Skip to content
CodexPal
AI tools · private, in-browser

How many tokens
is this text?

Paste a prompt or document and get a fast estimate of its token count and input cost.

Count before you send

Token estimator.

A quick estimate in your browser. Nothing you paste is sent anywhere.

Estimated tokens≈ 0
Likely range
0 – 0
Characters
0
Words
0
Input cost once · Claude Sonnet 5.5
USD 0.00
Input cost × 1,000 requests
USD 0.00

Uses the published rule of thumb of about four characters per token, or 60–80 English words per 100 tokens. For billing-grade counts, use the provider’s token-counting API with your exact model.

Why it is an estimate

Every model counts differently.

Each model family splits text with its own tokenizer. Anthropic notes that its newer tokenizer produces roughly 30% more tokens for the same text than earlier Claude models. Languages written in non-Latin scripts, code and unusual formatting often use more tokens per character than plain English.

Read: why the same text costs differently →
Get an exact number

Ask the provider.

For a billing-grade count, use the provider’s own tool. Anthropic’s token-counting endpoint is free to use and accepts the same input as a message. Gemini offers a count_tokens method and returns usage on every response. Every major API reports input and output tokens in its response.

Claude token counting ↗ · Gemini tokens guide ↗