Token counter & prompt cost calculator
← All tools· Estimate your full monthly bill
Paste a prompt and see how many tokens it uses — then compare what that single input costs across 29 models from OpenAI, Anthropic, Google, and more. Input tokens only; no output or cache modeling.
Your prompt
Token count uses a chars÷4 heuristic (~±15% vs real tokenizers). Actual counts vary by model and language.
Or enter token count directly
Estimate
Cost by model
Input tokens only, standard API tier. Sorted cheapest first.
| Model | Provider | Tier | Cost (this prompt) | Cost per 1k runs | Cost per 1M runs |
|---|---|---|---|---|---|
| open |
Your text never leaves the browser. Token counts and costs are computed entirely on your device — nothing is sent to a server.
How it works
When you paste text, the tool estimates tokens with a simple chars÷4 rule — roughly one token per four characters of English prose. That matches how most developers ballpark prompt size before shipping, but real tokenizers split differently: code, JSON, and non-English text often use more tokens per character, while some models merge common words into fewer tokens.
Costs come from each provider's published input price per million tokens. The table shows what you'd pay to send this prompt once, then scaled to 1,000 and 1,000,000 identical runs. Output tokens, prompt caching, and batch discounts are not included — use theinference cost calculator for full monthly estimates with output and cache assumptions.
Everything runs in your browser. No API calls, no logging, no analytics on your prompt content. Refresh the page and your text is gone unless you paste it again.