Safety.
3 · CheckKeep harmful content out of your product, in both directions. Screen what users send in and what your models send out. The Safety Kit protects your users, your agents and your brand without your team building a moderation stack.
… APIs in this kitAPIs in the Safety
Loading…Which Safety API do you need?
The question you arrived with, and the API that answers it.
What is the Safety Kit?
The Safety Kit is content moderation for AI products. It screens text, images, video and links on the way in and on the way out.
It makes your product safe to open to real users, keeps agents away from harmful content, and gives your customers confidence that what they see has been checked.
How AI products use it
- Stop toxic messages before they reach your model or your users.
- Screen uploaded videos for explicit content.
- Check links in user content before an agent opens them.
Why not build it in-house?
Each capability in the Safety Kit looks simple to build. The hard part is keeping it accurate, available and up to date once your product depends on it.
- Toxicity and profanityLanguage evolves, slang changes and users find new ways around filters. Keeping detection accurate needs constant updates and review.
- Image and video moderationExplicit content detection needs trained vision models, GPU capacity and careful handling of the very content you are trying to block.
- Link safetyMalicious domains appear and disappear by the hour. Static blocklists are outdated almost as soon as they ship.
- AccountabilityWhen moderation fails, the impact lands on your users and your brand. Proving content is screened becomes your responsibility to evidence.
Do you run an API that belongs in the Safety Kit?
Publish it on ApyHub and put it in front of the teams and AI agents building with the Safety Kit. Your API joins the catalog under one subscription, becomes callable through MCP, and earns from every call.
Questions about the Safety Kit
What is the ApyHub Safety Kit?
The Safety Kit is content moderation for AI products. It screens text, images, video and links on the way in and on the way out.
What is a content moderation API?
A content moderation API checks text, images or video for harmful content such as toxicity, profanity or explicit material, and returns a label or score your product can act on.
How do I keep an AI chatbot from showing toxic content?
Screen both sides of the conversation. Check user messages before they reach your model, and check model responses before they reach the user, with Detect Text Toxicity, CheckText Profanity or AI Text Moderation.
Can the Safety Kit moderate images and video?
Yes. Classify NSFW Image and AI Image Explicit Content Detection screen images, and AI Video Explicit Content Detection screens video uploads.
Why check links before an agent opens them?
Links in user content or web results can lead to malicious pages. Checking them first keeps your agents and users away from unsafe destinations.
Can I test Safety Kit APIs before integrating them?
Yes. Every API has a Try it panel on its service page. Your key is filled in, you send a real request and see the actual response in your browser before you write any code.
Can AI agents use the Safety Kit?
Yes. Every endpoint is MCP-ready. Connect ApyHub MCP to Claude, ChatGPT, Cursor, Mistral Le Chat or any MCP-compatible agent, and your agent can discover and call these APIs directly.
How is it priced?
Every kit sits under one subscription, paid in atoms, ApyHub's usage unit. Every call shows its cost, and the free Starter plan needs no card.