AI Rate Card

Nemotron 3.5 Content Safety (free) · aihubmix

Developed by NVIDIA, Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model fine-tuned from Google Gemma-3-4B. Supporting an expansive context length of 128,000 tokens, this model moderates both user inputs and generated responses for LLMs and VLMs. It provides robust safety filtering to ensure aligned and secure interactions across multiple modalities.

Base modelAll models on this baseAll models of the providerto the provider

All NVIDIA models at every provider

Input, $/1M Free

Output, $/1M Free

Limits not published by the provider - free does not mean unlimited

Context 131 072

Max output 8 192

Accepts images, text

Last checked 04.11.2026 12:00:14 UTC

Source provider's page

Price alerts

Sign in to follow the price

API

OpenAI-compatible API: the official OpenAI SDKs work with this base URL. Replace YOUR_API_KEY with your key from the provider.

API base URL
https://aihubmix.com/api/v1
Endpoint
https://aihubmix.com/api/v1/moderations
Model id
nemotron-3.5-content-safety-free
curl
curl https://aihubmix.com/api/v1/moderations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "nemotron-3.5-content-safety-free", "input": "text to check"}'
Python
import requests

r = requests.post(
    "https://aihubmix.com/api/v1/moderations",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
      "model": "nemotron-3.5-content-safety-free",
      "input": "text to check"
    },
)
print(r.json())
JavaScript
const r = await fetch("https://aihubmix.com/api/v1/moderations", {
  method: "POST",
  headers: {Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
  body: JSON.stringify({
    "model": "nemotron-3.5-content-safety-free",
    "input": "text to check"
  }),
});
console.log(await r.json());
Request (JSON)
{
  "model": "nemotron-3.5-content-safety-free",
  "input": "text to check"
}
Response (JSON)
{
  "id": "modr-...",
  "model": "nemotron-3.5-content-safety-free",
  "results": [
    {
      "flagged": false,
      "categories": {
        "harassment": false,
        "violence": false
      },
      "category_scores": {
        "harassment": 0.0001,
        "violence": 0.0002
      }
    }
  ]
}

The address is taken from the provider's model list; check it against the provider's documentation.

Provider's API documentation

Source: AI Rate Card, https://airatecard.com/en/c/offer%3Aaihubmix%7Cnemotron-3.5-content-safety-free, prices checked 2026-11-04; seller's page: https://aihubmix.com

Technical details

ID: offer:aihubmix|nemotron-3.5-content-safety-free