LocalMod vs Sightengine

LocalMod is a free content moderation API for text and images that runs on Linux within a self-hosted setup. The project says it can run offline, keeping user data within the user's infrastructure. Text classifiers check for PII, toxicity, prompt injection, spam, and NSFW text; the PII classifier covers emails, phone numbers, Social Security numbers, and credit card numbers. Image moderation detects explicit or adult images. API endpoints support single and batch text analysis, PII redaction, and image analysis from a URL or uploaded file. The README documents Python use, running an API server, and Docker deployment, and includes an example Discord bot for real-time text and image moderation with auto-delete, timeouts, and logging. Offline operation requires downloading the models once and setting LOCALMOD_OFFLINE=1; the documented download is about 3.5 GB and includes the image model. The README recommends a GPU for production workloads and lists CPU and GPU latency estimates by classifier. LocalMod is MIT licensed.

Sightengine provides APIs to assess, filter, and moderate images, videos, and text. Its visual moderation checks categories including nudity, hate, violence, drugs, weapons, and self-harm. It also detects AI-generated images, videos, speech, and music, as well as deepfakes. Additional tools include OCR and QR moderation, image and video search, age estimation, liveness checks, and recapture detection. Image moderation thresholds and rules can be configured for different community policies. Developers can use API examples and SDKs for Curl, Python, PHP, and Node.js. Sightengine says it does not involve human moderators or share customer content with third parties. The Free plan costs nothing and has daily and monthly usage limits; it does not include video processing or live-stream support. Starter costs $29 a month for 10,000 operations, with additional operations at $0.002 each. Sightengine is cloud-deployed and lists API and web platforms.