BERT Tokenizer Calculator

Estimate token counts for BERT and similar models.

Text Input

Input Text

Model Type

Max Sequence Length

Add Special Tokens

Note: Token counts are estimates. Actual tokenization depends on the specific vocabulary and text content.

Estimated Tokens

of 512 max

📝Words

🔤Tokens/Word

1.56

Character Count44

Characters (no spaces)36

Avg. Chars/Word4.0

Special Tokens2

Subword Splits~3

Padding Tokens498

Vocabulary Size30,522

Embedding Memory42.00 KB