Token Count

Estimates LLM token counts entirely locally, with no external lookups.

Overview

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.

Endpoint

Method	Endpoint	Price	Description
POST	/v1/marketplace/api/token-count-508	$0.00575	Invoke Token Count (Llm) and return the upstream response.

How to call it

Requests are paid per call over the x402 protocol. Call the endpoint, receive a 402 Payment Required quote, then repeat the request with the signed payment header. The SDKs do both steps for you.

# 1. Ask for a quote
curl -i -X POST https://api.jarvisclaw.ai/v1/marketplace/api/token-count-508 \
  -H 'Content-Type: application/json' \
  -d '{}'

# 2. Pay it (the SDK signs and retries for you)
curl -X POST https://api.jarvisclaw.ai/v1/marketplace/api/token-count-508 \
  -H 'Content-Type: application/json' \
  -H 'X-PAYMENT: <signed-payload>' \
  -d '{}'

Open in the marketplace