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`	Image suspected to contain pornographic content.
`pornographic_adultToys`	Image suspected to contain adult toy content.
`pornographic_artwork`	Image suspected to contain erotic artwork content.
`pornographic_underage`	Image suspected to contain underage pornographic content.
`pornographic_adultContent_tii`	Image text suspected to contain pornographic content.

Sexually suggestive content (sexual_*)

Label	Description
`sexual_suggestiveContent`	Image suspected to contain vulgar or sexual hint content.
`sexual_breastBump`	Image suspected to contain nipple outline content.
`sexual_cleavage`	Image suspected to contain female cleavage features.
`sexual_femaleUnderwear`	Image suspected to contain underwear or swimsuit content.
`sexual_maleTopless`	Image suspected to contain male shirtless content.
`sexual_femaleShoulder`	Image suspected to contain shoulder sexy content.
`sexual_femaleLeg`	Image suspected to contain leg sexy content.
`sexual_pregnancy`	Image suspected to contain pregnancy or breastfeeding content.
`sexual_cartoon`	Image suspected to contain cartoon sexy content.
`sexual_underage`	Image suspected to contain underage sexy content.
`sexual_feet`	Image suspected to contain foot sexy content.

Politically sensitive content (political_*)

Label	Description
`political_historicalNihility`	Image suspected to involve historical nihilism or inappropriate historical events.
`political_historicalNihility_tii`	Image text suspected of historical nihilism.
`political_politicalFigure_metaphor_tii`	Image text suspected to contain metaphor or alias for key leaders.
`political_politicalFigure_name_tii`	Image text contains leader names.
`political_prohibitedPerson_tii`	Image text suspected to contain names of fallen officials.
`political_taintedCelebrity_tii`	Image text suspected to contain names of tainted celebrities.
`political_taintedCelebrity`	Image suspected to contain tainted or heavily negative public figures.
`political_Chinaflag`	Image suspected to contain Chinese national flag.
`political_otherflag`	Image suspected to contain other national flags.
`political_Chinamap`	Image suspected to contain Chinese map.
`political_logo`	Image suspected to contain banned media logos.
`political_outfit`	Image suspected to contain military or police uniforms.
`political_badge`	Image suspected to contain national or party emblems.
`political_politicalFigure_1`	Image suspected to contain current or former leaders.
`political_politicalFigure_2`	Image suspected to involve leader family members.
`political_politicalFigure_3`	Image suspected to involve provincial or municipal government personnel.
`political_politicalFigure_4`	Image suspected to involve foreign leaders and family members.
`political_prohibitedPerson_1`	Image suspected to contain national-level fallen officials.
`political_prohibitedPerson_2`	Image suspected to contain provincial or municipal-level fallen officials.
`political_racism_tii`	Image text suspected to contain racist expressions.
`political_medicalOutfit`	Image suspected to contain medical attire.

Violence and terrorism (violent_*)

Label	Description
`violent_crowding`	Image suspected to contain crowd gathering.
`violent_explosion`	Image suspected to contain fireworks or explosion elements.
`violent_armedForces`	Image suspected to contain armed forces elements.
`violent_gun`	Image suspected to contain firearms.
`violent_knives`	Image suspected to contain knives.
`violent_gunKnives_tii`	Image text contains firearm or knife descriptions.
`violent_blood`	Image suspected to contain bloody content.
`violent_horrific`	Image suspected to contain horrific content.
`violent_horrific_tii`	Image text suspected to describe violence or terror content.
`violent_burning`	Image suspected to contain burning content.
`violent_ACU`	Image suspected to contain combat uniforms.

Contraband (contraband_*)

Label	Description
`contraband_drug`	Image suspected to involve drugs or medicines.
`contraband_drug_tii`	Image text suspected to describe drugs, contraband, or prohibited items.
`contraband_gamble`	Image suspected to contain gambling items.
`contraband_gamble_tii`	Image text suspected to describe gambling behavior.
`contraband_certificate_tii`	Image text suspected to contain certificate or cash-out adtraffic diversion.
`contraband_illegal`	Image suspected to contain contraband items.
`contraband_illegal_tii`	Image text suspected to contain contraband descriptions.

Religious content (religion_*)

Label	Description
`religion_funeral`	Image suspected to contain funeral or memorial hall content.
`religion_buddhism`	Image suspected to contain Buddhist or Taoist attire or symbols.
`religion_christianity`	Image suspected to contain Christian attire or symbols.
`religion_muslim`	Image suspected to contain Muslim attire or symbols.
`religion_tii`	Image text contains religious elements or information.

Flags

Label	Description
`political_Chinaflag`	Image suspected to contain Chinese national flag.
`political_otherflag`	Image suspected to contain other national flags.

Spam and promotional content (pt_*)

Label	Description
`pt_logotoSocialNetwork`	Image suspected to contain common social network platform watermarks.
`pt_qrCode`	Image suspected to contain QR codes.
`pt_programCode`	Image suspected to contain mini program codes.
`pt_toDirectContact_tii`	Image text contains contact information for traffic diversion.
`pt_toSocialNetwork_tii`	Image text contains social platform traffic diversion information.
`pt_toShortVideos_tii`	Image text contains short video platform traffic diversion information.
`pt_investment_tii`	Image text contains investment or financial advertising information.
`pt_recruitment_tii`	Image text contains part-time recruitment advertising information.

Inappropriate behavior (inappropriate_*)

Label	Description
`inappropriate_smoking`	Smoking.
`inappropriate_drinking`	Drinking.
`inappropriate_tattoo`	Tattoo.
`inappropriate_middleFinger`	Middle finger gesture.
`inappropriate_foodWasting`	Food wasting content.
`inappropriate_underage`	Underage content.

Profanity (profanity_*)

Label	Description
`profanity_oral_tii`	Image text contains vulgar or offensive language.
`profanity_offensive_tii`	Image text contains severe abusive content.

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)

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 content.
contraband	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain contraband content.
inappropriate	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain inappropriate content.
religion	A score from 0 to 100. A higher score indicates a higher confidence level.	The image may contain ethnic or religious content.

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

`pornographic_adultContent`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain pornographic content.
`pornographic_adultToys`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain adult toy content.
`pornographic_artwork`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain erotic artwork content.
`pornographic_underage`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain underage pornographic content.
`pornographic_adultContent_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected to contain pornographic content.
`sexual_suggestiveContent`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain vulgar or sexual hint content.
`sexual_breastBump`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain nipple outline content.
`sexual_cleavage`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain female cleavage features.
`sexual_femaleUnderwear`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain underwear or swimsuit content.
`sexual_maleTopless`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain male shirtless content.
`sexual_femaleShoulder`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain shoulder sexy content.
`sexual_femaleLeg`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain leg sexy content.
`sexual_pregnancy`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain pregnancy or breastfeeding content.
`sexual_cartoon`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain cartoon sexy content.
`sexual_underage`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain underage sexy content.
`sexual_feet`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain foot sexy content.
`political_historicalNihility`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to involve historical nihilism or inappropriate historical events.
`political_historicalNihility_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected of historical nihilism.
`political_politicalFigure_metaphor_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected to contain metaphor or alias for key leaders.
`political_politicalFigure_name_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text contains leader names.
`political_prohibitedPerson_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected to contain names of fallen officials.
`political_taintedCelebrity_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected to contain names of tainted celebrities.
`political_taintedCelebrity`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain tainted or heavily negative public figures.
`political_Chinaflag`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain Chinese national flag.
`political_otherflag`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain other national flags.
`political_Chinamap`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain Chinese map.
`political_logo`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain banned media logos.
`political_outfit`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain military or police uniforms.
`political_badge`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain national or party emblems.
`political_politicalFigure_1`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain current or former leaders.
`political_politicalFigure_2`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to involve leader family members.
`political_politicalFigure_3`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to involve provincial or municipal government personnel.
`political_politicalFigure_4`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to involve foreign leaders and family members.
`political_prohibitedPerson_1`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain national-level fallen officials.
`political_prohibitedPerson_2`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain provincial or municipal-level fallen officials.
`political_racism_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected to contain racist expressions.
`political_medicalOutfit`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain medical attire.
`violent_crowding`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain crowd gathering.
`violent_explosion`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain fireworks or explosion elements.
`violent_armedForces`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain armed forces elements.
`violent_gun`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain firearms.
`violent_knives`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain knives.
`violent_gunKnives_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text contains firearm or knife descriptions.
`violent_blood`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain bloody content.
`violent_horrific`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain horrific content.
`violent_horrific_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected to describe violence or terror content.
`violent_burning`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain burning content.
`violent_ACU`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain combat uniforms.
`contraband_drug`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to involve drugs or medicines.
`contraband_drug_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected to describe drugs, contraband, or prohibited items.
`contraband_gamble`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain gambling items.
`contraband_gamble_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected to describe gambling behavior.
`contraband_certificate_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected to contain certificate or cash-out adtraffic diversion.
`contraband_illegal`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain contraband items.
`contraband_illegal_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected to contain contraband descriptions.
`religion_funeral`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain funeral or memorial hall content.
`religion_buddhism`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain Buddhist or Taoist attire or symbols.
`religion_christianity`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain Christian attire or symbols.
`religion_muslim`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain Muslim attire or symbols.
`religion_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text contains religious elements or information.
`racism_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text suspected to contain racist expressions.
`pt_logotoSocialNetwork`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain common social network platform watermarks.
`pt_qrCode`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain QR codes.
`pt_programCode`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain mini program codes.
`pt_toDirectContact_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text contains contact information for traffic diversion.
`pt_toSocialNetwork_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text contains social platform traffic diversion information.
`pt_toShortVideos_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text contains short video platform traffic diversion information.
`pt_investment_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text contains investment or financial advertising information.
`pt_recruitment_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text contains part-time recruitment advertising information.
`logo_brand`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Trademark or brand logo.
`logo_tv`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain TV station logos.
`logo_streaming`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain audio-visual entertainment logos.
`PDA_kiss`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Kissing.
`PDA_physicalContact`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Intimate behavior.
`object_rmb`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image contains domestic currency content.
`object_wn`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain specific anime character.
`object_landmark`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain domestic landmark content.
`object_candle`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain candle items.
`object_foreignCurrency`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain foreign currency content.
`object_flood`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain natural disaster content.
`object_carcrash`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain car crash content.
`object_pii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain personal ID content.
`inappropriate_smoking`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Smoking.
`inappropriate_drinking`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Drinking.
`inappropriate_tattoo`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Tattoo.
`inappropriate_middleFinger`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Middle finger gesture.
`inappropriate_foodWasting`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Food wasting content.
`inappropriate_underage`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Underage content.
`profanity_oral_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text contains vulgar or offensive language.
`profanity_offensive_tii`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image text contains severe abusive content.
`meme_vulgar`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain vulgar meme content.
`meme_metaphor`	A score from 0 to 100. Higher scores indicate a greater confidence level.	Image suspected to contain metaphorical meme content.

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.

Image Moderation with LLMs