LLM Token 计数器

Tokens are the basic units that language models process. A token is roughly 4 characters in English or about 1.5 characters in Chinese. Words are typically split into 1-3 tokens.

The tool estimates tokens for GPT-4/GPT-3.5 (cl100k_base), Claude, Gemini, and other major LLMs using their respective tokenization patterns.

Token count determines API cost and context window usage. Most models have maximum token limits per request, so knowing your token count helps optimize prompts.