Moderatecontent Image Moderation
Official vendor OpenAPI document · agent-readyAI/MLVisionapiKey1 EndpointsREST
For Agents
Classify whether an image contains nudity or adult content via a single GET request and receive an everyone/teen/adult rating with confidence scores.
Use for: I need to check whether an image URL contains nudity, Rate a user-uploaded photo for SFW content, Filter classified ad images before publishing, Score an avatar URL for adult content
Not supported: Does not handle video, audio, or text moderation, and does not perform face recognition or general object tagging - use for still-image NSFW rating only.
ModerateContent is a free image moderation service that classifies whether an image contains adult or suggestive material. The API exposes a single GET endpoint that accepts an image URL plus an API key and returns a rating label (everyone, teen, adult) along with a numeric confidence score and predicted nudity probabilities. It is designed for forums, classifieds, and user-generated content sites that need a quick safe-for-work check before publishing media.
Install Jentic One Beta
Connect the Image Moderation to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Image Moderation, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmoderatecontent.com%2Fmoderatecontent" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmoderatecontent.com%2Fmoderatecontent" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Image Moderation API.
Rate an image URL as everyone, teen, or adult based on visible nudity
Return numeric probabilities for adult versus safe-for-work content
Pre-screen classified-ad photos before they appear publicly
Filter user avatar uploads against an everyone-only policy
Score forum attachments to send borderline cases to human review
Use Cases
Patterns agents use Image Moderation API for, with concrete tasks.
★ Classified Ad Photo Screening
Online marketplaces and classified-ad sites screen seller-uploaded photos before they appear in listings. The single GET / endpoint with a key and image_url query parameter returns a rating string and numeric scores, letting moderation logic auto-approve safe images, queue borderline cases, and reject adult content. Integration is a single HTTP call, typically deployed in under a day.
For a list of classified ad image URLs, call ModerateContent and return only the URLs rated 'everyone'
Avatar and Profile Picture Filter
Apply a strict everyone-only policy to user avatars and profile pictures on family-friendly platforms. Hosting the image first then passing the public URL to the moderation API lets the platform reject any upload that returns an adult or teen rating before it is shown to other users. Suitable for kids' platforms and education products.
Upload the user's chosen avatar to a temporary CDN, call ModerateContent with the URL, and only persist the avatar if the rating is 'everyone'
Agent-Driven Bulk Image Review with Jentic
Run a Jentic-connected agent over a backlog of legacy user-uploaded images to retroactively flag content that violates current SFW policy. The agent searches Jentic for the moderation operation, loads the schema, and processes the queue, writing flagged image IDs to a review spreadsheet for human moderators.
Iterate over 10,000 historical avatar URLs, classify each via ModerateContent, and produce a CSV of those with an adult rating for review
Key Endpoints
1 endpoints — moderatecontent is a free image moderation service that classifies whether an image contains adult or suggestive material.
METHOD
PATH
DESCRIPTION
GET
/
Classify an image URL as everyone, teen, or adult with nudity scores
GET
/
Classify an image URL as everyone, teen, or adult with nudity scores
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Image Moderation API by hand means handling its API key auth and coding the single NSFW-rating GET with its image parameter yourself. Through Jentic you install once, import the Image Moderation API from the API Directory, store the key once, and your agent calls it.
Permission scoping
Image Moderation exposes a single rating operation whose image is passed as a request parameter rather than a URL path resource, so scope your agent by limiting it to that one operation. You leave out everything else so the agent rates still images for NSFW content and does nothing more.
Credential isolation
Your Image Moderation API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'rate an image for NSFW content', and Jentic returns the matching Image Moderation operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Image Moderation API through Jentic.
What authentication does the Image Moderation API use?
Although the OpenAPI security block is empty, the live API requires a free key parameter on every GET request to https://api.moderatecontent.com/moderate/. Sign up at moderatecontent.com to receive the key. Through Jentic, the key is stored encrypted in your Jentic One instance and is injected at execution time so the agent never handles it directly.
Can I rate an image without uploading it?
Yes. The single GET / endpoint accepts a publicly reachable image URL via the url query parameter, fetches it server-side, and returns a rating label plus numeric scores. There is no multipart upload - the image must already be hosted somewhere ModerateContent can reach.
What are the rate limits for the Image Moderation API?
The free tier is throttled to roughly one request per second per key with a daily volume cap that depends on the account; paid plans raise both limits. The OpenAPI spec does not declare exact numbers, so production agents should respect 429 responses and back off.
How do I screen an image through Jentic?
Run pip install jentic, then search Jentic for 'rate an image for adult content'. Jentic returns the GET / operation on api.moderatecontent.com with its query schema. Load the schema, pass the image url, and execute - Jentic resolves the API key from the vault.
Is the Image Moderation API free?
ModerateContent advertises a free tier suitable for low-volume use. Higher request rates and SLAs require a paid plan. The free tier is enough to prototype and ship a small classified-ad or forum moderation flow without payment.
Can I limit what my agent is allowed to do with the Image Moderation API?
Yes. Because you run Jentic One yourself, your own rules decide which operations and credentials the agent may use. The Image Moderation API exposes a single rating operation that takes an image URL as a request parameter, so you can restrict the agent to just that one call and leave everything else out. Your agent then only rates still images for NSFW content and does nothing more.
GET STARTED