← back to hub
↑ parent
Tokenizer Visualization
{{ tokenizerEngine }}
Paste text to see how different tokenizers segment it.
Engine
UTF-8 bytes
Naive words
OpenAI: cl100k_base (GPT‑3.5/4)
OpenAI: o200k_base (GPT‑4o)
OpenAI: p50k_edit (Code editing models)
OpenAI: r50k_base
Tokens
{{ tokenizerTokens.length }} total · {{ tokenizerWordCount }} words · {{ tokenizerCharCount }} chars
{{ i }}
{{ tok.text }}
#{{ tok.id }}
Tokens will appear here.