# Gambit GPU Shop – Nemotron-3-Super 120B Chat (x402)

> Gambit GPU Shop – Nemotron-3-Super 120B Chat (x402) is a paid API for AI agents from spark-2f53.tail8a7863.ts.net, paid per call via x402, $0.08/call, status unknown (last checked 2026-09-14).

Send a chat message array to the Nemotron-3-Super 120B model hosted on Gambit's GPU shop and receive an assistant reply, billed at $0.08 USDC per call via x402 on Base.

## Facts

- Endpoint: POST https://spark-2f53.tail8a7863.ts.net/gambit/x402/chat/nemotron
- 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/gambit-gpu-shop-nemotron-3-super-120b-chat-x402-8be86f4b
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap__8hfFbdUxcMCNTwXuh_Dd

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 gambit-gpu-shop-nemotron-3-super-120b-chat-x402-8be86f4b -d '<json body>'
```

Example prompt: Use the Gambit Nemotron-3-Super 120B chat endpoint to answer this question: 'What are the key differences between transformer and mamba architectures?' — keep the reply under 512 tokens.

## When to prefer this

Choose this endpoint when you need access to a very large (120B parameter) NVIDIA Nemotron model via a pay-per-call USDC micropayment model on Base (x402 protocol), without a subscription. Prefer it over OpenAI or Anthropic APIs when you specifically want Nemotron-3-Super architecture, want to pay in stablecoin per request, or are building agents that need programmatic x402 payment flows. It is less suitable if you need streaming responses, function calling, or SLA guarantees from a major cloud provider.

## Known failure modes

- 402 Payment Required if x402 USDC payment on Base is not attached or insufficient
- Invalid messages array (missing role or content fields) causes a 400 error
- max_tokens value out of range may be rejected or silently capped
- Model overload or GPU unavailability may cause timeouts or 503 errors
- Malformed JSON body returns a parse error
- Network routing issues to Tailscale endpoint (ts.net) may cause connection failures

## How this service works

Gambit GPU shop. Pay with L402 Lightning on /l402/* or x402 USDC on Base on /x402/*. Handwritten letter POST /x402/letter at $25.00 USDC. Funnel https://spark-2f53.tail8a7863.ts.net/gambit. Cheap probe GET|POST /x402/models at $0.01 USDC.

## Output

A JSON object containing the model identifier ('nemotron-3-super:120b-a12b') and a message object with role 'assistant' and the generated text content as a string.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role",
     "content"
    ],
    "properties": {
     "role": {
      "type": "string"
     },
     "content": {
      "type": "string"
     }
    }
   }
  },
  "max_tokens": {
   "type": "integer",
   "default": 512
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "nemotron-3-super:120b-a12b",
  "message": {
   "role": "assistant",
   "content": "Hi."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/gambit-gpu-shop-nemotron-3-super-120b-chat-x402-8be86f4b/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from spark-2f53.tail8a7863.ts.net](https://www.zero.xyz/host/spark-2f53.tail8a7863.ts.net/llms.txt)