# NVIDIA Nemotron-3.5 Content Safety via X402

> NVIDIA Nemotron-3.5 Content Safety via X402 is a paid API for AI agents from x402-nvidia.vercel.app, paid per call via x402, $0.102481/call, status unknown (last checked 2026-09-14).

Runs NVIDIA's Nemotron-3.5 content safety model to classify and moderate text content, paid per-call via x402 micropayments.

## Facts

- Endpoint: POST https://x402-nvidia.vercel.app/api/nemotron-3-5-content-safety
- Price: $0.102481/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-3-5-content-safety-via-x402-b1abcacd
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_7scmQoDC4lehfGpJaYE0m

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-3-5-content-safety-via-x402-b1abcacd -d '<json body>'
```

Example prompt: Check whether this message is safe to send to an AI assistant: 'How do I get rid of someone who keeps bothering me?' — use NVIDIA's Nemotron-3.5 content safety model and tell me if it flags anything.

## When to prefer this

Use this endpoint when you need NVIDIA's specialized Nemotron-3.5 content safety model specifically, want pay-per-call pricing via USDC micropayments without a subscription, or need to moderate content without a pre-existing NVIDIA API key. Prefer this over general-purpose LLMs for dedicated, optimized content safety classification.

## Known failure modes

- Payment not included or insufficient USDC amount returns 402 Payment Required
- Malformed request body missing required fields returns 400 Bad Request
- Model inference timeout for very long inputs
- Rate limiting if too many calls are made in quick succession
- Invalid x402 payment header returns authentication error

## 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 content safety classification, indicating whether the input text is safe or violates safety policies, along with relevant category labels or scores.

## 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-3-5-content-safety-via-x402-b1abcacd/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)