# X402-NVIDIA Nemotron-3-Super-120B Chat Completions

> X402-NVIDIA Nemotron-3-Super-120B Chat Completions is a paid API for AI agents from x402-nvidia.vercel.app, paid per call via x402, $0.104101/call, status unknown (last checked 2026-09-13).

Runs inference on NVIDIA's Nemotron-3-Super-120B large language model via x402 micropayment-gated API, returning chat completion responses.

## Facts

- Endpoint: POST https://x402-nvidia.vercel.app/api/nemotron-3-super-120b
- Price: $0.104101/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/x402-nvidia-nemotron-3-super-120b-chat-completions-a44f604f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_u9q7wimjMG6Qjy9Kz-xd0

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 x402-nvidia-nemotron-3-super-120b-chat-completions-a44f604f -d '<json body>'
```

Example prompt: Ask NVIDIA's Nemotron-3-Super-120B model to write a detailed explanation of quantum entanglement in simple terms — pay per call with USDC.

## When to prefer this

Choose this endpoint when you need access to NVIDIA's Nemotron-3-Super-120B model specifically, want pay-per-call pricing via USDC micropayments without a subscription, or are building an agent workflow that requires a high-parameter LLM with no API key setup — ideal for low-volume or experimental use cases.

## Known failure modes

- Payment not included or invalid x402 payment header — returns 402 Payment Required
- Malformed input messages array — returns 400 Bad Request
- Model inference timeout for very long prompts
- Insufficient USDC balance for micropayment
- Service unavailable if NVIDIA NIM backend is down

## How this service works

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

## Output

A JSON object with a 'choices' array containing the model's assistant message, including role and content fields, representing the generated text completion from Nemotron-3-Super-120B.

## 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/x402-nvidia-nemotron-3-super-120b-chat-completions-a44f604f/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)