For dating apps
Moderate what people post on a dating app
Profile photos, prompts and messages: one API call before anyone else sees them. You get accept, review or reject, with the category, the score and the threshold, so you can tell the user why.
2,000 free credits every month, up to 1,000 images. No card needed.
curl -X POST \
-H "Authorization: Bearer $OPENSHIELD_API_KEY" \
--data-binary @photo.jpg \
"https://api.openshield.dev/v1/image?ref=avatar_4821"{
"summary": {
"action": "reject",
"reject_reason": [
{ "id": "nudity", "score": 0.97, "threshold": 0.8 }
]
},
"scores": { "nudity": 0.97, "gore": 0.01 },
"ref": "avatar_4821"
}Your rules
Why the categories are separate
On many dating apps, swimwear or underwear in a photo is acceptable and full nudity is not, or the rule depends on the surface: a public profile or a private conversation. openshield scores nudity, suggestive content, underwear and swimwear as separate image categories. You set a review threshold and a reject threshold for each, in a workflow, so a public photo workflow can be stricter than a private-chat workflow.
What you check
Everything a profile can show
One API for photos, bios and messages, and one for new accounts, from the same account.
Profile photos and uploads
JPEG, PNG, WebP or GIF, up to 15 MB. Built-in categories include nudity, suggestive content, underwear, swimwear, gore, weapons, hate symbols, offensive gestures, self-harm and minor. Text written on an image and QR codes can be read and checked, for off-platform links and personal data. Add your own categories in words for a house rule the catalogue does not have, up to 20 custom categories per workflow: you do not train a model.
Bios, prompts and messages
Bios, profile prompts and chat messages go through the text API: sexual content, hate speech, personal data (email, phone), spam, scams, off-platform contact, and links to adult or unsafe sites. The same call checks a bio and a message.
New accounts
Fake or automated sign-ups are a fraud problem, not a photo problem. The fraud prevention API (beta) scores a sign-up or a login: allow, step up, hold or block, with the rules that fired. Pack rules start in shadow. Same account and prepaid balance.
Why it fits a dating app
A decision your code can act on
Accept, review or reject
Accept: show the photo or the text. Review: hold it for your team. Reject: refuse it, with a message you choose from the category id. openshield does not review profiles for you.
A workflow per surface
One workflow for public photos, another for chat, each with its own thresholds and a version history.
A key per service
Limit a key to the workflows that surface needs. Rotate it with a grace delay, so a deploy never has a gap.
A journal you can search
Each decision is kept with your profile, photo or message id (ref), the reasons, the scores and the workflow version: 7 days before a first top-up, 30 days after. The content is never kept.
Nothing stored, in the EU
Content is checked in memory and forgotten when the answer is sent, in the European Union. Fraud instances run in Germany, and their events are pseudonymized.
How it fits
Check before anyone else sees it
Your server calls the API with your own id, then shows, holds or refuses. For a new account, call POST /fraud/v1/decide before you open the profile (beta).
- 01
A user posts
A user uploads a photo or saves a bio. Your server gets it, as it does today.
- 02
Check it
Call POST /v1/image or POST /v1/text with the content and your own ref, the photo id for example. The answer carries the decision and the reasons.
- 03
Publish, hold or refuse
Act on summary.action. If the check fails or times out, hold the content: do not show what was never checked.
import { checkText, ModerationError } from "./moderation"
// A request the API refuses as it is: it will never be accepted.
const refused = [400, 413, 415]
export async function moderateComment(text: string, commentId: string) {
try {
const decision = await checkText(text, commentId)
if (decision.action === "accept") return "publish"
if (decision.action === "review") return "hold"
return "refuse"
} catch (error) {
const status = error instanceof ModerationError ? error.status : 0
if (refused.includes(status)) return "refuse"
// A timeout or any other failure: keep it hidden for now.
return "hold"
}
}Categories
What a check can find on a profile
These come from openmod's catalogue. A workflow picks the ones you care about and the thresholds for each.
Images
- Nudity
- Suggestive content
- Underwear
- Swimwear
- Gore
- Violence
- Weapon
- Hate symbol
- Offensive gesture
- Self-harm
- Minor
- QR code
- and your own
Texts
- Sexual content
- Hate speech
- Self-harm
- Child safety
- Email address
- Phone number
- Spam
- Scam
- Off-platform contact
- Adult site link
- Unsafe site link
In the docs
Read how it works
- Quickstart Your first check in five minutes, from an account to a key and one request.
- Best practices Server-side only, fail closed, and messages chosen by category id.
- Workflows Categories, thresholds, custom categories and versions.
- The journal and ref What the journal keeps, and how your own id finds a decision.
- Images Check an image with POST /v1/image, as bytes or as a public URL.
- Texts Check a text with POST /v1/text, for comments, messages, names and bios.
- Node.js and TypeScript A small module with timeouts and a decision that fails closed.
- Migrating from the OpenAI moderation API Call POST /v1/text or POST /v1/image, then map the decision and the category ids.
More
Other ways in
- For your SaaS Moderate posts, comments, avatars and uploads before they go live.
- For your AI agents Moderate what an agent reads and what it writes.
- For marketplaces Moderate listing photos, descriptions and seller sign-ups before they go live.
- Image moderation API Nudity, gore, weapons and more, with a score per category.
- Text moderation API Unsafe text, personal data, spam and scams, with the reasons.
- Fraud prevention API Sign-up farms, card testing and account takeover, with your own openfraud instance.
- SightEngine alternative The same workflow routes: a new base URL and a new key.
- Pricing Free use each month, then a prepaid balance, priced by what each check uses.
Questions
Before you start
- Can I allow swimwear but reject nudity?
- Yes. They are separate image categories. Set a high reject threshold for swimwear, or leave it off that workflow, and a stricter threshold for nudity. You change this in the workflow, and each save is a new version.
- What do I do with the review outcome?
- Hide the photo or the message from other users until someone on your team approves it. If you have no moderation queue, start with a flag on the row and a screen that lists the flagged rows. openshield does not review content for you.
- What if a check fails or times out?
- Hold the content until a retry succeeds or someone has looked at it. Showing what was never checked is the case a moderation API exists to prevent.
- Can I call the API from my front end?
- No. Keys are secret and belong on your servers, and the API refuses calls that carry a browser Origin header. Call it from your backend and give your front end the decision.
- Do you store photos or messages?
- No. Content is checked in memory and forgotten once the answer is sent. The journal keeps metadata only: the time, the decision, the reasons, the scores and your ref. Fraud events are the documented exception, kept pseudonymized: see Privacy and data in the docs.
- What does a check cost?
- Beta prices, in euros, excluding VAT, from a prepaid balance with no subscription: €0.002 for an image under a usual workflow (nudity and visual categories), €0.003 per started 1,000 characters of text checked with rules and AI, and €0.001 for a fraud decision. Every account gets 2,000 free credits each month (up to 1,000 images), shared by moderation checks and fraud calls. It does not carry over to the next month, and no card is needed. The full grid is on the pricing page.
Start with 2,000 free credits every month
No card needed. Create a key and send your first request in five minutes.
Prepaid, in euros, excluding VAT