# Model Access Gateway – GPT-OSS-120B Chat Completions (x402)

> Model Access Gateway – GPT-OSS-120B Chat Completions (x402) is a paid API for AI agents from agent402-arb.rosariovitale0096.workers.dev, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-15).

Runs OpenAI-compatible chat completions using the GPT-OSS-120B model, billed per-request in USDC via x402 with no API key required.

## Facts

- Endpoint: POST https://agent402-arb.rosariovitale0096.workers.dev/llm/gpt-oss-120b?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/model-access-gateway-gpt-oss-120b-chat-completions-x402-0302c981
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_h9ciMO6DaMiLp_XRstTlv

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 model-access-gateway-gpt-oss-120b-chat-completions-x402-0302c981 -d '<json body>'
```

Example prompt: Send this conversation to GPT-OSS-120B and get a reply — the system prompt is 'You are a helpful assistant' and the user message is 'Explain quantum entanglement in two sentences.' Pay the per-call fee automatically in USDC.

## When to prefer this

Choose this endpoint when you need OpenAI-compatible chat completions without registering for an API key or pre-purchasing credits — ideal for autonomous agents that can pay per-call in USDC on Base via x402. Prefer it over standard OpenAI when you want crypto-native, account-free billing or when operating in a permissionless agent economy. It is specifically suited to the GPT-OSS-120B model; choose a sibling endpoint for other models in the gateway.

## Known failure modes

- Payment not included or insufficient USDC — HTTP 402 returned before inference runs
- Malformed request body missing required 'messages' field — returns 400 or model error
- Model overloaded or upstream provider unavailable — may return 503 or timeout
- Invalid x402 payment header or wrong network — payment rejected, no completion returned
- Rate limit hit on underlying model provider — upstream 429 propagated

## How this service works

OpenAI GPT OSS 120B API (openai/gpt-oss-120b): LLM inference via OpenAI-compatible chat completions, pay per call in USDC on Base with x402. No API key, no account. Suited for AI agents and scripts that need OpenAI GPT OSS 120B on demand. Streaming and function calling supported. Exact price in the 402 quote before payment; automatic refund if the model fails to answer.

## Output

Returns a standard OpenAI chat.completion JSON object containing the assistant's message content, role, finish_reason (e.g. 'stop'), model name, creation timestamp, and token usage breakdown (prompt_tokens, completion_tokens, total_tokens).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "type": "string",
   "description": "Optional: fixed by the route (openai/gpt-oss-120b)"
  },
  "tools": {
   "type": "array"
  },
  "stream": {
   "type": "boolean",
   "description": "true: server-sent events after payment"
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role"
    ],
    "properties": {
     "role": {
      "enum": [
       "system",
       "user",
       "assistant",
       "tool",
       "developer"
      ],
      "type": "string"
     },
     "content": {
      "type": [
       "string",
       "array",
       "null"
      ]
     }
    }
   },
   "minItems": 1
  },
  "max_tokens": {
   "type": "integer",
   "maximum": 16384,
   "minimum": 1,
   "description": "Optional, default 4096"
  },
  "temperature": {
   "type": "number",
   "maximum": 2,
   "minimum": 0
  },
  "response_format": {
   "type": "object"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "chatcmpl-7f3c2a91",
  "model": "openai/gpt-oss-120b",
  "usage": {
   "total_tokens": 10,
   "prompt_tokens": 9,
   "completion_tokens": 1
  },
  "object": "chat.completion",
  "choices": [
   {
    "index": 0,
    "message": {
     "role": "assistant",
     "content": "OK"
    },
    "finish_reason": "stop"
   }
  ],
  "created": 1791979200
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/model-access-gateway-gpt-oss-120b-chat-completions-x402-0302c981/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent402-arb.rosariovitale0096.workers.dev](https://www.zero.xyz/host/agent402-arb.rosariovitale0096.workers.dev/llms.txt)