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

> Model Access Gateway – GPT-OSS-120B Chat Completions (x402, USDC) is a paid API for AI agents from modelaccessgateway.com, paid per call via x402, $0.001/call, status unknown (last checked 2026-10-18).

Runs OpenAI-compatible chat completions against the GPT-OSS-120B model, billed per call in USDC on Base via x402 with no account or API key required.

## Facts

- Endpoint: POST https://modelaccessgateway.com/llm/gpt-oss-120b?utm_source=zero.xyz
- Price: $0.001/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-18
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/model-access-gateway-gpt-oss-120b-chat-completions-x402-usdc-745297f6
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_U3Sz0xb6yk2opVkNxbOHc

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-usdc-745297f6 -d '<json body>'
```

Example prompt: Using Model Access Gateway's pay-per-call setup, send a chat message to GPT-OSS-120B asking it to summarize the following text in 3 bullet points — pay in USDC, stream the response, and set max_tokens to 512.

## When to prefer this

Choose this endpoint when you need OpenAI-compatible GPT-OSS-120B inference without an API subscription, account registration, or stored credentials — ideal for agentic workflows that pay per call in USDC via x402 on Base. Prefer it over subscription-gated APIs when cost isolation per call matters, when operating anonymously, or when building agents that need built-in crypto micropayment flows. The automatic refund guarantee on model failure makes it lower-risk than raw provider APIs for unreliable or experimental workloads.

## Known failure modes

- Payment rejected or insufficient USDC balance — x402 payment handshake fails, no completion returned and automatic refund issued
- Model backend unavailable — upstream model error triggers automatic refund per gateway policy
- Invalid messages array (empty or missing required role field) — 400 validation error
- max_tokens exceeds 16384 limit — schema validation failure
- Temperature out of 0–2 range — request rejected with validation error
- Network timeout on long completions — partial response or no response, refund policy applies

## How this service works

LLM inference API: OpenAI-compatible chat completions for 136 AI models (Claude, GPT, Gemini, Grok, DeepSeek, Qwen, Kimi, GLM), paid per call in USDC on Base with x402. No account, no API key, automatic refund if the model fails.

## Output

Returns an OpenAI-compatible chat.completion JSON object containing the assistant's generated message, the finish reason (stop, length, tool_calls, etc.), token usage breakdown (prompt, completion, total), a completion ID, and the model name. When streaming is enabled, delivers server-sent events incrementally until the response is complete.

## 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-usdc-745297f6/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from modelaccessgateway.com](https://www.zero.xyz/host/modelaccessgateway.com/llms.txt)