Thai Text Toxicity Classification

Reads Thai text and returns whether it is toxic, offensive or otherwise inappropriate, with a confidence score.

POST/v3/store/nlp/toxicity-classificationTry it

• Price1 ICper 400 characters
• Served43.6Kcalls

• v1.0
• Active

Input

text

พนันกับคาสิโนออนไลน์

OutputPOST /v3/store/nlp/toxicity-classification

label

toxic

score

0.7037630677223206

input_text

พนันกับคาสิโนออนไลน์

duration

0.02465963363647461

message

success

status_code

200

Every field, under Response

Request

curl -X POST "https://api.iapp.co.th/v3/store/nlp/toxicity-classification?text=พนันกับคาสิโนออนไลน์" \
  -H "apikey: YOUR_API_KEY"

Response

200OK. The fields are explained under Response.

{
    "label": "toxic",
    "score": 0.7037630677223206,
    "input_text": "พนันกับคาสิโนออนไลน์",
    "duration": 0.02465963363647461,
    "message": "success",
    "status_code": 200
}

Request

POST, the text in the query string. 1 IC per 400 characters.

Headers

apikeystringrequired

Your API key, created under API Keys in the control panel.

Query

textstringrequired

The text, in Thai.

The legacy path /toxic-classification/predict answers at the same price.

Response

labelstring

toxic or non_toxic

scorenumber

The confidence, 0 to 1

input_textdurationmessagestatus_code

Your text, seconds, success, 200

Details

Measured

Limits

• Thai text.
• One moderation signal, to use beside your other checks.

Data handling

Text is processed in memory and not kept after the response. The service is GDPR and PDPA compliant.