LLM Token Counter
Paste any text to estimate its token count, then see the estimated input cost across frontier models. Counts update as you type and nothing leaves your browser.
Characters
0
Words
0
Estimated tokens
0
Estimated input cost (0 tokens)
| Model | Vendor | Est. input cost |
|---|---|---|
| Claude Opus 5 | Anthropic | $0.00 |
| Claude Sonnet 5 | Anthropic | $0.00 |
| Claude Haiku 4.5 | Anthropic | $0.00 |
| GPT-5.6 (Sol) | OpenAI | $0.00 |
| Gemini 3.6 Flash | $0.00 | |
| GLM-5.2 | Z.ai | $0.00 |
| GLM-4.6 | Z.ai | $0.00 |
| DeepSeek V4 (flash) | DeepSeek | $0.00 |
Token counts are an estimate based on roughly 4 characters per token, not a real tokenizer. The actual count differs by model, so treat this as a rough guide. Costs use per-1M-token API list input rates and cover input only. Output tokens add to the total on a real run.
Common questions
- How is the token count calculated?
- This tool uses a simple heuristic of roughly 4 characters per token (characters divided by 4, rounded up). It does not run a real tokenizer, which keeps the page fast and dependency-free. Treat the number as an estimate.
- Why does my real token count differ?
- Every model uses its own tokenizer, so the same text can count differently across models. Code, punctuation, and non-English text can shift the ratio well away from 4 characters per token. Use this as a rough guide, not an exact count.
- How is the cost estimated?
- Cost is the estimated token count divided by one million, multiplied by each model's per-1M-token input list price. It covers input only; a real run also pays for output tokens, and provider discounts, caching, or batch rates can change the total.