Count tokens.
Estimate costs. Ship smarter.

Know what your AI calls will cost before you make them. Compare across OpenAI, Anthropic, Google, Meta and Mistral.

✓ No signup ✓ OpenAI exact via tiktoken ~ Others clearly estimated ✓ Local processing
0 chars · 0 words · 0 lines

Compare models

How tokenization works

🔢

What are tokens?

Tokens are the chunks LLMs process — roughly 3–4 characters of English text. 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 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.

Simple, transparent pricing

Everything you need to ship AI features without surprises.

Free

$0/mo

  • Token counting — all models
  • File uploads up to 2 MB
  • Cleaning demo (first 5,000 chars)
  • Retrieval demo (top 3 chunks)
  • CSV export
  • Batch upload

Pro

$12/mo

  • Everything in Free