CUSTOM POLICIES & ACTIONS
Set the Rules. Choose the Response.
Configure content moderation API checks around your community policies. Allow acceptable content, block violations or route uncertain cases for review. Connect results to group muting and member controls when your policy calls for further action.
MADE FOR YOUR USERS
Use Cases for content moderation API
Different conversations need different rules. Match detection and response to the risks your users face.
Communities
Keep Spam Out of the Conversation.
Check for abusive replies and promotional spam in group discussions. Combine AI results, custom word lists and member reports to help moderators keep conversations on topic.
Marketplaces
Catch Risky Messages Around a Sale.
Flag prohibited promotions and contact details split across messages. Keep the listing and conversation together when your team reviews suspected off-platform solicitation.
Gaming
Keep Competition from Turning into Abuse.
Apply community policies to player chat, shared images and voice messages. Use moderation results and player reports to guide group muting or further review.
Dating
Help Members Feel Safer Connecting.
Check messages and profile content for sexual material and abusive language. Put reporting and blocking within reach, with a review path for disputed decisions.
RELATED CUSTOMER STORY
Content Review in WeSing’s Community
CHOOSE WITH CONFIDENCE
Plan your content moderation API integration
See how messaging fits your product and what your application connects.
| Your requirement | How it is delivered | What to plan for |
|---|---|---|
| AI text, image, audio and video checks | Cloud moderation with content categories and review recommendations. | Text and image checks return synchronously; audio and video results arrive asynchronously. |
| Messages that try to evade filters | Contextual merge detection for text in direct and group chat. | Enable the setting for the relevant scenario; test split-message examples from your community. |
| Policies for different audiences | Risk categories, sensitivity settings, custom word libraries and scenario configurations. | Configure policies separately for messages, profiles and custom content. |
| Risk-based intervention | Pass, Review or Block recommendations; text/image risk scores; configurable interception and Chat member controls. | Your application connects review outcomes to escalation rules, warnings and account actions. |
| Moderator review and reporting | Console filtering plus webhooks carrying message references and violation labels. | Connect reports, appeals and decision history to your tools; measure false positives and review turnaround. |
| Availability and rollout | Enable Chat Content Understanding and select your moderation configuration. | Access currently requires allowlisting. The on-demand API currently supports Singapore-hosted apps; confirm model language coverage before launch. |
THREE STEPS TO YOUR FIRST CONVERSATION
Integrate content moderation API
Configure your content moderation API policy, connect the content checks, then test what users and moderators see.
BUDGET BEFORE YOU BUILD
Content moderation API Costs & Free Quota
Budget for your content moderation API integration. Plan for messaging users and the content you check. Chat plan allowances and moderation service charges are separate.
CHAT FREE PLAN
Free$0 · 1,000 MAU / month
Start with the free Chat plan. Monthly usage renews automatically; review feature limits and upgrade requirements as your audience grows.
CHAT STANDARD
$399 USD / month · 10,000 MAU
For core messaging and group chat. Compare plans for advanced features such as read receipts, translation and community capabilities.
YOUR APPLICATION
Contact us
Estimate text and image checks, audio and video processing, plus reviewer workload. Confirm moderation pricing and access alongside your Chat plan; Chat free quota does not imply free AI moderation.
SEE THE PRODUCT IN ACTION
Keep Safety Within the Conversation
What does a content moderation API do for chat?
AI content moderation analyzes messages and media for risks such as abuse, sexual content and unwanted advertising. Tencent RTC connects these checks with content labels and moderation recommendations. Combine model-based detection with custom word lists and contextual merge detection to identify violations that a simple keyword filter may miss.
Which message types can a content moderation API check?
Yes. Chat Content Understanding supports all four formats. Text and image checks return results synchronously; audio and video checks return results asynchronously through webhooks. Video policies can inspect frames, audio or both. For media in your own storage, connect violation callbacks to your app’s display and access controls.
Can I customize content moderation API rules and actions?
Yes. Configure risk categories, sensitivity and custom word libraries by scenario, including direct messages, group chat and profiles. Choose whether to intercept violating content or suspected content as well. Use results to drive your application’s escalation rules and connect Chat controls such as group muting. AI recommendations and account-level actions remain separate decisions.
How do content moderation API results connect to human review and analytics?
Use the moderation console to filter content, and send results to your backend with message, sender and violation details. Combine these with user reports in your review tools. Track confirmed violations, overturned decisions and review times to tune policies. Your application manages reviewer assignment, appeals and decision-history reporting.
How do I enable the content moderation API for an international app?
Request access to Chat Content Understanding, which currently requires allowlisting. The documented on-demand moderation API currently supports Singapore-hosted applications. Confirm supported languages and models for your audience, then test local slang, mixed-language messages and false positives. Moderation service charges are separate from your Chat messaging plan.
How do I connect a content moderation API to human review?
Route supported review results to your application’s policy workflow. Store the decision context, provide appeals where appropriate and define how moderators handle uncertain results.
Can a content moderation API stop every harmful chat message?
No automated review is perfect. Check supported text and media categories, tune your policy and pair review results with reporting, blocking and human escalation.