ToolVet
78trust / 100

Prompt Cost

by TrollBridge in Onchain & crypto

x402 APIPassing, checked 33 min ago

Prompt cost estimator — paste a prompt, get a heuristic token estimate and what it would cost across every model in the /models catalog, cheapest first. Heuristic estimate, not an exact tokenizer count. Toll: $0.02 USDC on Base or Solana.

GET
https://mini-tollbooth.onrender.com/prompt-cost
Price
$0.02
per call in USDC
Uptime
100%
last 30 days
Response time
218 ms
639 ms slowest 5%
Last check
Passed
33 min ago, next any minute now

Run a free test callHow to call it

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed

How to call it

GET https://mini-tollbooth.onrender.com/prompt-cost

Each call costs $0.02 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.

GET https://mini-tollbooth.onrender.com/prompt-cost?model=openai%2Fgpt-4o-mini&text=Explain+quantum+computing+simply

Parameters

ParameterTypeRequiredDescription
modelstringNoOptional model id (substring match) — cost for just that model.
textstringYesThe prompt to estimate token cost for (max 50,000 chars).

Example response

The provider's example. We can't check it without paying.

{
  "cheapest": {
    "est_cost_usd": 0.0000042,
    "id": "openai/gpt-4o-mini"
  },
  "description": "Prompt cost estimator — paste a prompt, get a heuristic token estimate and what it would cost across every model in the /models catalog, cheapest first. Heuristic estimate, not an exact tokenizer count.",
  "estimated_tokens": 28,
  "lane": "/prompt-cost"
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.02.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i 'https://mini-tollbooth.onrender.com/prompt-cost?model=openai%2Fgpt-4o-mini&text=Explain+quantum+computing+simply'

# 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 - 'https://mini-tollbooth.onrender.com/prompt-cost?model=openai%2Fgpt-4o-mini&text=Explain+quantum+computing+simply' \
  | grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decode
JavaScript: 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 $0.02 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.02" });
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 $0.02 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fmini-tollbooth.onrender.com%2Fprompt-cost
const res = await pay("https://mini-tollbooth.onrender.com/prompt-cost?model=openai%2Fgpt-4o-mini&text=Explain+quantum+computing+simply");
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 $0.02 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.02"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.get("https://mini-tollbooth.onrender.com/prompt-cost?model=openai%2Fgpt-4o-mini&text=Explain+quantum+computing+simply")
    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

WhenResultHTTPTimePrice
33 min agoPassed402625 ms$0.02
5 h agoPassed402219 ms$0.02
9 h agoPassed402218 ms$0.02
13 h agoPassed402753 ms$0.02
18 h agoPassed402610 ms$0.02
Show 10 older checks
22 h agoPassed402242 ms$0.02
26 h agoPassed402191 ms$0.02
30 h agoPassed402209 ms$0.02
34 h agoPassed402239 ms$0.02
38 h agoPassed402277 ms$0.02
42 h agoPassed402183 ms$0.02
45 h agoPassed402262 ms$0.02
2 days agoPassed402546 ms$0.02
2 days agoPassed402192 ms$0.02
2 days agoPassed402639 ms$0.02