Perspective API

Moderation API is the content moderation platform built on our own frontier models. Instead of wrapping a general-purpose LLM, we train purpose-built trust & safety models on a large proprietary dataset of real-world harmful content. They detect toxicity, harassment, hate, sexual content, spam, scams, phishing, malicious URLs and personal data across text and images, and catch the obfuscation bad actors use to evade filters. Train custom models on your own policy in Model studio, or deploy AI agents that enforce your guidelines with full conversation context. Every decision returns a clear allow, review or reject recommendation. Built-in review queues and a moderation dashboard let your team handle edge cases, act on bad actors and improve accuracy with every decision. Dry-run mode lets you test on live traffic before blocking anything. Go live in an afternoon with SDKs, a REST API or no-code integrations. GDPR and CCPA compliant. Start free, no credit card.

Bodyguard protects your online communities and platforms against toxic content, cyberharassment and hate speech. Leverage the power of positive interactions, shield your communities from the negative ones. Different toxic content categories and severity levels. Contextual analysis. Internet language “decoding”. From a few blog comments, to thousands of social media comments, all the way up to live streaming. Powerful data bank to inform content decisions and uncover new ways to engage with your followers. Choose what toxic content categories you want to moderate. Safe platforms are 3x more likely to retain users and to attract new users towards the community. A lack of toxic content means visitors will spend around 60% more time on your platforms. Protect your brand image, users and employees. Don’t attach your business or brand to toxic content. Smooth, quick integration via API. Works with any platform. Pricing based on your needs.