Moderation API for reports, review queues, and appeals

ChefSphere moderation APIs cover reports, review queues, appeals, and automated safety checks so public UGC is not moderated in a shared inbox nobody owns. Social feeds, live chat, and publishing comments attract abuse; pretending otherwise is how brands learn the hard way in app stores and press. This guide is about moderation workflows—not social post creation and not live session hosting—even though those modules generate the content you review.

Keeping moderation intent distinct helps you staff queues and set SLAs without confusing safety with engagement features. It also clarifies prepaid planning: moderation scans sit above cheap catalog reads on the token-weight table because automated checks and review tooling cost real money. One shared balance still funds safety beside commerce and community on packs starting at $29.

Reports need clear reasons, evidence references, and ownership so operators can act without tribal knowledge. Review queues need prioritization and status so high-risk content does not sit behind vanity spam forever. Appeals need a path users understand when content is removed, and automated checks should reduce volume without becoming an unexplainable black box your support team cannot defend.

Moderation scan weight is published so you can model UGC-heavy apps honestly instead of pretending every post is free to review. If your launch is public-by-default, budget scans alongside social writes and live chat rather than discovering burn after a viral week floods reports. Growth and Scale packs exist when moderation coincides with AI vision inputs or high-volume live sessions.

Pair moderation with social and live when public UGC is on by default, and pair with AI when prompts or images need safety posture before they reach other users. Pair with media when private assets or flagged uploads require controlled access during review. Early access onboarding is where we align which content types are in scope for version one.

Authenticate with an X-API-Key in the Firebase-style model and burn prepaid tokens per call on one ledger across nineteen modules. Unused tokens stay available when report volume dips between campaigns. Request access, describe your content types and audience rules, and we email when onboarding opens.

Illustrative OpenAPI samples help you plan report and queue flows without treating fictional paths as production contracts for enforcement actions. Production environments arrive with access so you integrate against the real moderation surface. Enterprise from $300 per month exists when dedicated limits or custom weights are required for high-volume safety workloads.

Define what gets auto-removed, what goes to human review, and how appeals work before marketing an unlimited community your staffing cannot support. Those product rules matter more than decorative trust badges and more than any sample snippet in illustrative docs. A moderation surface without policy becomes brand and regulatory risk faster than engagement metrics can justify.

Related guides on social feed, live streaming, and AI vision show how safety plugs into the surfaces that generate content. Request early access with expected UGC volume and whether minors are in scope for your launch markets. We contact you when keys and packs are available.