Token count

Count exact LLM tokens for a string using the real OpenAI BPE (o200k_base for gpt-4o/o-series, cl100k_base for gpt-4/gpt-3.5). Deterministic, offline - budget context windows without calling a model.

Input

Field	Type	Description
text *	string
model	string	gpt-4o (default, o200k) | gpt-4 / gpt-3.5 (cl100k)

Example output

{
  "tokens": 2,
  "characters": 11,
  "model": "gpt-4o",
  "encoding": "o200k_base"
}

Try it - see the 402 challenge (free)

curl -i -X POST https://agent402.tools/api/token-count \
  -H "Content-Type: application/json" \
  -d '{"text":"hello world","model":"gpt-4o"}'

The response is HTTP 402 Payment Required with exact payment requirements. Any x402 v2 client pays automatically and retries:

Paid call (JavaScript agent)

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

const client = new x402Client();
registerExactEvmScheme(client, { signer: privateKeyToAccount(KEY) });
const payFetch = wrapFetchWithPayment(fetch, client);

const res = await payFetch("https://agent402.tools/api/token-count", {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    "text": "hello world",
    "model": "gpt-4o"
  }),
});

No wallet? Pay with compute

This is a pure-CPU tool, so an agent without a wallet can pay with proof-of-work instead of USDC: fetch a challenge, solve the sha256 puzzle (16 leading zero bits - a fraction of a second of CPU, no money, no AI tokens), and resend with the X-Pow-Solution header.

import { createHash } from "node:crypto";
const lz = (b) => { let t = 0; for (const x of b) { if (!x) { t += 8; continue; } t += Math.clz32(x) - 24; break; } return t; };
const c = await (await fetch("https://agent402.tools/api/pow/challenge?slug=token-count")).json();
let n = 0;
while (lz(createHash("sha256").update(c.challenge + ":" + n).digest()) < c.difficulty) n++;
await fetch("https://agent402.tools/api/token-count", { method: "POST", headers: { "X-Pow-Solution": c.token + ":" + n, "Content-Type": "application/json" }, body: JSON.stringify({"text":"hello world","model":"gpt-4o"}) });

Part of these workflows

This tool is one step in 2 curated multi-tool workflows - agents can fetch the whole sequence as an MCP prompt or call https://agent402.tools/api/skill-packs/{slug}/prompt.

• RAG corpus prep - Take a raw document and turn it into a vector-DB-ready JSONL dataset, deterministically. Measures the corpus, token-counts it with the real OpenAI BPE, chunks at the right token boundary, attaches entities + keywords as metadata, emits NDJSON, then validates every record against a JSON Schema before you ingest it. Seven pure-CPU tools, free-tier eligible - the canonical 'prep my docs for embeddings' workflow done as deterministic tool calls instead of a hand-rolled Python script.
• Text analysis - Full text analysis - word/sentence stats, keyword extraction, and token count in one pass.

Related tools