# Agent Toolbox – GPT-OSS-120B Chat Completions

> Agent Toolbox – GPT-OSS-120B Chat Completions is a paid API for AI agents from agent-toolbox.zafermemon87.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-29).

OpenAI-compatible chat completion endpoint powered by gpt-oss-120b, an open-weight reasoning model, returning structured responses with visible reasoning traces.

## Facts

- Endpoint: POST https://agent-toolbox.zafermemon87.workers.dev/v1/llm/gpt-oss-120b/chat/completions?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-toolbox-gpt-oss-120b-chat-completions-27236216
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FKzTN4wyfu3gfzEhxsHAr

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 agent-toolbox-gpt-oss-120b-chat-completions-27236216 -d '<json body>'
```

Example prompt: Ask the gpt-oss-120b reasoning model: given the following financial data, reason step-by-step about which investment option carries the least risk and return your answer as a JSON object with fields 'recommendation' and 'rationale'.

## When to prefer this

Choose this endpoint when you need a large (120B parameter) open-weight reasoning model with visible chain-of-thought via the OpenAI SDK interface, especially for multi-step inference tasks, structured JSON output, or when you want a drop-in OpenAI-compatible API without OpenAI's proprietary model lock-in. Prefer over smaller models when reasoning quality matters more than latency. Not suitable for streaming use cases or inputs exceeding 32,000 characters.

## Known failure modes

- Input exceeds 32,000 character limit — request rejected
- max_tokens value above 2048 — validation error
- Malformed messages array (missing role or content) — schema error
- Payment failure or insufficient USDC balance — 402 response
- Model unavailable or worker error — 5xx response
- Temperature outside 0–2 range — validation error

## How this service works

OpenAI-compatible chat completion with gpt-oss-120b (OpenAI's open-weight reasoning model): set the base URL to /v1/llm/gpt-oss-120b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call, no streaming.

## Output

Returns an OpenAI-format chat.completion JSON object containing the assistant's reply in choices[0].message.content, an optional reasoning_content field with the model's internal chain-of-thought, token usage breakdown (prompt_tokens, completion_tokens, total_tokens), a finish_reason, and metadata like model name, object type, and a unique completion ID.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role",
     "content"
    ],
    "properties": {
     "role": {
      "type": "string"
     },
     "content": {
      "type": "string"
     }
    }
   },
   "description": "OpenAI chat messages: [{role: system|user|assistant, content}] (up to 32,000 characters in total)"
  },
  "max_tokens": {
   "type": "integer",
   "maximum": 2048,
   "minimum": 1,
   "description": "Default 2048"
  },
  "temperature": {
   "type": "number",
   "maximum": 2,
   "minimum": 0
  },
  "response_format": {
   "type": "object",
   "description": "{\"type\": \"json_object\"} for JSON output"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "id": "chatcmpl-2f3cbf59f9204d269ba32770",
  "model": "gpt-oss-120b",
  "plain": "gpt-oss-120b: The capital of France is Paris.",
  "usage": {
   "total_tokens": 124,
   "prompt_tokens": 78,
   "completion_tokens": 46
  },
  "object": "chat.completion",
  "choices": [
   {
    "index": 0,
    "message": {
     "role": "assistant",
     "content": "The capital of France is Paris.",
     "reasoning_content": "User asks: \"In one sentence, what is the capital of France?\" Answer: \"The capital of France is Paris.\" Provide one sentence."
    },
    "finish_reason": "stop"
   }
  ],
  "created": 1792850662
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-toolbox-gpt-oss-120b-chat-completions-27236216/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-toolbox.zafermemon87.workers.dev](https://www.zero.xyz/host/agent-toolbox.zafermemon87.workers.dev/llms.txt)