AI Token Counter API

Count LLM tokens in text: exact counts for OpenAI's o200k_base and cl100k_base tokenizers, estimates for Claude, Gemini and Llama, and how much of common context windows it fills.

POST /api/v1/tools/ai-token-counterMCP ai_token_counterDeveloper Tools

Count tokens exactly for OpenAI o200k_base and cl100k_base, with labelled estimates for Claude, Gemini and Llama, and check which context windows your prompt fits.

Input

Send these as a JSON object. Unknown fields are rejected.

input: The text or prompt to count. (string, required)

Try it in the browser JSON Schema Get an API key

curl https://pithlab.com/api/v1/tools/ai-token-counter \n  -H "Authorization: Bearer $PITHLAB_KEY" \n  -H "Content-Type: application/json" \n  -d '{"input":"PithLab counts tokens the way GPT-4o does."}'

Example response

{
  "ok": true,
  "result": {
    "characters": 42,
    "words": 7,
    "lines": 1,
    "tokens": {
      "o200k_base": 13,
      "cl100k_base": 14
    },
    "estimates": {
      "claude": 12,
      "gemini": 11,
      "llama": 11
    },
    "contextWindows": [
      {
        "window": "8K",
        "tokens": 8192,
        "fits": true,
        "percent": 0.2,
        "remaining": 8179
      },
      {
        "window": "32K",
        "tokens": 32768,
        "fits": true,
        "percent": 0,
        "remaining": 32755
      },
      {
        "window": "128K",
        "tokens": 128000,
        "fits": true,
        "percent": 0,
        "remaining": 127987
      },
      {
        "window": "200K",
        "tokens": 200000,
        "fits": true,
        "percent": 0,
        "remaining": 199987
      },
      {
        "window": "1M",
        "tokens": 1000000,
        "fits": true,
        "percent": 0,
        "remaining": 999987
      }
    ]
  }
}