "content": "What is the weather in Beijing today?"
            },
            {
                "role": "assistant",
                "tool_calls": [
                    {
                        "id": "call_e8d8a81c1f3942868443360f",
                        "type": "function",
                        "function": {
                            "name": "get_weather",
                        "arguments": "{\"city\": \"Beijing\", \"unit\": \"celsius\"}"
                        }
                    }
                ]
            },
            {
                "role": "tool",
                "tool_call_id": "call_e8d8a81c1f3942868443360f",
            "content": "{\"city\": \"Beijing\", \"temperature\": 26, \"unit\": \"celsius\", \"condition\": \"Sunny\"}"
            }
        ],
        "tools": [
            {
                "type": "function",
                "function": {
                    "name": "get_weather",
                "description": "Get the current weather for a specified city.",
                    "parameters": {
                        "type": "object",
                        "properties": {
                            "city": {
                                "type": "string",
                            "description": "City name, for example, Beijing."
                            },
                            "unit": {
                                "type": "string",
                                "enum": [
                                    "celsius",
                                    "fahrenheit"
                                ],
                            "description": "Temperature unit"
                            }
                        },
                        "required": [
                            "city"
                        ]
                    }
                }
            }
        ],
        "tool_choice": "auto",
        "stream": False
    }
    response = requests.post(url, headers=headers, data=json.dumps(data), verify=False)
    # Print result.
    print(response.status_code)
    print(response.text)

Run the following commands in the Linux environment:

curl --request POST \
  --url https://api-ap-southeast-1.modelarts-maas.com/openai/v1/chat/completions \
  --header 'authorization: Bearer $MAAS_API_KEY' \
  --header 'content-type: application/json' \
  --data '{
  "model": "glm-5.2",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "What is the weather in Beijing today?"
    },
    {
      "role": "assistant",
      "content": null,
      "tool_calls": [
        {
          "id": "call_e8d8a81c1f3942868443360f",
          "type": "function",
          "function": {
            "name": "get_weather",
            "arguments": "{\"city\": \"Beijing\", \"unit\": \"celsius\"}"
          }
        }
      ]
    },
    {
      "role": "tool",
      "tool_call_id": "call_e8d8a81c1f3942868443360f",
      "content": "{\"city\": \"Beijing\", \"temperature\": 26, \"unit\": \"celsius\", \"condition\": \"Sunny\"}"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for a specified city.",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {
              "type": "string",
              "description": "City name, for example, Beijing."
            },
            "unit": {
              "type": "string",
              "enum": [
                "celsius",
                "fahrenheit"
              ],
              "description": "Temperature unit"
            }
          },
          "required": [
            "city"
          ]
        }
      }
    }
  ],
  "tool_choice": "auto",
  "stream": false
}'

Example response:

{
  "id": "d41eba20c8a545c69864003a3fcd5ae2",
  "object": "chat.completion",
  "created": 1782270016,
  "model": "glm-5.2",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Here is the weather information for Beijing today: \n\n- ️ Weather Conditions: Sunny \n- ️ Temperature: 26°C \n\n It is sunny in Beijing today with a comfortable temperature of 26°C, making it a perfect day to go out! If you need to check the weather for any other city, feel free to let me know anytime~"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 246,
    "total_tokens": 306,
    "completion_tokens": 60,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0
    }
  },
  "service_tier": "default"
}

Parent Topic: Sending a Chat Request (Chat/Post)

Previous topic: MaaS Standard API V1

Next topic: Anthropic-compatible APIs

Feedback

Was this page helpful?

Helpful Not helpful

Provide feedback

Thank you very much for your feedback. We will continue working to improve the documentation.See the reply and handling status in My Cloud VOC.

The system is busy. Please try again later.

For any further questions, feel free to contact us through the chatbot.

Chatbot