Contador de tokens LLM
Cuenta tokens con el tokenizador BPE real para los modelos de OpenAI (exacto), además de estimaciones claramente identificadas para Claude, Gemini y otros modelos.
Enter some text to see the count.
Cómo usar
- Paste the text you want to count.
- Pick a model. GPT-4o family and GPT-4/3.5 are counted exactly with the real tokenizer.
- Claude, Gemini, Llama and Mistral show an estimate, always labeled as one, with the heuristic stated.
Notas
Exact counts run entirely in your browser with gpt-tokenizer (o200k_base / cl100k_base); your text is never sent to a server. Other providers do not publish a browser tokenizer, so this page offers only a character-based estimate for them and never presents it as exact.
Preguntas frecuentes
- How far off can the estimates be?
- For English prose, often within 10–20%, but code, long numbers and CJK text can be far off. Keep a margin when budgeting from an estimate.
- Why does Japanese cost more tokens?
- BPE tokenizers are trained mostly on English, so a Japanese character typically becomes about one token (sometimes more). You can verify this with the exact GPT counters on this page.