# NVIDIA Nemotron-3 Content Safety API (x402)

> NVIDIA Nemotron-3 Content Safety API (x402) is a paid API for AI agents from x402-nvidia.vercel.app, paid per call via x402, $0.188236/call, status unknown (last checked 2026-09-14).

Runs text content through NVIDIA's Nemotron-3 content safety model to classify and flag unsafe or policy-violating content, paid via x402 micropayments.

## Facts

- Endpoint: POST https://x402-nvidia.vercel.app/api/nemotron-3-content-safety
- Price: $0.188236/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/nvidia-nemotron-3-content-safety-api-x402-5f212a12
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_JHSA1js6wjEp0XcAg_QWT

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability nvidia-nemotron-3-content-safety-api-x402-5f212a12 -d '<json body>'
```

Example prompt: Use the NVIDIA Nemotron-3 content safety model to check whether this user comment is safe to post: 'You're an absolute idiot and I hope something terrible happens to you.' Tell me if it's flagged and why.

## When to prefer this

Choose this endpoint when you need NVIDIA's specialized Nemotron-3 content safety model specifically, accessible without an NVIDIA API key via per-call x402 micropayments. Ideal for agents that need on-demand content moderation without subscription commitments, or when integrating content safety into automated workflows that already use x402 payment rails.

## Known failure modes

- Payment failure if x402 USDC micropayment is not provided or insufficient (402 error)
- Malformed request body missing required content field returns 400
- Model timeout or NVIDIA NIM backend unavailability returns 503
- Rate limiting if too many requests in short succession

## How this service works

Access 48+ NVIDIA NIM AI models via x402 micropayments. Chat completions, vision, safety, translation, and more.

## Output

Returns a choices array containing the model's safety assessment of the input text, including classification of whether the content is safe or unsafe and any relevant violation categories detected.

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "example": {
  "choices": [
   {
    "message": {
     "role": "assistant",
     "content": "Hello!"
    }
   }
  ]
 },
 "properties": {
  "choices": {
   "type": "array",
   "description": "Model responses"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/nvidia-nemotron-3-content-safety-api-x402-5f212a12/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-nvidia.vercel.app](https://www.zero.xyz/host/x402-nvidia.vercel.app/llms.txt)