Take website screenshots from your AI agent

Try it free

curl -X POST https://agentsvc.io/api/v1/try/screenshot -H "Content-Type: application/json" -d '{}'

JavaScript

npm i @x402/fetch @x402/evm viem

import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client();
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agentsvc.io/api/v1/proxy/screenshot", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({ url: "https://example.com", full_page: true }),
});
console.log(await res.json());

Python

pip install "x402[httpx]" eth_account

from eth_account import Account
from x402 import x402Client
from x402.http.clients import x402HttpxClient
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client

client = x402Client()
register_exact_evm_client(client, EthAccountSigner(Account.from_key(PRIVATE_KEY)))
async with x402HttpxClient(client) as http:
    r = await http.post("https://agentsvc.io/api/v1/proxy/screenshot", json={"url": "https://example.com", "full_page": True})
    await r.aread()
    print(r.json())

Input and output

• url: the page to capture.
• width and height: viewport in pixels, default 1280 x 800. Use 390 x 844 for a phone view.
• full_page: true captures the whole page height instead of the first screen.
• wait_ms: extra wait after loading, default 1000. Raise it for pages that animate in or load late.

The answer has data.image_base64. Save it as a file:

curl -X POST https://agentsvc.io/api/v1/proxy/screenshot \
  -H "Authorization: Bearer asvc_cr_..." -H "Content-Type: application/json" \
  -d '{"url":"https://example.com","full_page":true}' | jq -r .data.image_base64 | base64 -d > page.png

Need the text, not the picture?

Reading a page as text is cheaper and easier for a model: web pages as Markdown from $0.0025.

Paying

No account and no API key. Three ways to pay, all only for calls that succeed:

• Wallet (x402): a separate wallet with a few dollars of USDC on Base, Solana, Polygon or Arbitrum. The x402 client pays the price from the 402 answer and retries; you pay no gas.
• Credit token: buy one at /credits ($5 to $100, USDC on Base, +10% bonus) and send it as Authorization: Bearer. Good for a script that runs through a long list.
• Zero: if your agent already uses the Zero CLI, it pays the 402 for you: zero fetch https://agentsvc.io/api/v1/proxy/screenshot -d '{"url":"https://example.com"}'

Details for every client, MCP and frameworks: docs, LangChain, Vercel AI SDK.

Claude Code, Codex or Cursor can learn this as a skill: npx skills add agentsvc/skills (source).