# Arch Tools AI Generate

> Arch Tools AI Generate is a paid API for AI agents from archtools.dev, paid per call via x402, $0.04/call, status unknown (last checked 2026-09-14).

Sends a prompt to an AI model (defaulting to Claude) and returns a generated text response, billed per-call in USDC on Base.

## Facts

- Endpoint: POST https://archtools.dev/v1/tools/ai-generate
- Price: $0.04/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/arch-tools-ai-generate-f3219020
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_0V2Qo4ky1db7XJ4MnATAu

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 arch-tools-ai-generate-f3219020 -d '<json body>'
```

Example prompt: Use the Claude model to generate a response to this prompt: 'Write a concise executive summary of the benefits of renewable energy for a business audience', with a system prompt of 'You are a professional business writer' and a max of 512 tokens.

## When to prefer this

Choose this endpoint when you need pay-per-call AI text generation without managing API keys or model subscriptions — ideal for agent pipelines that need occasional LLM inference billed transparently in USDC on Base. Prefer it over direct Anthropic API calls when you want x402 micropayment billing and don't want to manage authentication credentials. Best suited for lightweight, single-turn prompt-response tasks rather than multi-turn conversation management.

## Known failure modes

- Missing required 'prompt' field returns a 400 validation error
- Payment failure or insufficient USDC balance results in a 402 Payment Required response
- Invalid or unsupported model name may fall back to default or return an error
- Exceeding token limits or rate limits may result in truncated output or 429 errors
- Network timeouts on long completions if max_tokens is very large

## How this service works

AI text generation via Claude. Prompt in, polished text out - drafting, rewriting, extraction and reasoning for agents. Pay per call with USDC (x402) or credits - archtools.dev

## Output

A JSON object containing the AI model's generated text response to the supplied prompt, shaped by any provided system prompt and constrained by the max_tokens limit.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "model": {
   "enum": [
    "claude",
    "gpt4",
    "grok",
    "gemini"
   ],
   "type": "string",
   "default": "claude",
   "description": "AI model to use"
  },
  "prompt": {
   "type": "string",
   "description": "The prompt or question"
  },
  "system": {
   "type": "string",
   "description": "System prompt / persona"
  },
  "max_tokens": {
   "type": "integer",
   "default": 1024
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/arch-tools-ai-generate-f3219020/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from archtools.dev](https://www.zero.xyz/host/archtools.dev/llms.txt)