Name: token-count
Price: 0.005 USDC
Availability: InStock

$ man token-count

agentutility / wordmint / token-count

PRICE / CALL

$0.005

USDC · base mainnet · scheme: exact

METHOD

POST

CLUSTER

wordmint

CATEGORY

uncategorized

STATUS

● live

NAME

token-count — estimates llm token counts entirely locally, with no external lookups

SYNOPSIS

POST https://x402.agentutility.ai/token-count
     Content-Type: application/json
     X-PAYMENT:    <signed-transferWithAuthorization>

     { ... }

↳ first call → 402 Payment Required. Sign USDCtransferWithAuthorization, retry with theX-PAYMENT header.

DESCRIPTION

Estimates LLM token counts entirely locally, with no external lookups. Heuristic estimator targeting cl100k_base / o200k_base (GPT-4o) with calibrated multipliers for Claude and Gemini; the input model name is matched against an internal table of supported tokenizers. Accuracy ±5% versus tiktoken on typical English. Use it as a tokenizer estimate, GPT-4 token count, Claude token count, Gemini token count, or context-window pre-flight.

INPUT — request schema

property	type	description	req?
text	string	Text to count. Up to 1,000,000 chars.	required
model	string	Target model. Examples: 'gpt-4o' (default), 'claude-sonnet-4-5', 'gemini-2-pro'. Free-form; matched against an internal multiplier table.	optional

OUTPUT — response shape

field	type	description
text_chars	string	Character count of the input text that was tokenized.
model	string	Model name supplied in the request (e.g. gpt-4o, claude-3-5-sonnet, gemini-1.5-pro).
matched_tokenizer	string	Internal tokenizer family matched to the model (e.g. cl100k_base, o200k_base, claude-approx, gemini-approx).
estimated_tokens	string	Estimated token count for the input text under the matched tokenizer.
accuracy_note	string	Expected accuracy band versus the official tokenizer, typically within plus or minus 5% on English prose.
source	string	Origin of the estimate; always local-heuristic.

EXAMPLES — two ways to call

EXAMPLE 1 · curl

curl -X POST https://x402.agentutility.ai/token-count \
  -H 'Content-Type: application/json' \
  -d '{ }'

first response = 402 Payment Required with payment requirements; sign + retry with X-PAYMENT.

EXAMPLE 2 · mcp

# Install the MCP package for this endpoint's cluster
npx -y @agentutility/mcp-<cluster>

# Required: EVM private key with USDC on Base
export X402_PRIVATE_KEY=0x...

# Then call the token-count tool from your MCP-aware agent.

MCP server handles payment automatically — your coding agent just calls the tool by name.

METADATA

tags: wordminttokenizertoken-countcontext-windowgpt-4claude-tokenstiktokencl100k
methods: POST
cluster: wordmint
price: $0.005 USDC per call

ADJACENT — other endpoints in wordmint

endpoint	description	price
brand-tagline	Generates brand taglines and slogans for launch pages, X bios, email copy, and product cards.	$0.005
brand-tagline-generate	Generates tagline options for a brand or startup from its name, concept, audience, and tone.	$0.005
card-resolve	Normalizes free-form graded card text into a canonical card object.	$0.005
content-simhash	Fingerprints text with a 64-bit SimHash for near-duplicate detection, computed entirely locally.	$0.005
cron-parse	Cron parser.	$0.005
detect-language	Language detector / language identification.	$0.005
dictionary-define	Looks up English word definitions with pronunciation, part of speech, and synonyms.	$0.005
embedding-similarity	Measures how semantically similar two strings are: embeds both via Venice (default model: text-embedding-bge-m3) and returns the cosine s…	$0.005