| What it does | Typed clients that retry, wait and verify for you.
| AI moderation API that detects toxicity, hate, threats, sexual content, self-harm and spam in 26 languages
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| IT
|
|---|
| Pricing model | Not given
| Free trial
|
|---|
| Pricing | Not given
| Free during the beta: 120 messages per minute per API key, up to 10 active API keys, all categories and custom rules included, usage dashboard included. No credit card required. Paid plans with higher limits coming after beta.
|
|---|
| Key features | - Automatic retry with exponential backoff for 429 and 5xx errors
- Idempotency key handling to prevent duplicate prints on retry
- Job polling with jobs.wait() method
- Webhook signature verification
- Support for Node 18+, Deno, Bun and edge runtimes
- Synchronous and asynchronous Python client
- No external dependencies for JavaScript
- Python SDK uses only standard library
- TypeScript support with full type definitions
- Support for PDF/A, PDF/X and PDF/UA compliance
| - Reads conversation context up to 10 previous messages
- Custom rules written in plain language, up to 10 per request
- Block specific types of slurs separately: racial, xenophobic, antisemitic, homophobic, transphobic or ableist
- Spam and flood detection per user and channel
- Usage dashboard showing requests and flags
- No message storage - messages checked and discarded immediately
- Single HTTP call API with response in milliseconds
- Works with Discord, Twitch, Telegram, Minecraft, games, forums and websites
- Answers Perspective API requests for easy migration
|
|---|
| What makes it different | - Automatic retry handling with Idempotency-Key to ensure requests are processed exactly once
- No external dependencies, using only platform fetch and Web Crypto for JavaScript
- Complete typing support in TypeScript and documentation in Python
- Unified error type with detailed status, code, title, detail and request ID
| - Understands conversation context to distinguish jokes from attacks, unlike keyword filters
- Custom rules in plain language for each community's unique policies
- No messages stored - privacy by design with GDPR compliance
- Drop-in replacement for Perspective API which shuts down December 31, 2026
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | 4 ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 5 | 0 |
| Citation Flow (Majestic) | 13 | 0 |
| Referring domains (Majestic) | 0 | 0 |