Content Moderator Image API Documentation

Content Moderator Image API Documentation

Playground

Image Content Moderator provides automated image moderation to detect and flag policy-violating or inappropriate images for automation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Ensure your images meet safety and compliance standards with WaveSpeed AI’s Content Moderator. This fast, affordable moderation tool analyzes images for policy violations, inappropriate content, and safety concerns — essential for platforms, applications, and workflows that handle user-generated content.

Why It Works Well

• Fast analysis: Quick moderation results for high-volume workflows.
• Comprehensive detection: Identifies various types of inappropriate or unsafe content.
• Text context support: Optionally include associated text for more accurate moderation decisions.
• Ultra-affordable: At just $0.001 per image, scale moderation without breaking the budget.
• Simple integration: Minimal parameters make it easy to add to any pipeline.

Parameters

How to Use

1. Upload your image — drag and drop or paste a public URL.
2. Add text context (optional) — include any associated text that should be considered.
3. Run — click the button to analyze.
4. Review results — check the moderation output for any flagged content.

Pricing

Flat rate per moderation request.

Best Use Cases

• User-Generated Content — Screen uploads before publishing to your platform.
• Social Media & Communities — Maintain safe spaces by filtering inappropriate images.
• E-commerce — Ensure product listings meet marketplace content policies.
• Content Pipelines — Add automated safety checks to media processing workflows.
• AI Output Screening — Verify generated images comply with safety guidelines before delivery.

Pro Tips for Best Results

• Include associated text when available — it helps provide context for more accurate moderation.
• Use in automated pipelines for consistent, scalable content screening.
• Combine with human review for edge cases or appeals.
• Set up batch processing for high-volume moderation needs.
• If using URLs, ensure they are publicly accessible for successful analysis.

Notes

• If using a URL for the image, ensure it is publicly accessible.
• Moderation results should be used as guidance — consider human review for borderline cases.
• Processing is typically very fast, suitable for real-time moderation workflows.
• The text field can provide valuable context for images with ambiguous content.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "text": "A clear example input"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/content-moderator/image" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters