Token Counter
Paste any text to count characters, words, and estimated AI tokens across major model tokenizers.
Your text
Token count
Characters
0
Words
0
Estimated tokens by model family
| Tokenizer | Tokens | Cost as input (example model) |
|---|---|---|
| GPT (OpenAI) | 0 | $0.000000 |
| Claude (Anthropic) | 0 | $0.000000 |
| Gemini (Google) | 0 | $0.000000 |
How this is calculated
tokens ≈ characters ÷ 4 (English prose rule of thumb, varies slightly by tokenizer family). For exact counts, use the provider's own tokenizer library.
Pricing is verified against provider pricing pages as of 2026-09-01. AI and cloud pricing changes frequently — confirm the current rate on the provider's own pricing page before budgeting.
Frequently asked questions
What's the difference between a word count and a token count?
A word counter splits on whitespace. A token counter splits the way an LLM's tokenizer does — subword units that don't map 1:1 to words, which is why token counts are usually higher than word counts.
How many tokens is 1,000 words?
Roughly 1,300 tokens for English prose, using the common ¾-word-per-token rule of thumb — the exact figure varies by tokenizer and content type (code and non-English text tokenize differently).
Can I use this to check if my text fits a model's context window?
Yes — compare the estimated token count here against your target model's context window. For a detailed budget across a full conversation, use the Context Window Calculator.
Does this tool store or send my text anywhere?
No — the count is computed entirely in your browser from the text you paste; nothing is sent to a server.