LLM image moderation-AI Guardrails(AI Guardrails)-阿里云帮助中心

Image Moderation Enhanced Edition uses a custom-trained Qwen large language model (LLM) combined with expert models to detect non-compliant content in images, including pornography, suggestive content, politically sensitive content, violence and terrorism, contraband, religious content, ad traffic and spam, inappropriate content, and other risk categories. The service also supports returning raw LLM results. This topic describes how to activate and call the image moderation service.

Image moderation models are under active development. Contact your business manager to provide feedback.

How it works

Image Moderation Enhanced Edition uses a custom-trained Qwen LLM based on image content risk characteristics, providing the following image moderation services:

Image Moderation for Large and Small Model Integration:
The image moderation LLMs for integrated applications and expert model capabilities can fully identify pornographic, suggestive, politically sensitive, terrorist, prohibited, religious, advertising, undesirable, and other illegal content in images.For details on the detection categories, see Rules.
Image Moderation for Large and Small Model Integration_For regions outside the Chinese mainland:
For global services, this feature combines image moderation Large Language Models (LLMs) and expert models to comprehensively detect non-compliant content in images, such as pornography, suggestive content, political content, terrorism, violence, prohibited items, religious content, flags, spam ads, inappropriate content, and abusive language. (Note: For the international version, all LLM inference is processed in the Singapore region.)This service also includes risk controls specific to international markets, including Southeast Asia, the Middle East, and Europe and the Americas. For details on the detection categories, see Rules.
Image Moderation Service Based on LLMs:
LLMs that are customized and trained for image moderation can identify risks in images, such as pornographic content, politically sensitive content, terrorist content, prohibited content, undesirable scenes, abusive content, and ads. The actual output results can be returned.For details on the detection categories, see Rules.
Large Model-Powered Ad Traffic Detection:
Detects adversarial and AI-generated promotional content using large models.For details on the detection categories, see Rules.

For the US (Virginia), Germany (Frankfurt), and China (Hong Kong) regions, LLM inference runs in Singapore. Data and logs are stored locally in the respective regions (Frankfurt and Hong Kong).

Select your service

Service	Description	Supported regions	Use cases
Image Moderation for Large and Small Model Integration(`postImageCheckByVL_global`)	Combines an LLM and expert models to provide more granular labels, such as pornography subcategories, specific behaviors, and specific objects. Offers a wider detection range and richer labels. Provides low false positive and false negative rates.	China (Shanghai), China (Hangzhou), China (Beijing), China (Shenzhen), China (Chengdu)	Social media, live streaming, gaming, e-commerce, and education businesses that require strict risk control and fine-grained policies. Businesses that need detailed risk labels. Highly recommended for new users with high performance requirements.
Image Moderation for Large and Small Model Integration_For regions outside the Chinese mainland (postImageCheckByVL_cb)	For use outside the Chinese mainland, this service extends the Image Moderation for Large and Small Model Integration service with risk controls tailored for regions such as Southeast Asia, the Middle East, and Europe and the Americas.	Singapore, China (Hong Kong), US (Virginia), Germany (Frankfurt)
Image Moderation Service Based on LLMs (baselineCheckByVL)	Provides broad generalization and is suitable for scenarios that focus on broad risk categories without requiring high granularity.	China (Shanghai), China (Hangzhou), China (Beijing), China (Shenzhen), China (Chengdu)	Businesses that want to experience pure LLM-based moderation capabilities. Teams that need raw LLM description results for internal risk control strategies or model fine-tuning. Businesses that do not require fine-grained labels and only need to identify broad risk categories such as pornography, politically sensitive content, and violence and terrorism.
Large Model-Powered Ad Traffic Detection (adCheckByVL)	Uses a custom-trained LLM for deep semantic understanding of images to accurately identify various highly evasive and adversarial ad and spam behaviors, such as disguised contact information, misleading redirects, QR code steganography, and AI-generated spam ads.	China (Shanghai), China (Beijing)	Managing and combating spam ads on platforms such as social media, content communities, and forums. Preventing non-compliant ads that direct users to third-party platforms in the product review or Q&A sections of e-commerce platforms. Detecting spam information in images within comments and live comments in scenarios such as live streaming and short videos.

Prerequisites

Before you begin, ensure that you have:

An active Image Moderation 2.0 subscription (pay-as-you-go)
An Alibaba Cloud account or a RAM user with the AliyunYundunGreenWebFullAccess policy
An AccessKey pair for authentication

Get started

Step 1: Activate the service

Visit the service activation page and activate Image Moderation Enhanced Edition. After activation, the default billing method is pay-as-you-go. Fees are settled daily based on actual usage. You are not charged if you do not call the service. For details on the billing methods, see Billing. You can also purchase pay-as-you-go resource plans. Resource plans offer tiered discounts compared to the pay-as-you-go method and are suitable for users with predictable and high usage.

Step 2: Grant permissions to a RAM user

Create an AccessKey pair for your Alibaba Cloud account or a RAM user. The RAM user must have the AliyunYundunGreenWebFullAccess policy to call Content Moderation APIs.

Log on to the RAM console using your Alibaba Cloud account or as a RAM administrator.
Create a RAM user. See Create a RAM user.
Attach the AliyunYundunGreenWebFullAccess policy to the RAM user. See Manage permissions for RAM users.

Step 3: Install the SDK

Follow the Image Moderation SDK and integration guide to install the SDK and configure your endpoint.

The following table lists all supported regions and endpoints:

Region	Public endpoint	VPC endpoint	Supported service
China (Shanghai)	green-cip.cn-shanghai.aliyuncs.com	green-cip-vpc.cn-shanghai.aliyuncs.com	postImageCheckByVL, baselineCheckByVL, adCheckByVL
China (Hangzhou)	green-cip.cn-hangzhou.aliyuncs.com	green-cip-vpc.cn-hangzhou.aliyuncs.com	postImageCheckByVL, baselineCheckByVL
China (Beijing)	green-cip.cn-beijing.aliyuncs.com	green-cip-vpc.cn-beijing.aliyuncs.com	postImageCheckByVL, baselineCheckByVL, adCheckByVL
China (Shenzhen)	green-cip.cn-shenzhen.aliyuncs.com	green-cip-vpc.cn-shenzhen.aliyuncs.com	postImageCheckByVL, baselineCheckByVL
China (Chengdu)	green-cip.cn-chengdu.aliyuncs.com	N/A	postImageCheckByVL, baselineCheckByVL
Singapore	green-cip.ap-southeast-1.aliyuncs.com	green-cip-vpc.ap-southeast-1.aliyuncs.com	postImageCheckByVL_cb
China (Hong Kong)	green-cip.cn-hongkong.aliyuncs.com	green-cip-vpc.cn-hongkong.aliyuncs.com
US (Virginia)	green-cip.us-east-1.aliyuncs.com	green-cip-vpc.us-east-1.aliyuncs.com
Germany (Frankfurt)	green-cip.eu-central-1.aliyuncs.com	green-cip-vpc.eu-central-1.aliyuncs.com

Important

In the Germany (Frankfurt) and China (Hong Kong) regions, LLM inference runs in the Singapore region. Data and logs are stored locally in the respective regions (Frankfurt and Hong Kong).

Step 4: Configure detection rules (optional)

In the Content Moderation console, configure detection rules: enable or disable detection categories, copy a service, configure a custom image library, configure a custom glossary, query detection records, and review usage data. See Console guide.

API reference

API overview

API: ImageModeration
Service code: postImageCheckByVL_global, postImageCheckByVL_cb, postImageCheckByVL_ec, baselineCheckByVL, adCheckByVL
QPS limit: 50 calls/second per user. Exceeding this limit throttles requests. Contact your business manager for a quota increase.
Billing: Billed per successful request (HTTP 200), settled daily. Pricing varies by service. For details, see the Billing section.

Debug the API

Before integration, you can use Alibaba Cloud OpenAPI online debugging to try the Enhanced Image Moderation and APIs. You can also view sample code and SDK dependency information to obtain an overview of how to use these APIs and their parameters.

Important

API calls through the online debugger are billed.

Image requirements

Constraint	Limit
Supported formats	PNG, JPG, JPEG, BMP, WEBP, TIFF, SVG, HEIC (longest edge < 8,192 px), GIF (first frame), ICO (last image)
Max file size	20 MB
Max dimensions	16,384 px (height or width); 250 million total pixels
Optimal resolution	At least 200 x 200 px (lower resolutions reduce accuracy)
Download timeout	3 seconds
URL restrictions	Publicly accessible; max 2,048 characters; no Chinese characters; one URL per request

Submit an image

Submit an image using one of the following methods per request:

Method	Required parameters	Notes
URL	`imageUrl`	URL must be publicly accessible
OSS authorization	`ossBucketName`, `ossObjectName`, `ossRegionId`	Grant `AliyunCIPScanOSSRole` on the Cloud Resource Access Authorization page
Local upload	Upload via SDK	File is deleted 30 minutes after upload; does not consume OSS storage. See the Image Moderation SDK guide for code examples.

Request parameters

The request body is a JSON object. For required common request parameters, see the Integration guide.

Top-level parameters

Parameter	Type	Required	Example	Description
VlContent	Object			Contains the raw output from the LLM. For more information, see VlContent.
`Service`	String	Yes	`postImageCheckByVL`	The detection service. Valid values: `postImageCheckByVL`: Image Moderation for Large and Small Model Integration `postImageCheckByVL_cb`: Image Moderation for Large and Small Model Integration_For regions outside the Chinese mainland `baselineCheckByVL`: Image Moderation Service Based on LLMs `adCheckByVL`: Large Model-Powered Ad Traffic Detection
`ServiceParameters`	JSONString	Yes	—	A JSON string containing the content detection parameters.

ServiceParameters fields

Parameter	Type	Required	Example	Description
`imageUrl`	String	Conditional	`https://img.alicdn.com/tfs/TB1U4r9AeH2gK0jSZJnXXaT1FXa-2880-480.png`	The URL of the image to moderate. Required when submitting by URL.
`ossBucketName`	String	Conditional	`bucket_01`	The name of the authorized Object Storage Service (OSS) bucket. Required when submitting by OSS.
`ossObjectName`	String	Conditional	`2022023/04/24/test.jpg`	The object key of the image in the OSS bucket. Required when submitting by OSS.
`ossRegionId`	String	Conditional	`cn-beijing`	The region where the OSS bucket is located. Required when submitting by OSS.
`dataId`	String	No	`img123****`	A unique identifier to associate the result with your business data. Alphanumeric characters, underscores, hyphens, and periods. Max 64 characters.
`infoType`	String	No	`customImage`	Specifies additional information to return. Valid values: `customImage` (returns custom image library match details), `vlContent` (returns raw LLM detection results). Separate multiple values with commas. Note The `vlContent` parameter is valid only when you call the `baselineCheckByVL` (Image Moderation Service Based on LLMs) service. `vlContent`: The raw detection results from the LLM.
`referer`	String	No	`www.aliyun.com`	The `Referer` request header, used for hotlink protection. Max 256 characters.

Request example

{
    "Service": "postImageCheckByVL_global",
    "ServiceParameters": {
        "imageUrl": "https://img.alicdn.com/tfs/TB1U4r9AeH2gK0jSZJnXXaT1FXa-2880-480.png",
        "dataId": "img0307****"
    }
}

Response parameters

Top-level response fields

Parameter	Type	Example	Description
`RequestId`	String	`70ED13B0-BC22-576D-9CCF-1CC12FEAC477`	The unique request ID. Used for troubleshooting.
`Code`	Integer	`200`	The status code.
`Msg`	String	`OK`	The response message.
`Data`	Object	—	Detection results.

Data fields

Parameter	Type	Example	Description
`RiskLevel`	String	`high`	Overall risk level, based on the highest-risk label. Valid values: `high`, `medium`, `low`, `none`.
`DataId`	String	`img123******`	Data ID from the request. Returned only if `dataId` was specified in the request.
`Result`	Array	—	Array of detected risk labels. Each entry contains `Label`, `Confidence`, `Description`, and `RiskLevel`.
`Ext`	Object	—	Supplementary information, including custom library matches.

Result fields

Parameter	Type	Example	Description
`Label`	String	`violent_explosion`	Risk label. A single image can match multiple labels.
`Confidence`	Float	`81.22`	Confidence score (0–100, two decimal places). Higher score means higher confidence.
`Description`	String	`Fireworks content`	Human-readable label description. Use `Label` — not `Description` — to determine actions, as this field may change.
`RiskLevel`	String	`high`	Risk level for this label, based on configured score thresholds. Valid values: `high`, `medium`, `low`, `none`.

Ext fields

Parameter	Type	Description
`CustomImage`	JSONArray	Custom library match details. Returned when a submitted image matches a library entry.

CustomImage fields

Parameter	Type	Example	Description
`LibId`	String	`lib0001`	ID of the matched custom library.
`LibName`	String	`Custom Image Library A`	Name of the matched custom library.
`ImageId`	String	`20240307`	ID of the matched image in the library.

Table 6. VlContent

Parameter	Type	Example	Description
OutputText	String	The image shows a large black and blue knife next to some magazines. This image belongs to the 'terrorism' category.	The raw text output from the image moderation LLM.

Response example

{
    "RequestId": "70ED13B0-BC22-576D-9CCF-1CC12FEAC477",
    "Code": 200,
    "Msg": "OK",
    "Data": {
        "RiskLevel": "high",
        "DataId": "img0307****",
        "Result": [
            {
                "Label": "violent_explosion",
                "Confidence": 92.40,
                "Description": "Fireworks content",
                "RiskLevel": "high"
            },
            {
                "Label": "violent_burning",
                "Confidence": 67.15,
                "Description": "Burning scenes",
                "RiskLevel": "medium"
            }
        ],
        "Ext": {}
    }
}

Request and response examples are formatted for readability. Actual API responses do not include line breaks or indentation.

Example response for raw LLM detection results:

{
    "Code": 200,
    "Data": {
        "DataId": "data20240307",
        "Ext": {
            "VlContent": {
                "OutputText": "The image shows a large black and blue knife next to some magazines. This image belongs to the 'terrorism' category."
            }
        },
        "Result": [
            {
                "Confidence": 80.0,
                "Description": "terrorism",
                "Label": "terror"
            }
        ],
        "RiskLevel": "high"
    },
    "Msg": "success",
    "RequestId": "1234-1234-ABCD-1111-2222"
}

Example response for detected risk content:

{
    "Msg": "OK",
    "Code": 200,
    "Data": {
        "DataId": "img0307****",
        "Result": [
            {
                "Label": "violent_crowding",
                "Confidence": 81.88,
                "Description": "crowd gathering"
            },
            {
                "Label": "violent_explosion",
                "Confidence": 74.66,
                "Description": "fireworks content"
            }
        ],
        "RiskLevel": "high"
    },
    "RequestId": "ABCD1234-1234-1234-1234-1234XYZ"
}

Example response for no detected risk:

{
    "Msg": "OK",
    "Code": 200,
    "Data": {
        "DataId": "img123****",
        "Result": [
            {
                "Label": "nonLabel",
                "Description": "No risk detected"
            }
        ],
        "RiskLevel": "none"
    },
    "RequestId": "ABCD1234-1234-1234-1234-1234XYZ"
}

Example response for a whitelist image match:

{
    "Msg": "OK",
    "Code": 200,
    "Data": {
        "DataId": "img123****",
        "Result": [
            {
                "Label": "nonLabel_lib",
                "Confidence": 87.28,
                "Description": "Hit whitelist image library"
            }
        ],
        "RiskLevel": "none"
    },
    "RequestId": "ABCD1234-1234-1234-1234-1234XYZ"
}

Additional information

Example response for raw LLM detection results:

{
    "Code": 200,
    "Data": {
        "DataId": "data20240307",
        "Ext": {
            "VlContent": {
                "OutputText": "The image shows a large black and blue knife next to some magazines. This image belongs to the 'terrorism' category."
            }
        },
        "Result": [
            {
                "Confidence": 80.0,
                "Description": "terrorism",
                "Label": "terror"
            }
        ],
        "RiskLevel": "high"
    },
    "Msg": "success",
    "RequestId": "1234-1234-ABCD-1111-2222"
}

Example response for a custom image library match:

{
    "Code": 200,
    "Data": {
        "DataId": "",
        "Ext": {
            "CustomImage": [
                {
                    "ImageId": "12345",
                    "LibId": "TEST20240307",
                    "LibName": "Risk Image Library A"
                }
            ]
        },
        "Result": [
            {
                "Confidence": 98.18,
                "Label": "violent_explosion_lib",
                "Description": "fireworks content_Hit custom library"
            }
        ],
        "RiskLevel": "high"
    },
    "Msg": "success",
    "RequestId": "5F572704-4C03-51DF-8957-D77BF6E7444E"
}

Risk labels

The service returns risk labels grouped by category. Each label has a confidence score (0–100). Higher score means higher confidence. Enable or disable individual labels in the .

Understanding risk levels and handling results

Each label has a RiskLevel and Confidence. The RiskLevel in the Data object reflects the highest risk across all labels.

Use RiskLevel to guide your moderation workflow:

Risk level	Recommended action
`high`	Block or remove content immediately
`medium`	Route to manual review
`low`	Process only if your use case requires high recall; otherwise treat as no risk
`none`	No risk detected

Tuning confidence thresholds: Default risk score thresholds determine when a label is assigned high, medium, or low. Lowering a threshold increases recall (fewer missed violations) but also increases false positives. Raising a threshold improves precision but may miss some violations. Adjust thresholds per label in the to match your platform's tolerance for false positives versus false negatives.

Store returned risk labels and confidence scores. Use them to prioritize manual review, build annotation datasets, and apply tiered governance policies.

Label reference

Labels are grouped into the categories below. The _tii suffix indicates text detected within the image (text-in-image), not visual content.

Pornographic content (pornographic_*)

Label	Description
`pornographic_adultContent`	Adult pornographic content
`pornographic_cartoon`	Pornographic cartoon content
`pornographic_adultToys`	Adult toys
`pornographic_artwork`	Pornographic artwork
`pornographic_underage`	Child pornography
`pornographic_adultContent_tii`	Pornographic text in the image
`pornographic_suggestive_tii`	Vulgar text in the image
`pornographic_o_tii`	LGBT-related text in the image
`pornographic_organs_tii`	Text describing sexual organs in the image
`pornographic_adultToys_tii`	Text about adult toys in the image

Sexually suggestive content (sexual_*)

Label	Description
`sexual_suggestiveContent`	Vulgar or sexually suggestive content
`sexual_femaleUnderwear`	Underwear or swimwear
`sexual_cleavage`	Female cleavage
`sexual_maleTopless`	Topless males
`sexual_cartoon`	Sexually suggestive cartoon content
`sexual_femaleShoulder`	Suggestive content featuring female shoulders
`sexual_femaleLeg`	Suggestive content featuring female legs
`sexual_pregnancy`	Maternity photos or breastfeeding
`sexual_feet`	Suggestive content featuring feet
`sexual_kiss`	Kissing
`sexual_intimacy`	Intimate behavior
`sexual_intimacyCartoon`	Intimate acts in cartoons or anime

Politically sensitive content (political_*)

Label	Description
`political_historicalNihility`	Content related to historical nihilism or sensitive historical events
`political_historicalNihility_tii`	Text related to historical nihilism
`political_politicalFigure_1`	Current or former leaders
`political_politicalFigure_2`	Family members of leaders
`political_politicalFigure_3`	Provincial or municipal government officials
`political_politicalFigure_4`	Foreign leaders or their family members
`political_politicalFigure_name_tii`	Names of leaders in image text
`political_prohibitedPerson_1`	Disgraced national-level officials
`political_prohibitedPerson_2`	Disgraced provincial- or municipal-level officials
`political_prohibitedPerson_tii`	Names of disgraced officials in image text
`political_taintedCelebrity`	Public figures involved in scandals or major negative events
`political_taintedCelebrity_tii`	Names of scandal-involved celebrities in image text
`political_CNFlag`	The national flag of China
`political_CNMap`	A map of China
`political_logo`	Logos of banned media outlets
`political_outfit`	Military or police uniforms, or combat attire
`political_badge`	National or party emblems
`political_racism_tii`	Special expressions in image text. See the for details.

Violence and terrorism (violent_*)

Label	Description
`violent_explosion`	Fireworks or explosions
`violent_armedForces`	Terrorist organizations
`violent_burning`	Burning scenes
`violent_weapon`	Military equipment
`violent_crowding`	Crowd gatherings
`violent_gun`	Guns
`violent_knives`	Knives
`violent_horrific`	Horrific content
`violent_nazi`	Nazi-related content
`violent_bloody`	Bloody content
`violent_extremistGroups_tii`	Text related to terrorist organizations
`violent_extremistIncident_tii`	Text related to terrorist incidents
`violence_weapons_tii`	Text describing firearms, ammunition, or weapons
`violent_ACU`	Combat uniforms

Contraband (contraband_*)

Label	Description
`contraband_drug`	Illegal drugs or medication
`contraband_drug_tii`	Text describing illegal drugs
`contraband_gamble`	Gambling-related items
`contraband_gamble_tii`	Text describing gambling activities
`contraband_certificate_tii`	Spam or ads for fake certificates or cash-out services in image text

Religious content (religion_*)

Label	Description
`religion_flag`	Religious flags or symbols
`religion_clothing`	Specific attire or symbols. See the for details.
`religion_logo`
`religion_taboo1_tii`
`religion_taboo2_tii`

Flags

Label	Description
`flag_country`	Flag-related content

Spam and promotional content (pt_*)

Label	Description
`pt_logotoSocialNetwork`	Watermarks from social media platforms
`pt_qrCode`	QR codes
`pt_logo`	Logos
`pt_toDirectContact_tii`	Contact information used for spam in image text
`pt_custom_01`	Custom label 01
`pt_custom_02`	Custom label 02

Inappropriate behavior (inappropriate_*)

Label	Description
`inappropriate_smoking`	Smoking-related content
`inappropriate_drinking`	Drinking-related content
`inappropriate_tattoo`	Tattoos
`inappropriate_middleFinger`	Middle finger gesture
`inappropriate_foodWasting`	Food waste

Profanity (profanity_*)

Label	Description
`profanity_oral_tii`	Profanity or vulgar slang in image text
`profanity_offensive_tii`	Severely abusive language in image text

Custom image library labels

Configure a custom image library in the console. When a submitted image matches a library image, the system returns the label with a _lib suffix (for example, violent_explosion_lib). The Confidence score reflects similarity.

No-risk labels

Label	Confidence score	Description
`nonLabel`	Not returned	No threats detected, or all detection categories are disabled.
`nonLabel_lib`	0–100	The image is highly similar to an exempted image in your custom library.

Table 9. Labels for the Image Moderation Service Based on LLMs (baselineCheckByVL)

Label	Confidence score	Description
politics	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain political content.
pornographic	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain pornographic content.
sexualHint	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain sexually suggestive content.
sexual	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain sexual content.
profanity	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain profane content.
terror	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain terrorist content.
ad	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain advertising.
contraband	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain contraband.
inappropriate	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain inappropriate content.

Table 8. Image Moderation for Large and Small Model Integration (postImageCheckByVL): Supported Labels

Label	Confidence score	Description
`pornographic_adultContent`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain adult pornographic content.
`pornographic_adultToys`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain adult toys.
`pornographic_artwork`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain pornographic artwork.
`pornographic_underage`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain child pornography.
`pornographic_adultContent_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text may contain pornographic content.
`sexual_suggestiveContent`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain vulgar or sexually suggestive content.
`sexual_breastBump`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain nipple outlines.
`sexual_cleavage`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain female cleavage.
`sexual_femaleUnderwear`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain underwear or swimwear.
`sexual_maleTopless`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain topless males.
`sexual_femaleShoulder`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain sexually suggestive content involving shoulders.
`sexual_femaleLeg`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain sexually suggestive content involving legs.
`sexual_pregnancy`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain maternity photos or breastfeeding.
`sexual_cartoon`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain sexually suggestive cartoon content.
`sexual_underage`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain sexually suggestive content involving minors.
`political_historicalNihility`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may relate to historical nihilism or sensitive historical events that are inappropriate for dissemination.
`political_historicalNihility_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text may relate to historical nihilism.
`political_politicalFigure_1`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain current or former political leaders.
`political_politicalFigure_2`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain family members of political leaders.
`political_politicalFigure_3`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain provincial or municipal government officials.
`political_politicalFigure_4`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain foreign leaders and their family members.
`political_politicalFigure_name_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text contains the names of political leaders.
`political_politicalFigure_metaphor_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text may contain aliases or metaphors for major political leaders.
`political_prohibitedPerson_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text may contain the names of disgraced officials.
`political_prohibitedPerson_1`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain disgraced national-level officials.
`political_prohibitedPerson_2`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain disgraced provincial- or municipal-level officials.
`political_taintedCelebrity`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain tainted public figures.
`political_taintedCelebrity_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text may contain the names of tainted public figures.
`political_Chinaflag`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain the national flag of China.
`political_otherflag`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain the national flags of other countries.
`political_Chinamap`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain a map of China.
`political_logo`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain logos of banned media outlets.
`political_outfit`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain military or police uniforms, or combat attire.
`political_medicalOutfit`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain medical attire.
`political_badge`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain national or party emblems.
`political_racism_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text may contain sensitive expressions. See the Content Moderation console for more information.
`violent_crowding`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain crowd gatherings.
`violent_explosion`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain content related to explosions or fireworks.
`violent_armedForces`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain terrorist organizations.
`violent_gun`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain guns.
`violent_Knives`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain knives.
`violent_gunKnives_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text describes guns or knives.
`violent_blood`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain bloody content.
`violent_horrific`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain horrific content.
`violent_horrific_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text may describe violent or horrific content.
`violent_burning`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain burning elements.
`contraband_illegal`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain contraband.
`contraband_drug`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain illegal drugs or controlled substances.
`contraband_drug_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text may describe illegal drugs.
`contraband_gamble`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain gambling-related items.
`contraband_gamble_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text may describe gambling activities.
`contraband_certificate_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text may contain advertisements for services such as certificate fabrication or facilitating cash-out schemes.
contraband	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain contraband.
`religion_funeral`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may depict funerals or memorial halls.
`religion_buddhism`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain specific attire or symbols. See the Content Moderation console for more information.
`religion_christianity`	A score from 0 to 100. Higher scores indicate a greater confidence level.
`religion_muslim`	A score from 0 to 100. Higher scores indicate a greater confidence level.
`religion_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.
`racism_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.
`PDA_kiss`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain kissing.
`PDA_physicalContact`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain intimate behavior.
`object_landmark`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain domestic landmarks.
`object_rmb`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain RMB banknotes or coins.
`object_foreignCurrency`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain foreign currency.
`object_wn`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain a specific character.
`object_carcrash`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain a car crash.
`object_candle`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain candles.
`object_flood`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain content related to natural disasters.
`object_pii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain personally identifiable information (PII).
`pt_logotoSocialNetwork`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image contains watermarks from social media platforms.
`pt_qrCode`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image contains a QR code.
`pt_programCode`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image contains a Mini Program code.
`pt_toDirectContact_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text may contain promotional information or spam. See the Content Moderation console for more information.
`pt_toSocialNetwork_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.
`pt_toShortVideos_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.
`pt_investment_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.
`pt_recruitment_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.
`inappropriate_smoking`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain smoking-related content.
`inappropriate_drinking`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain alcohol-related content.
`inappropriate_tattoo`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain tattoos.
`inappropriate_middleFinger`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain the middle finger gesture.
`inappropriate_foodWasting`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain content related to food waste.
`logo_brand`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain trademarks.
`logo_tv`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain TV station logos.
`logo_streaming`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain logos from the media and entertainment industry.
`profanity_oral_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text contains vulgar slang or profanity.
`profanity_offensive_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The text contains severely abusive language.
`meme_vulgar`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain vulgar memes.
`meme_metaphor`	A score from 0 to 100. Higher scores indicate a greater confidence level.	The image may contain metaphorical memes.

Status codes

Requests are billed only for status code 200.

Code	Description
`200`	Request succeeded.
`400`	A required parameter is empty.
`401`	A parameter value is invalid.
`402`	A parameter exceeds the maximum length. Correct and retry.
`403`	QPS limit exceeded. Reduce concurrency and retry.
`404`	Image download failed. Check the URL or retry.
`405`	Image download timed out. Verify accessibility and retry.
`406`	Image file too large. Resize and retry.
`407`	Unsupported image format. Use a supported format and retry.
`408`	Insufficient permissions. Verify service activation, no overdue payments, and RAM user has the required policy.
`500`	Internal system error. Retry later.

Billing

Image Moderation Enhanced Edition LLM image moderation service supports pay-as-you-go and resource plan deduction billing. Requests returning non-200 status codes are not charged.

Pay-as-you-go

After activating Image Moderation Enhanced Edition, the default billing method is pay-as-you-go. Fees are settled daily based on actual usage. You are not charged if you do not call the service.

Billing category	Included service	Unit price
Image Moderation LLM edition (image_vl_standard)	Image Moderation for Large and Small Model Integration: postImageCheckByVL Image Moderation for Large and Small Model Integration_For regions outside the Chinese mainland: postImageCheckByVL_cb Image Moderation Service Based on LLMs: baselineCheckByVL Large Model-Powered Ad Traffic Detection: adCheckByVL	CNY 45 per 10,000 calls Note Each call to any of the services listed on the left counts as one billing unit. Fees are based on actual usage. For example, 100 calls to the Image Moderation for Large and Small Model Integration service cost CNY 0.45.

Note

Content Moderation Enhanced Edition pay-as-you-go billing is settled once per hour. In bill details, the moderationType field identifies the moderation type. View your bill details.

You can also purchase pay-as-you-go resource plans. Resource plans offer tiered discounts compared to the pay-as-you-go method and are suitable for users with predictable and high usage.

Resource plan deduction

For large-volume or consistent moderation needs, purchase a resource plan in advance. Larger plans offer greater discounts. You can purchase and use multiple plans at the same time. For more information, see Purchase a resource plan for Content Moderation Enhanced Edition.

This resource plan applies to Content Moderation Enhanced Edition. It cannot be shared with the resource plans for Content Moderation 1.0. The deduction ratios are as follows:

Type

Deduction ratio

Image Moderation LLM edition (image_vl_standard)

Deduction ratio: 6. Each API call deducts 6 from your resource plan quota.

Example: a 10-call quota minus one API call leaves a balance of 4 calls.

Resource plan quota is applied before pay-as-you-go billing. When the quota is exhausted, usage is billed on a pay-as-you-go basis. Monitor your resource plan balance and pay-as-you-go bills. You can set up low-balance alerts in the Resource Plan system of the Alibaba Cloud User Center.

LLM Image Moderation