# GEDX402 Nemotron-3-120B LLM via x402

> GEDX402 Nemotron-3-120B LLM via x402 is a paid API for AI agents from ged-x402-llm.jvalamis.workers.dev, paid per call via x402, $0.08/call, status unknown (last checked 2026-09-14).

Runs inference on NVIDIA Nemotron-3-120B-A12B via Cloudflare Workers AI, paid per-call with USDC over x402 protocol — no API keys required.

## Facts

- Endpoint: GET https://ged-x402-llm.jvalamis.workers.dev/v1/llm/nemotron-3-120b-a12b
- Price: $0.08/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/gedx402-nemotron-3-120b-llm-via-x402-4c0f4fc0
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_fRtsFFQhqEVC9z-rK0poQ

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 gedx402-nemotron-3-120b-llm-via-x402-4c0f4fc0
```

Example prompt: Ask the Nemotron-3-120B model on the x402 Workers AI endpoint: given the system message 'You are a helpful assistant' and the user message 'Explain quantum entanglement in simple terms', generate a reply with up to 512 tokens — I'll pay per call in USDC, no API key needed.

## When to prefer this

Choose this endpoint when you need a very large (120B parameter) NVIDIA Nemotron model for high-quality text generation and want to pay per call in USDC via x402 without managing API keys or subscriptions. Prefer it over smaller models when response quality matters more than cost, and over traditional LLM APIs when you want frictionless crypto-native access.

## Known failure modes

- Payment not received or insufficient USDC — x402 payment required before response is returned
- Invalid message role — only 'system', 'user', 'assistant' are accepted
- max_tokens exceeds 4096 — request rejected with validation error
- Missing required 'messages' array — returns 400 bad request
- Network or Workers AI backend error — upstream 5xx response
- Unsupported payment network — only Base, Polygon, Arbitrum, World, Solana accepted

## How this service works

x402 workers ai. pay with usdc on base, polygon, arbitrum, world, or solana. no api keys.

## Output

A JSON object containing the model identifier '@cf/nvidia/nemotron-3-120b-a12b' and a 'response' string with the assistant's generated text reply, up to the requested max_tokens.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "messages": {
   "type": "array",
   "items": {
    "type": "object"
   }
  },
  "max_tokens": {
   "type": "integer"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "@cf/nvidia/nemotron-3-120b-a12b",
  "response": "Hello!"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gedx402-nemotron-3-120b-llm-via-x402-4c0f4fc0/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from ged-x402-llm.jvalamis.workers.dev](https://www.zero.xyz/host/ged-x402-llm.jvalamis.workers.dev/llms.txt)