Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.omnifence.ai/llms.txt

Use this file to discover all available pages before exploring further.

Every moderation job evaluates content against four checks (one per moderation category plus the prompt prohibition check). You can disable any check that doesn’t fit your use case — disabled checks are skipped entirely, saving cost and latency. By default, all four checks are enabled.

​
Where to configure

Open the Moderation page in the customer dashboard. Each check appears as a tile with a toggle. Changes are saved immediately and apply to all subsequent jobs.

​
Available checks

CheckWhat it does
nsfwFlags images containing nudity, sexual content, or other adult material.
ai_adult_generalCatch-all VLM check for adult content not covered by the other categories.
underageFlags images that appear to depict minors.
textKeyword filtering and an LLM prohibition check on submitted text prompts.
When underage is enabled, jobs are rejected if the check fires. Account termination is not automatic — it is a manual admin action triggered separately. Disabling underage removes that rejection signal, so make sure you have an alternative CSAM-detection control in place before turning it off.

​
How disabled checks behave

  • Text disabled — keyword filtering and the LLM prohibition check are skipped for prompts, so a prompt is never rejected on text grounds.
  • A single VLM category disabled (e.g. nsfw) — the per-category VLM prompt is skipped at enqueue time and the category does not appear in the result. For video, the corresponding per-frame VLM prompt is skipped too.
  • Every VLM-backed category disabled (nsfw, ai_adult_general, underage all false) — the entire VLM job is skipped, and for videos, frame extraction is skipped.
  • Every applicable check disabled — the job completes immediately with is_prohibited: false and an empty categories object (only categories.custom is present, possibly empty). No children are enqueued; the webhook still fires.

​
API access

You can also read and update your toggles from the API.

​
Read current settings

curl https://api.evershield.ai/api/v1/me/moderation-config \
  -H "Authorization: Bearer $STARS_API_KEY"

{
  "enabled_categories": { "nsfw": false },
  "catalogue": {
    "nsfw": { "label": "NSFW", "description": "...", "icon": "..." },
    "...": "..."
  }
}
The enabled_categories object contains only the checks you’ve explicitly disabled — anything missing is enabled. The catalogue provides human-readable labels and descriptions for each check.

​
Update settings

curl -X PUT https://api.evershield.ai/api/v1/me/moderation-config \
  -H "Authorization: Bearer $STARS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "nsfw": false, "ai_adult_general": false }'
The body must be a JSON object. Allowed keys are the four check names listed above; values must be booleans. Sending an empty object {} resets every check back to its default (enabled).