Molmo2 Text Content Moderator API Documentation

Molmo2 Text Content Moderator API Documentation

Playground

Molmo2-4B Text Content Moderator: Analyze text content for safety, appropriateness, and policy compliance. Detects hate speech, violence, sexual content, and other harmful categories. Open-source vision-language model. Ready-to-use REST API, no cold starts, affordable pricing.

Features

Automatically screen text for harmful content with Molmo2 Text Content Moderator. This AI-powered moderation tool analyzes text and returns safety classifications for harassment, hate speech, sexual content, and violence — essential for chat platforms, user-generated content, and compliance workflows.

Related Models

• Molmo2 Image Content Moderator — Screen images for harmful content.
• Molmo2 Video Content Moderator — Screen videos for harmful content.

Why It Works Great

• Comprehensive detection: Screens for harassment, hate, sexual content, and violence.
• Child safety: Dedicated detection for content involving minors.
• Instant results: Near-instant processing for real-time moderation.
• JSON output: Clean, structured results for easy integration.
• Ultra-affordable: Just $0.003 per request — 333 requests for $1.
• Simple integration: Single text input for straightforward API calls.

Parameters

How to Use

1. Enter your text — paste or type the content to analyze.
2. Run — click the button to analyze.
3. Review results — check the JSON output for safety classifications.

Pricing

Flat rate per text analyzed.

Output Format

The model returns a JSON object with boolean flags for each content category:

{
 "harassment": false,
 "hate": false,
 "sexual": false,
 "sexual/minors": false,
 "violence": false
}

Detection Categories

Best Use Cases

• Chat Platforms — Moderate messages in real-time.
• Comments & Reviews — Screen user comments before publishing.
• Forums & Communities — Ensure posts meet community guidelines.
• Social Media — Filter text content at scale.
• Customer Support — Flag abusive messages automatically.
• Content Pipelines — Pre-screen text before human review.

Pro Tips for Best Results

• Use as a first-pass filter before human moderation for edge cases.
• Integrate via API for real-time chat moderation.
• At $0.003 per request, high-volume moderation is extremely cost-effective.
• Combine with image and video moderation for comprehensive screening.
• Process messages as they arrive for instant feedback.

Notes

• Processing is near-instant for real-time applications.
• Returns boolean values — true indicates detected content.
• Designed for automated workflows with JSON output.
• Consider human review for flagged content or edge cases.
• Works with any language text input.

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/molmo2/text-content-moderator" \
  -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