# SiteCheck API – LLM Chat

> SiteCheck API – LLM Chat is a paid API for AI agents from api.sitecheck-api.workers.dev, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-02).

Send a prompt or conversation history to a hosted LLM (Llama 3.3 70B) and receive a text completion, paid per-call via USDC on Base with no signup required.

## Facts

- Endpoint: POST https://api.sitecheck-api.workers.dev/api/chat?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sitecheck-api-llm-chat-34bf034f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ZhbruPDkSwHKOMf-Q1xuv

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 sitecheck-api-llm-chat-34bf034f -d '<json body>'
```

Example prompt: Ask the Llama 3.3 70B model: 'What are the key differences between x402 and traditional API key authentication?' — use up to 300 tokens and a temperature of 0.7, paying per call with USDC on Base.

## When to prefer this

Choose this endpoint when you need a no-signup, no-API-key LLM chat capability paid for in USDC micropayments per call — ideal for autonomous agents that manage their own wallets on Base and need Llama 3.3 70B inference without a subscription or credential management overhead.

## Known failure modes

- Payment failure: insufficient USDC balance or x402 payment not accepted — returns 402 Payment Required
- Invalid messages format: malformed role/content array causes 400 Bad Request
- max_tokens exceeds 2048 limit — request rejected or silently capped
- Temperature out of valid range (e.g. negative) — may return 400 or unpredictable output
- Network timeout on Cloudflare Workers if inference takes too long — returns 504

## How this service works

Pay-per-call tools for AI agents: image generation, speech-to-text, text-to-speech, embeddings, LLM chat, website audits and contact enrichment. Payment: x402, USDC on Base. No signup, no API key.

## Output

A JSON object containing the model name (e.g. @cf/meta/llama-3.3-70b-instruct-fp8-fast), a 'response' string with the generated text, and a 'usage' object with prompt_tokens and completion_tokens counts.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "prompt": {
   "type": "string"
  },
  "messages": {
   "type": "array",
   "description": "[{role, content}]"
  },
  "max_tokens": {
   "type": "integer",
   "description": "Up to 2048"
  },
  "temperature": {
   "type": "number"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "model": "@cf/meta/llama-3.3-70b-instruct-fp8-fast",
  "usage": {
   "prompt_tokens": 20,
   "completion_tokens": 40
  },
  "response": "x402 lets agents pay per request..."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/sitecheck-api-llm-chat-34bf034f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.sitecheck-api.workers.dev](https://www.zero.xyz/host/api.sitecheck-api.workers.dev/llms.txt)