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.

Prompt moderation evaluates a text prompt against your client’s keyword blocklist and a language-model prohibition check. A prompt the model judges prohibited is rejected, and the reason is returned on the completed job.

​
Input

Submit a multipart/form-data request with:
FieldTypeRequiredDescription
promptstringYesThe text prompt to moderate.
webhook_urlstringNoURL to receive the result on completion.
curl -X POST https://api.evershield.ai/api/v1/moderate/prompt \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "prompt=A sunset over the ocean"

​
Pipeline

Prompt moderation runs two sequential steps:
  1. Blocked keyword check. The text is scanned against the configured blocklist. A match ends the pipeline before any further processing.
  2. LLM prohibition check. A language model reviews the prompt for policy violations. If it judges the prompt prohibited, the job is rejected with is_prohibited: true and a short reason.

​
Output

{
  "job_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
  "type": "prompt",
  "status": "completed",
  "is_prohibited": true,
  "categories": {
    "custom": {}
  },
  "reason": "The prompt requests sexual content involving a minor.",
  "created_at": "2026-05-19T12:00:00.000Z",
  "completed_at": "2026-05-19T12:00:01.500Z"
}
When is_prohibited is true, reason explains why the prompt was prohibited. A prompt that passes returns is_prohibited: false with no reason. See decision logic for how the prohibition decision is determined.