# LLM Chat Completions via APEX Faucet (x402)

> LLM Chat Completions via APEX Faucet (x402) is a paid API for AI agents from apexfaucet.xyz, paid per call via x402, $0.002/call, status unknown (last checked 2026-11-02).

OpenAI-compatible chat completion API supporting multiple open-source LLMs, billed at $0.002 USDC per call via x402 micropayment protocol.

## Facts

- Endpoint: POST https://apexfaucet.xyz/api/x402/chat-completions?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/llm-chat-completions-via-apex-faucet-x402-72fea608
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-_KmjO5GH_1JKtT7M_gv7

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 llm-chat-completions-via-apex-faucet-x402-72fea608 -d '<json body>'
```

Example prompt: Send a chat completion request using gpt-oss-120b with this system prompt: 'You are a helpful assistant.' and user message: 'Explain the concept of zero-knowledge proofs in simple terms.' Keep the response under 512 tokens.

## When to prefer this

Choose this endpoint when you need a pay-per-call LLM API with no subscription or API key, especially in agentic or automated workflows using the x402 micropayment protocol. It's ideal for low-volume or bursty inference needs where you want to pay $0.002 per call in USDC rather than managing a monthly plan. Good for agents that need OpenAI-compatible chat completions with tool/function calling support using open-source models like Llama or Qwen.

## Known failure modes

- Insufficient USDC balance causes x402 payment failure and request rejection
- max_tokens exceeds 1024 causes validation error
- Empty or malformed messages array returns 400 error
- Invalid model name not in enum causes rejection
- Streaming not supported — requests with stream:true will fail or be ignored
- Context window overflow if messages array is too large or content too long

## How this service works

Free APEX on X1, and free USDC plus APEX on Arc, three times a day. No gas, no sign-up. Plus a swap, a screener, APEX City and token checks.

## Output

Returns a JSON object with `ok: true`, a `data` field containing the OpenAI-compatible chat completion response (including choices, message content, and tool calls if applicable), and a `paid` field confirming the $0.002 USDC micropayment amount deducted.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "enum": [
    "gpt-oss-120b",
    "gpt-oss-20b",
    "llama-3.3-70b",
    "llama-3.1-8b",
    "qwen3-30b"
   ],
   "type": "string",
   "description": "Default gpt-oss-120b."
  },
  "tools": {
   "type": "array",
   "description": "OpenAI-style function tools (optional)."
  },
  "messages": {
   "type": "array",
   "items": {
    "type": "object",
    "required": [
     "role"
    ],
    "properties": {
     "role": {
      "enum": [
       "system",
       "user",
       "assistant",
       "tool",
       "developer"
      ],
      "type": "string"
     },
     "content": {
      "type": "string"
     }
    }
   },
   "maxItems": 64,
   "minItems": 1
  },
  "max_tokens": {
   "type": "integer",
   "maximum": 1024,
   "minimum": 1
  },
  "temperature": {
   "type": "number",
   "maximum": 2,
   "minimum": 0
  },
  "reasoning_effort": {
   "enum": [
    "low",
    "medium",
    "high"
   ],
   "type": "string",
   "description": "gpt-oss and qwen3 only; default low."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "schema": {
  "type": "object",
  "properties": {
   "ok": {
    "type": "boolean"
   },
   "data": {
    "type": "object"
   },
   "paid": {
    "type": "number"
   }
  }
 },
 "example": {
  "ok": true,
  "data": {},
  "paid": 0.002
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/llm-chat-completions-via-apex-faucet-x402-72fea608/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from apexfaucet.xyz](https://www.zero.xyz/host/apexfaucet.xyz/llms.txt)