ChatWithDesensitize - Data Management - Alibaba Cloud Documentation Center

Chat API with DMS Data Masking capabilities.

Operation description

Chat API with DMS Data Masking capabilities.

Debugging

You can run this interface directly in OpenAPI Explorer, saving you the trouble of calculating signatures. After running successfully, OpenAPI Explorer can automatically generate SDK code samples.

Debug

Authorization information

The following table shows the authorization information corresponding to the API. The authorization information can be used in the Action policy element to grant a RAM user or RAM role the permissions to call this API operation. Description:

Operation: the value that you can use in the Action element to specify the operation on a resource.
Access level: the access level of each operation. The levels are read, write, and list.
Resource type: the type of the resource on which you can authorize the RAM user or the RAM role to perform the operation. Take note of the following items:
- For mandatory resource types, indicate with a prefix of * .
- If the permissions cannot be granted at the resource level, All Resources is used in the Resource type column of the operation.
Condition Key: the condition key that is defined by the cloud service.
Associated operation: other operations that the RAM user or the RAM role must have permissions to perform to complete the operation. To complete the operation, the RAM user or the RAM role must have the permissions to perform the associated operations.

Operation	Access level	Resource type	Condition key	Associated operation
dms:ChatWithDesensitize	none	All Resources ``	none	none

Request parameters

Parameter	Type	Required	Description	Example
InstanceId	long	Yes	The ID of the instance, used to specify the corresponding data masking rules. You can call the ListInstances or GetInstance operation to query the ID of the instance.	123***
Messages	array<object>	No	The conversation context passed to the model, arranged in chronological order.
	object	No	For each message body of the dialog, the standard format is as follows: { "content": "$message", "role": "$role：system，user，assistant" }
Model	string	No	The model name. Supported Models: Qwen series text-only Large Language Models (Commercial and Open-source). Multi-modal models are not supported.	qwen-plus
Stop	array	No	Stop sequences.
	string	No	Stop sequences: Generation will terminate immediately if the model generates any of the strings specified in the 'stop' parameter.	\n
NeedDesensitization	boolean	No	Whether to enable data masking. Defaults to false.	false
DesensitizationRule	string	No	Masking category. Required when needDataMasking is true.	UserInfo
MaxTokens	integer	No	Limits the maximum number of tokens the model can generate. If the output exceeds this value, generation will be truncated. Suitable for scenarios where you need to control the output length.	256
PresencePenalty	number	No	Controls the degree of repetition in generated text. Valid values: [-2.0, 2.0]. Positive values decrease repetition, while negative values increase it.	0.0
ResponseFormat	string	No	The format of the returned content. Valid values: text: Plain text response; json_object: Standardized JSON string.	text
Seed	integer	No	Random seed. Used to ensure the reproducibility of results under the same input and parameters. Valid values: [0, 2^31−1].	1
EnableThinking	boolean	No	Specifies whether to enable Thinking Mode when using hybrid thinking models.	true
ThinkingBudget	integer	No	The maximum number of tokens allowed for the model's internal reasoning process.	256
Temperature	number	No	The sampling temperature controls the diversity of the generated text. The higher the temperature, the more diverse the generated text, and conversely, the more deterministic the generated text. Valid values: [0, 2).	1
TopLogprobs	integer	No	Specifies the number of most likely candidate tokens to return at each generation step. Valid values: [0, 5].	1
TopK	integer	No	Specifies the number of candidate tokens to consider during sampling. Higher values increase randomness, while lower values make the output more deterministic. Set to null or a value greater than 100 to disable.	10
TopP	number	No	The probability threshold for nucleus sampling, used to control the diversity of the generated text. Higher Top-P values result in more diverse generated text. Valid values: (0,1.0].	0.5
XDashScopeDataInspection	string	No	Specifies whether to further identify non-compliant information in both input and output content, building upon the built-in content safety capabilities of the Tongyi Qianwen API.	{}
SearchOptions	object	No	Web search strategy.
	string	No	The strategy key-value pair for Web search.	{}
ModalitiesList	array	No	Output data modality; only applicable to the Qwen-Omni model.
	string	No	Output data modality.	text
AudioJson	string	No	Output audio voice and format; only applicable to the Qwen-Omni model, provided that the modalities parameter is set to ["text", "audio"].	{}
EnableCodeInterpreter	boolean	No	Specifies whether to enable the code interpreter feature. Takes effect only when model is qwen3-max-preview and enable_thinking is true.	false
Logprobs	boolean	No	Specifies whether to return the log probabilities of the output tokens.	false
VlHighResolutionImages	boolean	No	Specifies whether to increase the maximum pixel limit of input images to the equivalent of 16,384 tokens.	false
EnableSearch	boolean	No	Whether to enable web search.	false

Response parameters

Parameter	Type	Description	Example
	object	The response.
RequestId	string	ID of the request.	0C1CB646-1DE4-4AD0-B4A4-7D47DD52E931
ErrorCode	string	Error code.	UnknownError
ErrorMessage	string	Error message.	UnknownError
Success	boolean	Indicates whether the operation was successful. Valid values: true: The request was successful. false: The request fails.	true
Data	object	The data returned.
Created	string	The Unix timestamp (in seconds) when the request was created.	1763710100
Model	string	The model used for this request.	qwen-plus
Choices	array<object>	The candidate array for model-generated content.
Choices	object	Candidate content generated by the model.
FinishReason	string	Finish reason: ● stop: The model reached a natural stop point or a specified stop sequence. ● length: Generation ended because the maximum number of tokens was reached. ● tool_calls: The model stopped because it needs to call a tool to proceed.	stop
Message	object	The message body output by the model.
Content	string	The content of the model's response.
ReasoningContent	string	The internal reasoning content of the model.
Role	string	Message role.	system
Logprobs	object	Token probability information of model output.
	any	Token probability information of model output.	{}
Usage	object	The token consumption information of this request.
CompletionTokens	string	The number of output tokens.	10
PromptTokens	string	The number of input tokens.	9
TotalTokens	string	The total number of tokens consumed.	19
PromptTokensDetails	object	Fine-grained classification of input tokens.
	string	Fine-grained classification of input tokens.	{}
CompletionTokensDetails	object	Fine-grained classification of output tokens when using the Qwen-VL model.
	string	Fine-grained classification of output tokens.	{}
Message	string	Error message, provided when StatusCode is not 200.	InvalidParameter
StatusCode	string	Error code, 200 for normal calls, others for exceptions.	200
Type	string	Error type.	invalid_request_error

Examples

Sample success responses

JSONformat

{
  "RequestId": "0C1CB646-1DE4-4AD0-B4A4-7D47DD52E931",
  "ErrorCode": "UnknownError",
  "ErrorMessage": "UnknownError",
  "Success": true,
  "Data": {
    "Created": 1763710100,
    "Model": "qwen-plus",
    "Choices": [
      {
        "FinishReason": "stop",
        "Message": {
          "Content": "",
          "ReasoningContent": "",
          "Role": "system"
        },
        "Logprobs": {
          "key": {}
        }
      }
    ],
    "Usage": {
      "CompletionTokens": 10,
      "PromptTokens": 9,
      "TotalTokens": 19,
      "PromptTokensDetails": {
        "key": {}
      },
      "CompletionTokensDetails": {
        "key": {}
      }
    },
    "Message": "InvalidParameter",
    "StatusCode": 200,
    "Type": "invalid_request_error"
  }
}

Error codes

For a list of error codes, visit the Service error codes.

Change history

Change time	Summary of changes	Operation
2025-11-26	The request parameters of the API has changed. The response structure of the API has changed	View Change Details
2025-11-25	Add Operation	View Change Details