API Documentation - Token Counter Online

Base URL

https://tokencounteronline.com/api

Authentication

No authentication required. This is a free public API, rate limited by IP address.

Rate Limits

Limit: 60 requests per hour per IP
Window: Sliding 1-hour window
Headers: Rate limit info included in response headers

X-RateLimit-Limit: 60

X-RateLimit-Remaining: 58

X-RateLimit-Reset: 1735306800

POST /api/count

Count tokens for given text and model.

Request Body

{
  "text": "Your text here to count tokens...",
  "model": "openai"
}

Parameters

Field	Type	Required	Description
`text`	string	Yes	Text to count (max 100,000 chars)
`model`	string	No	Model ID (default: "generic")

Success Response (200)

{
  "success": true,
  "data": {
    "tokens": 1234,
    "words": 890,
    "characters": 5432,
    "model": "openai",
    "encoding": "o200k_base"
  },
  "rateLimit": {
    "limit": 60,
    "remaining": 58,
    "reset": 3540
  }
}

Error Response (429)

{
  "success": false,
  "error": {
    "code": "RATE_LIMIT_EXCEEDED",
    "message": "Rate limit exceeded. Try again in 59 minutes.",
    "retryAfter": 3540
  }
}

GET /api/models

Get list of all supported models.

Response (200)

{
  "success": true,
  "data": {
    "models": [
      {"id": "generic", "name": "Generic", "encoding": "approximation", "description": "Fast character/word-based approximation"},
      {"id": "openai", "name": "ChatGPT (OpenAI)", "encoding": "o200k_base", "description": "GPT-4o, o1, o3, GPT-4, GPT-3.5"},
      {"id": "claude", "name": "Claude (Anthropic)", "encoding": "sentencepiece", "description": "Claude 3.5, Claude 3, Claude 2"},
      {"id": "gemini", "name": "Gemini (Google)", "encoding": "sentencepiece", "description": "Gemini Pro, Flash, Ultra"},
      {"id": "llama", "name": "LLaMA (Meta)", "encoding": "sentencepiece", "description": "LLaMA 3.x, LLaMA 2"},
      {"id": "mistral", "name": "Mistral", "encoding": "sentencepiece", "description": "Mistral AI models"}
    ]
  }
}

Supported Models

Model ID	Name	Encoding
`generic`	Generic	approximation
`openai`	ChatGPT (OpenAI)	o200k_base
`claude`	Claude (Anthropic)	sentencepiece
`gemini`	Gemini (Google)	sentencepiece
`llama`	LLaMA (Meta)	sentencepiece
`mistral`	Mistral	sentencepiece

Code Examples

cURL

curl -X POST https://tokencounteronline.com/api/count \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello, how are you today?", "model": "openai"}'

JavaScript (Fetch)

const response = await fetch('https://tokencounteronline.com/api/count', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    text: 'Hello, how are you today?',
    model: 'openai'
  })
});

const data = await response.json();
console.log(`Tokens: ${data.data.tokens}`);

Python

import requests

response = requests.post(
    'https://tokencounteronline.com/api/count',
    json={
        'text': 'Hello, how are you today?',
        'model': 'openai'
    }
)

data = response.json()
print(f"Tokens: {data['data']['tokens']}")

Node.js

const response = await fetch('https://tokencounteronline.com/api/count', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    text: 'Hello, how are you today?',
    model: 'openai'
  })
});

const data = await response.json();
console.log(`Tokens: ${data.data.tokens}`);