All Products
Search

This Product

    Data Management:ChatWithDesensitizeSSE

    Document Center

    Data Management:ChatWithDesensitizeSSE

    Last Updated:Mar 31, 2026

    This API provides an SSE interface for chat with data masking.

    Operation description

    This API provides chat functionality with DMS data masking capabilities.

    Try it now

    Try this API in OpenAPI Explorer, no manual signing needed. Successful calls auto-generate SDK code matching your parameters. Download it with built-in credential security for local usage.

    Test

    RAM authorization

    The table below describes the authorization required to call this API. You can define it in a Resource Access Management (RAM) policy. The table's columns are detailed below:

    • Action: The actions can be used in the Action element of RAM permission policy statements to grant permissions to perform the operation.

    • API: The API that you can call to perform the action.

    • Access level: The predefined level of access granted for each API. Valid values: create, list, get, update, and delete.

    • Resource type: The type of the resource that supports authorization to perform the action. It indicates if the action supports resource-level permission. The specified resource must be compatible with the action. Otherwise, the policy will be ineffective.

      • For APIs with resource-level permissions, required resource types are marked with an asterisk (*). Specify the corresponding Alibaba Cloud Resource Name (ARN) in the Resource element of the policy.

      • For APIs without resource-level permissions, it is shown as All Resources. Use an asterisk (*) in the Resource element of the policy.

    • Condition key: The condition keys defined by the service. The key allows for granular control, applying to either actions alone or actions associated with specific resources. In addition to service-specific condition keys, Alibaba Cloud provides a set of common condition keys applicable across all RAM-supported services.

    • Dependent action: The dependent actions required to run the action. To complete the action, the RAM user or the RAM role must have the permissions to perform all dependent actions.

    Action

    Access level

    Resource type

    Condition key

    Dependent action

    dms:ChatWithDesensitizeSSE

    none

    *All Resource

    *

    		 None None

    Request syntax

    POST /worknode/innerapi/services HTTP/1.1

    Request parameters

    Parameter

    Type

    Required

    Description

    Example
    InstanceId

    integer

    Yes

    Instance ID. Use the instance ID to specify the corresponding data masking rule. Obtain the value of this parameter by invoking the ListInstances or GetInstance interface.

    123***
    Messages

    array

    No

    The context passed to the Large Language Model (LLM), ordered by conversation sequence.

    [ { "content": "你好", "role": "user" } ]

    any

    No

    The context passed to the Large Language Model (LLM), ordered by conversation sequence.

    { "content": "你好", "role": "user" }
    Model

    string

    No

    Model name. Supported models include Qwen series plain text Large Language Models (commercial and open source versions). Multimodal models are not supported.

    qwen-plus
    Stop

    array

    No

    List of stop words.

    string

    No

    List of stop words.

    \n
    NeedDesensitization

    boolean

    No

    Whether data masking is required. Default is false.

    false
    DesensitizationRule

    string

    No

    Data masking category. Cannot be empty if `needDesensitization` is true.

    UserInfo
    MaxTokens

    integer

    No

    Maximum number of tokens for model output. If the generated content exceeds this value, generation stops early. Use this parameter to control output length.

    256
    PresencePenalty

    string

    No

    Controls the repetition of content when the model generates text. Value range: [-2.0, 2.0]. Positive values reduce repetition, while negative values increase it.

    0.0
    ResponseFormat

    string

    No

    Format of the returned content. Options: text: output text response; json_object: output a standard JSON string.

    text
    Seed

    integer

    No

    Random number seed. Ensures reproducible results with the same input and parameters. Value range: [0, 2^31−1].

    1
    EnableThinking

    boolean

    No

    Enable thinking mode when using a hybrid thinking model.

    true
    ThinkingBudget

    integer

    No

    Maximum number of tokens for the thinking process.

    256
    Temperature

    string

    No

    Sampling temperature. Controls the diversity of text generated by the model. A higher temperature generates more diverse text; a lower temperature generates more deterministic text. Value range: [0, 2).

    1
    TopLogprobs

    integer

    No

    Specify the number of candidate tokens with the highest probability returned by the model at each generation step. Value range: [0, 5].

    1
    TopK

    integer

    No

    Specify the number of candidate tokens used for sampling during generation. A larger value results in more random output; a smaller value results in more deterministic output. If set to null or greater than 100, it is disabled.

    10
    TopP

    string

    No

    Probability threshold for nucleus sampling. Controls the diversity of text generated by the model. A higher top_p generates more diverse text. Value range: (0, 1.0].

    0.5
    XDashScopeDataInspection

    string

    No

    Based on the Content Moderation capabilities of the Qwen API, determine whether to further detect non-compliant information in input and output content.

    {}
    SearchOptions

    object

    No

    Web search policy.

    {}

    string

    No

    Web search policy.

    {}
    ModalitiesList

    array

    No

    Output data modalities. Applies only to the Qwen-Omni model.

    ["text","audio"]

    string

    No

    Output data modality.

    text
    AudioJson

    string

    No

    Tone and format of the output audio. Applies only to the Qwen-Omni model, and the `modalities` parameter must be [\"text\",\"audio\"].

    {}
    EnableCodeInterpreter

    boolean

    No

    Enable the code interpreter feature. This takes effect only when `model` is `qwen3-max-preview` and `enable_thinking` is true.

    false
    Logprobs

    boolean

    No

    Return the logarithmic probability of output tokens.

    false
    VlHighResolutionImages

    boolean

    No

    Increase the pixel limit of input images to the pixel value corresponding to 16384 tokens.

    false
    EnableSearch

    boolean

    No

    Enable web search.

    false
    IncludeUsage

    boolean

    No

    Include Token consumption information in the last block of the response during streaming output.

    true
    Stream

    boolean

    No

    Use streaming output.

    1-68f11da7e2b826dcc63c5877-hd
    Input

    string

    No

    Input for the vectorization model.

    test
    Dimensions

    integer

    No

    Dimensions of the vectorization model.

    256
    Parameters

    string

    No

    Model configuration parameters.

    {}

    Response elements

    Element

    Type

    Description

    Example

    object

    RequestId

    string

    Request ID.

    283C461F-11D8-48AA-B695-DF092DA32AF3
    Data

    string

    Returned data.

    true
    ErrorCode

    string

    Error code.

    UnknownError
    ErrorMessage

    string

    Error message.

    UnknownError
    Success

    boolean

    Indicates whether the request was successful. Return values are as follows:

    • true: The request was successful.

    • false: The request failed.

    true

    Examples

    Success response

    JSON format

    {
  "RequestId": "283C461F-11D8-48AA-B695-DF092DA32AF3",
  "Data": "true",
  "ErrorCode": "UnknownError",
  "ErrorMessage": "UnknownError",
  "Success": true
}

    Error codes

    See Error Codes for a complete list.

    Release notes

    See Release Notes for a complete list.