Skip to main content

Documentation Index

Fetch the complete documentation index at: https://doc.hitopen.com/llms.txt

Use this file to discover all available pages before exploring further.

The moderations endpoint classifies text against a set of content policy categories and returns a flag indicating whether the content violates policy, along with per-category scores. Use it to screen user-generated content before passing it to a model or storing it.

​
Endpoint

POST https://YOUR_NEWAPI_BASE_URL/v1/moderations

​
Request parameters

​
input
string | string[]
required
The text to classify. You can pass a single string or an array of strings to check multiple inputs in one request.
​
model
string
The moderation model to use. When omitted, the latest stable moderation model is used automatically. Common values include text-moderation-stable and text-moderation-latest.

​
Response fields

​
id
string
Unique identifier for the moderation request.
​
model
string
The moderation model that processed the request.
​
results
object[]
One result object per input string, in the same order as the input array.

​
Examples

curl -X POST "https://YOUR_NEWAPI_BASE_URL/v1/moderations" \
  -H "Authorization: Bearer sk-your-token" \
  -H "Content-Type: application/json" \
  -d '{
    "input": "I want to harm someone."
  }'

​
Checking multiple inputs

Python (batch)
from openai import OpenAI

client = OpenAI(
    api_key="sk-your-token",
    base_url="https://YOUR_NEWAPI_BASE_URL/v1",
)

inputs = [
    "I love sunny days at the park.",
    "How do I make explosives?",
    "Can you help me write a cover letter?",
]

response = client.moderations.create(input=inputs)

for i, result in enumerate(response.results):
    status = "FLAGGED" if result.flagged else "OK"
    print(f"[{status}] Input {i}: {inputs[i][:50]}")

​
Example response

{
  "id": "modr-abc123",
  "model": "text-moderation-stable",
  "results": [
    {
      "flagged": true,
      "categories": {
        "hate": false,
        "hate/threatening": false,
        "harassment": false,
        "self-harm": false,
        "sexual": false,
        "sexual/minors": false,
        "violence": true,
        "violence/graphic": false
      },
      "category_scores": {
        "hate": 0.0001,
        "hate/threatening": 0.0001,
        "harassment": 0.0023,
        "self-harm": 0.0012,
        "sexual": 0.0001,
        "sexual/minors": 0.0001,
        "violence": 0.9871,
        "violence/graphic": 0.0056
      }
    }
  ]
}