Free tools/LLM Token Counter & Cost

Count tokens — and price them across every model.

Live in-browser tokenizer · priced across 12 models

Paste a prompt or document to count its tokens live, then see what it costs as input on every major model — and whether it even fits each model's context window.

Tokens
33
Words
23
Characters
151

Cost of this text as input, per model

ModelAs inputFits context?
GPT-4o mini OpenAI$0.00000
DeepSeek-V3 DeepSeek$0.00001
Gemini 2.5 Flash Google$0.00001
Mistral Large Mistral$0.00002
Llama 3.3 70B (Groq) Meta / Groq$0.00002
Claude Haiku 4.5 Anthropic$0.00003
GPT-5 OpenAI$0.00004
Gemini 2.5 Pro Google$0.00004
o3 OpenAI$0.00007
GPT-4o OpenAI$0.00008
Claude Sonnet 4.5 Anthropic$0.00010
Claude Opus 4.5 Anthropic$0.00016

Token counts use OpenAI's o200k encoding (exact for GPT-4o/GPT-5; a close approximation for Claude and Gemini). Prices per 1M tokens, USD, LiteLLM table (updated 2026-05-22).

How to use it.

1. Paste your text

Drop in a prompt, system instruction, or whole document. Tokenizing happens in your browser as you type — nothing is sent anywhere.

2. Read the live counts

Tokens, words, and characters update instantly. Tokens are what you actually pay for, and they rarely match word count — punctuation, code, and rare words cost more.

3. See the cost and context fit

The table prices your text as input on each model and flags any model whose context window it would overflow.

4. Note the encoding caveat

Counts use OpenAI's o200k tokenizer — exact for GPT-4o/GPT-5, and a close approximation for Claude and Gemini, which use their own tokenizers.

Frequently asked questions.

What is a token?
A token is the unit a model reads — roughly ¾ of a word in English. 'Tokenization' splits text into these units; you're billed per token, not per word.
How many tokens is 1,000 words?
About 1,300 tokens in English (≈0.75 words per token). Code, numbers, and non-English text use more tokens per word.
Is the token count exact for Claude and Gemini?
It's exact for OpenAI models (o200k encoding) and a close approximation for others, which use different tokenizers. For most planning and cost-estimation it's accurate enough.

More free AI tools.

Numbers looking promising?

A free tool gives you a hypothesis. The 30-minute diagnostic is where we pressure-test it against your actual workflows — and decide whether the project is worth building, buying, or skipping.