GET /v1/content-safetyLLM content safety classifier
Agent Tools lf-agent-tools
Judges whether a piece of text is safe to hand to a model. Returns per-category scores and flags, a flagged boolean, a 0-1 risk_score, and an assessment of safe, sensitive, risky, or blocked.
Query Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | Text to classify |
Response Schema
categories (object): Per-category scores and flags
flagged (boolean): Any category flagged
risk_score (number): 0-1 risk score
assessment (string): safe, sensitive, risky, or blocked
cURL Example
curl 'https://lf-agent-tools.laminarforge.dev/v1/content-safety?text=<text>' -H 'Authorization: Bearer lf_YourApiKey'
Python Example
import requests
url = 'https://lf-agent-tools.laminarforge.dev/v1/content-safety'
headers = {'Authorization': 'Bearer lf_YourApiKey'}
params = {'text': '<text>'}
response = requests.get(url, headers=headers, params=params)
print(response.json())