ToolVet
81trust / 100

Auto Messages

by Messages auto in AI models & inference

x402 APIPassing, checked 33 min ago

Anthropic Messages API over x402 - point the Anthropic SDK (or Claude Code / the Agent SDK) at base_url https://agent402.tools/v1/auto and pay $0.01 per call in USDC, no API key, no signup. Same models, caps and price as this tier's /chat/completions route; any model here is served through the Messages wire (Claude natively, others translated). Depth: `effort` (low..max) on Claude 4.7+, thinking.budget_tokens on older Claude. Up to 16,000 input chars and 1024 output tokens; streaming supported.

POST https://agent402.tools/v1/auto/messages

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
183 ms typical, 183 ms slowest 5%
Last check
33 min ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://agent402.tools/v1/auto/messages" \
  -H "content-type: application/json" \
  -d '{"max_tokens":256,"messages":[{"content":"Summarize x402 in one sentence.","role":"user"}]}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fagent402.tools%2Fv1%2Fauto%2Fmessages
const res = await pay("https://agent402.tools/v1/auto/messages", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"max_tokens":256,"messages":[{"content":"Summarize x402 in one sentence.","role":"user"}]}),
});
console.log(await res.json());

Example input

{
  "max_tokens": 256,
  "messages": [
    {
      "content": "Summarize x402 in one sentence.",
      "role": "user"
    }
  ]
}

Example output

{
  "content": [
    {
      "text": "x402 is an HTTP-native way for agents to pay per request with USDC.",
      "type": "text"
    }
  ],
  "id": "msg_…",
  "model": "anthropic/claude-sonnet-5",
  "role": "assistant",
  "stop_reason": "end_turn",
  "type": "message",
  "usage": {
    "input_tokens": 14,
    "output_tokens": 18
  }
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
33 min agoPassed402204 ms$0.01
6 h agoPassed402183 ms$0.01