ToolVet
75trust / 100

Compute Gpu Prices

by Tanod utilpeek in Developer tools

x402 APIPassing, checked 1 h ago

utilpeek (Tanod) cloud GPU prices: AWS and Azure list price per GPU-hour by chip, memory and region, on-demand and spot, cheapest first. Use when an agent must pick the cheapest cloud GPU: H100, A100, L4 and more, AWS and Azure, per GPU-hour, on-demand or spot.

POST https://tanod.dev/v1/compute/gpu-prices

Last 30 days

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed

Uptime
100%
Response time
379 ms typical, 765 ms slowest 5%
Last check
1 h ago
Next check
any minute now

How to call it

POST https://tanod.dev/v1/compute/gpu-prices

Each call costs $0.002 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://tanod.dev/v1/compute/gpu-prices
content-type: application/json

{}

Parameters

ParameterTypeRequiredDescription
chipstring or nullNoGPU chip, any case, e.g. H100 or A100 80GB. Default: null.
limitintegerNoRows to return, 1-100. Default: 20.
max_usd_per_gpu_hournumber or nullNoCeiling on the ranked price, USD. Default: null.
min_gpu_mem_gbinteger or nullNoMinimum GPU memory in GB. Default: null.
pricingstringNoPrice to rank by; any is the lower of the two. One of: on_demand, spot, any. Default: "any".
providerstring or nullNoAWS or Azure. Default: null.
regionsarray of string or nullNoRegion names, e.g. us-east-1. Default: null.

Example response

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

Example response, 34 lines
{
  "count_matched": 22,
  "count_returned": 1,
  "generated_at": "2026-10-13T17:34:30Z",
  "note": "List prices per GPU-hour from the providers' public price lists (instance price divided by GPUs per instance), excluding tax, egress and storage. Spot prices change often. Not a quote.",
  "pricing": "any",
  "rows": [
    {
      "chip": "H100",
      "effective": "2026-10-12",
      "gpu_mem_gb": 80,
      "gpus": 8,
      "od_per_gpu_h": "6.8800",
      "price_kind": "on_demand",
      "price_usd_per_gpu_hour": "6.8800",
      "provider": "AWS",
      "region": "us-east-1",
      "sku": "p5.48xlarge",
      "source": "AWS Price List",
      "spot_per_gpu_h": null
    }
  ],
  "sources": {
    "aws": {
      "checked_at": "2026-10-13T17:34:30Z",
      "publication_date": "2026-10-12",
      "status": "ok"
    },
    "azure": {
      "checked_at": "2026-10-13T17:34:30Z",
      "status": "ok"
    }
  }
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.002.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://tanod.dev/v1/compute/gpu-prices' \
  -H 'content-type: application/json' \
  --data-raw '{}'

# 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://tanod.dev/v1/compute/gpu-prices' \
  -H 'content-type: application/json' \
  --data-raw '{}' \
  | 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 $0.002 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.002" });
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 $0.002 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Ftanod.dev%2Fv1%2Fcompute%2Fgpu-prices&method=POST
const res = await pay("https://tanod.dev/v1/compute/gpu-prices", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({}),
});
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 $0.002 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.002"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.post(
        "https://tanod.dev/v1/compute/gpu-prices",
        json={},
    )
    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
1 h agoPassed402303 ms$0.002
5 h agoPassed4021.2 s$0.002
9 h agoPassed402379 ms$0.002
18 h agoPassed402765 ms$0.002