Product updates
We've shipped two huge upgrades to make Moderation API faster to set up, richer in signal, and easier to maintain - and next week we’re launching something new every day (Dec 8-12).
Revamped dashboard
Next time you sign in, the dashboard will feel very different. We rebuilt it to:
- Make it easier to configure moderation policies
- Improve the development experience
Key changes:
- Channels: A new abstraction for routing different content types (e.g., chat messages, reviews, listings, profiles). Policies are configured per channel, and you pass the channel key in API calls to apply the right rules.
- Content types: Better context-aware display and analysis. Messages show in conversation context; profiles render as structured objects so it’s clear which field triggered a flag.
- Projects: Everything (queues, channels, authors, keys, actions) is scoped to a project - ideal for separating environments or client work, while custom models/wordlists stay at the org level.
- Playground: Now a modal for quick iteration with visibility into recommendation fields and severity scores; toggle to raw JSON.
Read the full post: Revamped dashboard
Unified moderation API endpoint
We consolidated all moderation routes into a single endpoint with new evaluation and recommendation fields.
- Evaluation: Final result with a binary flagged plus a severity score for prioritization.
- Recommendation: Suggested action—reject, review, or allow—based on severity and author status, configurable per channel.
The new endpoint requires upgrading the SDK or switching API endpoint.
Read the full post: Unified moderation API endpoint

🚀 Launch Week: Dec 8–12
Next week, for five days straight, we’re releasing a new feature each day.
Follow along and show some love on our new X account: @ModerationHQ
Thanks for building with us,
The Moderation API Team