Generations
by ThumbnailCreator in AI models & inference
Generate YouTube thumbnails with AI image models (GPT Image, Nano Banana, FLUX, Seedream, Ideogram, Grok) side by side. Optional query: models (comma-separated ids from https://thumbnailcreator.ai/llms.txt), n (1-4 per model), format (16:9, 1:1, 9:16, 4:5). Body: {"prompt": "3-2000 characters"}. Charged only when every image succeeds.
POST https://thumbnailcreator.ai/api/x402/generations
Last 30 days
Status and outage history · Atom feed
- Uptime
- 100%
- Response time
- 399 ms typical, 801 ms slowest 5%
- Last check
- 1 h ago
- Next check
- any minute now
How to call it
POST https://thumbnailcreator.ai/api/x402/generations
Each call costs $0.167 in USDC on Base, paid with the request over x402.
Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.
Example request
From the listing.
POST https://thumbnailcreator.ai/api/x402/generations
content-type: application/json
{
"prompt": "Excited chef holding a giant burger, bold yellow text \"$500 BURGER\""
}Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Yes | What the thumbnail shows, including any on-image text. |
requestId | string (uuid) | No | Optional idempotency key. |
Example response
The provider's example. We can't check it without paying.
{
"costMicros": 167000,
"format": "16:9",
"id": "b7c1c7b2-0000-4000-8000-000000000000",
"images": [
{
"format": "16:9",
"model": "gpt-image-2",
"priceMicros": 167000,
"status": "succeeded",
"url": "https://.../thumbnail.jpg"
}
],
"object": "generation",
"status": "succeeded"
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.167.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://thumbnailcreator.ai/api/x402/generations' \
-H 'content-type: application/json' \
--data-raw '{"prompt":"Excited chef holding a giant burger, bold yellow text \"$500 BURGER\""}'
# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://thumbnailcreator.ai/api/x402/generations' \
-H 'content-type: application/json' \
--data-raw '{"prompt":"Excited chef holding a giant burger, bold yellow text \"$500 BURGER\""}' \
| grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decodeJavaScript: pay and call
// 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";
// Pays at most $0.167 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.167" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);
// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.167 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fthumbnailcreator.ai%2Fapi%2Fx402%2Fgenerations&method=POST
const res = await pay("https://thumbnailcreator.ai/api/x402/generations", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"prompt": "Excited chef holding a giant burger, bold yellow text \"$500 BURGER\""
}),
});
console.log(res.status, await res.text());Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client
# Pays at most $0.167 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.167"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.post(
"https://thumbnailcreator.ai/api/x402/generations",
json={
"prompt": "Excited chef holding a giant burger, bold yellow text \"$500 BURGER\"",
},
)
print(res.status_code, res.text)Security scan
- No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time | Price |
|---|---|---|---|---|
| 1 h ago | Passed | 402 | 689 ms | $0.167 |
| 5 h ago | Passed | 402 | 766 ms | $0.167 |
| 9 h ago | Passed | 402 | 359 ms | $0.167 |
| 13 h ago | Passed | 402 | 1.1 s | $0.167 |
| 17 h ago | Passed | 402 | 415 ms | $0.167 |
| 21 h ago | Passed | 402 | 399 ms | $0.167 |
| 25 h ago | Passed | 402 | 371 ms | $0.167 |
| 29 h ago | Passed | 402 | 754 ms | $0.167 |
| 32 h ago | Passed | 402 | 752 ms | $0.167 |
| 36 h ago | Passed | 402 | 382 ms | $0.167 |
| 40 h ago | Passed | 402 | 801 ms | $0.167 |
| 43 h ago | Passed | 402 | 364 ms | $0.167 |
| 47 h ago | Passed | 402 | 283 ms | $0.167 |
| 2 days ago | Passed | 402 | 342 ms | $0.167 |
| 2 days ago | Passed | 402 | 386 ms | $0.167 |