Count tokens.
Estimate costs. Ship smarter.
Paste text or upload a file to see exact and estimated token counts across all major LLM APIs — with real-time cost projections.
Drop a file here or
.txt · .md · .pdf · .docx · .py · .js · .ts · .go · .rs · .java
and 20+ more code & text formats · max 10 MB
How tokenization works
What are tokens?
Tokens are the chunks LLMs process — roughly 3–4 characters of English text. "tokenization" splits to token, ization = 2 tokens. Code and non-Latin scripts often produce more tokens per character.
Exact vs. estimated
OpenAI uses the open-source tiktoken library — we run the same tokenizer server-side, so counts are exact. Anthropic, Google and others use proprietary tokenizers; we use a calibrated character-density estimate and label it clearly.
Cost formula
Cost = (tokens ÷ 1,000,000) × price-per-million-tokens. Input and output tokens are billed separately by most providers. We show both, assuming output ≈ input length as a working estimate.