LLM Token Counter & Cost Estimator

Paste text to instantly count tokens for Claude / GPT / Gemini / Llama / Mistral. Estimates $USD cost from per-token pricing, shows % of each model's context window (200K / 1M etc.).

100% Free No signup Browser-only 5 languages Dark mode

Paste text

Input mult (how many times) Expected output tokens Batch API (50% off) Cached input (10%)

Quick stats

Chars

Words

CJK

Lines

📐 Estimation method

• ASCII: ~4 chars / token (GPT BPE 平均)
• CJK: ~1.5 tokens / char (GPT/Claude いずれも)
• Exact values may vary ±10-20% by model

Model	Input	Output	In $/MT	Out $/MT	Total cost	Ctx	Used

❓ FAQ

Accurate?

Approximate (±10-20%). Exact requires the official tokenizer (tiktoken etc.). Good enough for cost planning

Pricing as of when?

As of 2026-04. From official Anthropic / OpenAI / Google docs

Batch / cache?

Anthropic & OpenAI Batch API = 50% off (async). Anthropic prompt cache hit = 10% of input price

🐛 Found a bug or issue with this tool?

Free to use, no signup. Even just the steps to reproduce are helpful. Reports go directly to the operator and help us fix issues.

LLM Token Counter & Cost Estimator

❓ FAQ

Thanks for your report!