Text Safety Infrastructure
AI Moderations
Text Moderation
AI Moderations uses natural language understanding and deep learning to detect risky text, including homophones, obfuscated writing, character splitting, lookalikes, and indirect references across political, sexual, illegal, abusive, and other common risk categories.
Suitable for community moderation, comment and direct-message review, customer-support conversations, live comment streams, LLM-generated content safety, and cross-region products that need one unified moderation schema for Chinese and English.
Read the text moderation product overview
Open the text moderation API documentation
Learn about private deployment and cooperation
- Public-cloud pricing is listed at about one-fifth of comparable competitors
- Supports both public-cloud API and private deployment
- Supports moderation for both Chinese and English text
- Fine-grained labels, scores, and policy orchestration in one flow
Live moderation plane
Text safety signal stream
2.0
RMB / 10k requests
Pricing is benchmarked against comparable text moderation services while keeping the usage threshold lower, so teams can validate first and scale later.
Coverage includes
Results include top-level risk type, public label code, score, and summary buckets so they can be applied directly to policy actions.
The website, user center, and API share the same result schema, making it easy to move from trial to production integration.
Capability Map
Covers common text risks while leaving room for policy orchestration
The service returns more than a binary hit signal. It also exposes public labels, scores, and business hints so product, operations, and risk teams can act directly on the result.
Sexual Content
Detects explicit sexual content, suggestive flirting, solicitation, minor-related sexual risk, and adult content distribution.
Suitable for communities, chat, comments, fiction, UGC, and LLM-generated text moderation.
Illegal Content
Covers gambling, drugs, fraud, underground trade, privacy abuse, and circumvention-related violations.
Suitable for content platforms, ecommerce, tools, AI apps, and enterprise compliance workflows.
Political Sensitivity
Detects sensitive expressions related to public institutions, political figures, regional conflict, historical controversy, and ideology.
Suitable for LLM output review, pre-publication moderation, and manual review routing.
Abuse & Hate
Detects personal attacks, discriminatory insults, hate speech, and hostile expressions.
Suitable for comment moderation, customer support chats, communities, and live interactions.
Spam & Promotion
Detects off-platform diversion, contact info drops, ecommerce promotion, financial marketing, and recruitment spam.
Suitable for anti-spam and anti-diversion controls across communities, social platforms, and brand sites.
Violence & Extremism
Detects violent harm, terrorism, self-harm risk, and weapons or dangerous goods related content.
Suitable for high-risk moderation, AI safety, and strict risk-control scenarios.
Integration Path
From trial and integration to production,you do not need to rebuild the whole workflow
The same platform covers website trial, API integration, quota management, admin operations, and private deployment evaluation, making it suitable for a smooth path from small-scale validation to production use.
Start with free credits
New users receive 1000 free credits to validate hit quality, label granularity, and business fit.
Integrate the API into the real workflow
Use the same moderation API in business services. The response fields are aligned with the website demo, making integration and debugging more direct.
Turn results into policy actions
Use top-level categories, label codes, and score thresholds to configure blocking, downgrading, manual review, or alerts.
Move to private deployment when needed
If the business later requires stronger data isolation or internal-network deployment, the project can move into private delivery without rebuilding from scratch.
Price Benchmark
Price is not the only selling point, but the entry barrier must stay low
Public-cloud pricing is shown against comparable competitors so teams can estimate costs quickly during evaluation and still leave room for scale-up.
| Tier | Reference competitor price | Our displayed price |
|---|---|---|
| Pay-as-you-go | 25 RMB / 10k | 5.0 RMB / 10k |
| 1.8M package | 22 RMB / 10k | 4.4 RMB / 10k |
| 7.2M package | 19 RMB / 10k | 3.8 RMB / 10k |
| 36M package | 18 RMB / 10k | 3.6 RMB / 10k |
| 180M package | 13 RMB / 10k | 2.6 RMB / 10k |
| 360M package | 10 RMB / 10k | 2.0 RMB / 10k |
Multiple policy templates
Supports allow, block, downgrade, review, and alert templates for different moderation goals and business scenarios.
Manual policy configuration
Policies can also be configured manually by top-level category, public label code, threshold, and traffic source.
Get Started
Validate with free credits before deciding to scale.
The website demo helps teams quickly inspect labels and scores, while the API docs support direct integration. New users receive 1000 credits, and approved company verification grants another 50000 free credits.
Contact
[email protected]
FAQ
The most common customer questions are about getting live faster
What integration modes are supported?
Both public-cloud API integration and private deployment on enterprise servers or internal networks are supported.
How is pricing calculated?
Public-cloud pricing follows traffic tiers, and the exact quota deduction rules are visible in the signed-in user center.
What benefits come with company verification?
New users receive 1,000 free credits, and uploading a staff badge for admin approval unlocks another 50,000 credits.