Token Counter
Paste your text and instantly see token counts for GPT-4, GPT-4o, Claude, and other models.
Token Counts
GPT-4 / GPT-4o
cl100k_base
0
GPT-4o-mini / o1
o200k_base
0
Claude (estimate)
~3.5 chars/token
0
General (estimate)
~0.75 words/token
0
How Tokenization Works
What is a Token?
Tokens are chunks of text that LLMs process. A token can be a word, part of a word, or punctuation. On average, 1 token ≈ 4 characters or ¾ of a word in English.
Why Token Counts Differ
Each model uses a different tokenizer. GPT-4 uses cl100k_base, newer models use o200k_base. Claude and Gemini have their own tokenizers with slightly different splits.
API Pricing
You pay per token — both for input (your prompt) and output (the response). Use this tool to estimate costs before sending large prompts.