ToolVet
80trust / 100

Dev Token Estimator

by AgentTools in Onchain & crypto

x402 APIPassing, checked 4 h ago

Estimate how many tokens a text consumes for each major model family (GPT, Claude, Gemini, Llama, DeepSeek) using a character/word heuristic that is within ~10% of real BPE tokenizers — enough for context budgeting and cost math, with zero dependencies. Use this when an agent needs to approximate token counts per LLM family, ±10%.

GET https://agentstoolshub.com/api/v1/dev/token-estimator

Last 30 days

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed

Uptime
100%
Response time
175 ms typical, 217 ms slowest 5%
Last check
4 h ago
Next check
any minute now

How to call it

GET https://agentstoolshub.com/api/v1/dev/token-estimator

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.

GET https://agentstoolshub.com/api/v1/dev/token-estimator?text=The+quick+brown+fox+jumps+over+the+lazy+dog.+Pack+my+box+with+five+dozen+liquor+jugs.

Parameters

ParameterTypeRequiredDescription
textstringYesText

Example response

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

Example response, 59 lines
{
  "result": {
    "answer": "23 tokens (GPT family)",
    "answerLabel": "85 chars · ±10% estimate",
    "details": [
      {
        "label": "Characters",
        "value": "85"
      },
      {
        "label": "Words",
        "value": "17"
      },
      {
        "label": "CJK characters",
        "value": "0"
      },
      {
        "label": "Method",
        "value": "heuristic (chars/word mix, CJK-aware)"
      }
    ],
    "steps": [
      "CJK characters count ≈ 1.1 tokens each",
      "Other scripts ≈ 3.7 chars/token, blended with words × 1.32",
      "Model multipliers applied: 1, 1.06, 1.12, 1.18, 1.1"
    ],
    "table": {
      "columns": [
        "Model family",
        "Est. tokens"
      ],
      "rows": [
        [
          "gpt-4o / gpt-4.1 / gpt-5 (o200k)",
          23
        ],
        [
          "claude (Opus / Sonnet / Haiku)",
          25
        ],
        [
          "gemini 2.5 / 3",
          26
        ],
        [
          "llama 4 / mistral",
          28
        ],
        [
          "deepseek v3",
          26
        ]
      ]
    },
    "value": 23
  },
  "tool": "token-estimator"
}

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 'https://agentstoolshub.com/api/v1/dev/token-estimator?text=The+quick+brown+fox+jumps+over+the+lazy+dog.+Pack+my+box+with+five+dozen+liquor+jugs.'

# 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://agentstoolshub.com/api/v1/dev/token-estimator?text=The+quick+brown+fox+jumps+over+the+lazy+dog.+Pack+my+box+with+five+dozen+liquor+jugs.' \
  | 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%2Fagentstoolshub.com%2Fapi%2Fv1%2Fdev%2Ftoken-estimator
const res = await pay("https://agentstoolshub.com/api/v1/dev/token-estimator?text=The+quick+brown+fox+jumps+over+the+lazy+dog.+Pack+my+box+with+five+dozen+liquor+jugs.");
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.get("https://agentstoolshub.com/api/v1/dev/token-estimator?text=The+quick+brown+fox+jumps+over+the+lazy+dog.+Pack+my+box+with+five+dozen+liquor+jugs.")
    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
4 h agoPassed402204 ms$0.002
8 h agoPassed402187 ms$0.002
12 h agoPassed402133 ms$0.002
16 h agoPassed402130 ms$0.002
20 h agoPassed402217 ms$0.002
23 h agoPassed402237 ms$0.002
27 h agoPassed402151 ms$0.002
31 h agoPassed402155 ms$0.002
34 h agoPassed402196 ms$0.002
38 h agoPassed402186 ms$0.002
41 h agoPassed402213 ms$0.002
45 h agoPassed402146 ms$0.002
2 days agoPassed402152 ms$0.002
2 days agoPassed402214 ms$0.002
2 days agoPassed402175 ms$0.002