Moderations

Use the moderation API to identify policy risk in user input, uploaded images, or pre-generation workflows. The interface follows the OpenAI Moderations shape.

`POST /v1/moderations`

Classify text and image inputs for content risk. Returns a flagged boolean, categories, and confidence scores per input. Accepts one or more inputs per request.

Parameters

Parameter	Type	Required	Description
input	string \| array	Yes	Content to moderate. Can be plain strings, text objects {type:"text", text:"..."}, image URL objects {type:"image_url", image_url: {url:"..."}}, or base64 image objects {type:"input_image", input_image: {data:"..."}}. Arrays supported for batch.
model	string	No	sealink-moderation-001 (default)
user	string	No	End-user identifier for monitoring and abuse detection

Response Format

Field	Type	Description
id	string	Request ID
model	string	Model used
results	array	Array of result objects, one per input
results[].flagged	boolean	Whether content violates policy
results[].categories	object	Per-category violation flags (boolean)
results[].category_scores	object	Per-category confidence scores (0-1)

Moderation Categories

harassment

harassment/threatening

hate

hate/threatening

self-harm

self-harm/intent

self-harm/instructions

sexual

sexual/minors

violence

violence/graphic

illicit

illicit/violent

cURL — Single Text

# Single text input
curl https://test.sealink.io/v1/moderations \
  -H "Authorization: Bearer <your-sealink-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "I want to learn about AI safety.",
    "model": "sealink-moderation-001"
  }'

cURL — Batch

# Batch: array of strings or content objects
curl https://test.sealink.io/v1/moderations \
  -H "Authorization: Bearer <your-sealink-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "input": [
      "Hello, how can I help you today?",
      {"type": "text", "text": "Some content to check"},
      {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
    ],
    "model": "sealink-moderation-001"
  }'

cURL — Base64 Image

# Base64 image input
curl https://test.sealink.io/v1/moderations \
  -H "Authorization: Bearer <your-sealink-key>" \
  -H "Content-Type: application/json" \
  -d '{
    "input": [
      {"type": "input_image", "input_image": {"data": "iVBORw0KGgo..."}}
    ],
    "model": "sealink-moderation-001"
  }'

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://test.sealink.io/v1",
    api_key="<your-sealink-key>",
)

response = client.moderations.create(
    model="sealink-moderation-001",
    input="I want to learn about AI safety.",
)
print(response.results[0].flagged)
print(response.results[0].categories)
print(response.results[0].category_scores)

Python — Batch

from openai import OpenAI

client = OpenAI(
    base_url="https://test.sealink.io/v1",
    api_key="<your-sealink-key>",
)

response = client.moderations.create(
    model="sealink-moderation-001",
    input=[
        "Hello, how can I help you today?",
        {"type": "text", "text": "Some content to check"},
        {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}},
    ],
)
for r in response.results:
    print(r.flagged, dict(r.categories))

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://test.sealink.io/v1",
  apiKey: "<your-sealink-key>",
});

const response = await client.moderations.create({
  model: "sealink-moderation-001",
  input: "I want to learn about AI safety.",
});
console.log(response.results[0].flagged);
console.log(response.results[0].categories);
console.log(response.results[0].category_scores);

Node.js — Batch

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://test.sealink.io/v1",
  apiKey: "<your-sealink-key>",
});

const response = await client.moderations.create({
  model: "sealink-moderation-001",
  input: [
    "Hello, how can I help you today?",
    { type: "text", text: "Some content to check" },
    { type: "image_url", image_url: { url: "https://example.com/photo.jpg" } },
  ],
});
for (const r of response.results) {
  console.log(r.flagged, r.categories);
}

Pricing

The Moderations endpoint is suitable for real-time safety checks, user input filtering, and content compliance. Availability and billing rules are reflected in the dashboard and billing records.