Roadmap
Where ModerateHQ is today and where it is headed. Treat this as a guide to our direction rather than a promise of dates. Priorities can shift as we learn from real usage.
Available now
Text moderation
POST text and get back approved, flagged, or blocked, with matched categories and a plain-language reason you can act on directly.
Steerable policies
Built-in community, strict, and gaming policies. Tune how readily borderline content is flagged for review instead of hard-blocked.
Dashboard and logs
Manage API keys, watch usage, review credit history, and search a full log of every decision and the reason behind it.
Fair-use rate limits
Per-account burst limits and a free trial daily cap, with clear 429 and 402 responses so your app can back off cleanly.
In progress
Prepaid credits
Buy credits and spend one per successful request. No seats, no monthly minimum, and you only pay for verdicts we actually return. The free trial is available today while we finish enabling purchases.
Batch moderation
Submit many items in a single call and receive results asynchronously, built for backfills and high-volume pipelines.
Signed webhooks
Register a URL once and receive signed callbacks when batch jobs finish, so you never have to poll for results.
Planned
Image moderation
Send an image URL and moderate it against the same policy model that powers text.
Audio moderation
Transcribe audio and moderate the transcript in one step.
Custom policies
Define your own guidelines and categories through the API, applied to your traffic immediately.
Reputation and human review
Per-user reputation signals and a built-in queue for reviewing flagged content without building your own tooling.
Official SDKs
Typed client libraries for languages like TypeScript and Python, so you can call the API without hand-writing HTTP requests.
Start moderating today
The text API, policies, and dashboard are live now. Try them on a free trial.