Free Token Counter — Privacy Focused

Token Counter

Free AI token calculator for GPT, Claude, Gemini, and more. Know exactly what your prompts will cost before you send them.

$2.50 / $10.00 per Mtok
Loading tokenizer...
Try:

Runs entirely in your browser — your text never leaves your device.

Features

The most accurate token counter for AI developers

Use this token counter for precise token counting. No guesswork. No surprises. Every token counted with the precision developers trust.

Full Model Coverage

Use this token counter for GPT-4o, GPT-4.1, GPT-5, o1/o3 and all major AI models — powered by the official OpenAI Tiktoken library.

Automatic Tokenizer Selection

Each AI model uses its correct encoding. This token counter automatically selects o200k_base or cl100k_base for accurate results.

Accurate Cost Estimation

This token calculator shows input and output costs at current API pricing. Know exactly what your prompts will cost with this token counter.

Shareable Links

Generate a URL with your text pre-filled. Share token counts with your team, or save your work with this token counter for later.

Client-Side Only

Everything runs in your browser using WebAssembly. Your text never leaves your device. No server, no logs, no tracking.

No Signup Required

Open the token counter and start counting tokens immediately. Zero friction, zero commitment.

How It Works

Use this token counter in three simple steps

01

Paste Your Text

Enter any text, prompt, or document into the token counter input. Works with any language.

02

Select a Model

Choose your AI model from the dropdown. The token counter handles encoding automatically.

03

Get Your Token Count

See the token count and estimated API cost instantly from this token counter. Copy the result with one click.

Pricing Reference

Token counter API pricing reference

Use this token calculator and counter to estimate AI API costs. Token counts are calculated against official API rates. Prices are in USD per million tokens.

Model Input / MTok Output / MTok
GPT-5.4 Nano $0.20 $1.25
GPT-5.4 Mini $0.75 $4.50
GPT-5.4 Pro $30.00 $180
GPT-5.4 $2.50 $15.00
GPT-5.3 Chat $1.75 $14.00
GPT-5.3-Codex $1.75 $14.00
GPT-5.2-Codex $1.75 $14.00
GPT-5.2 Chat $1.75 $14.00
GPT-5.2 Pro $21.00 $168
GPT-5.2 $1.75 $14.00
GPT-5.1-Codex-Max $1.25 $10.00
GPT-5.1 $1.25 $10.00
GPT-5.1 Chat $1.25 $10.00
GPT-5.1-Codex $1.25 $10.00
GPT-5.1-Codex-Mini $0.25 $2.00
GPT-5 Image Mini $2.50 $2.00
GPT-5 Image $10.00 $10.00
GPT-5 Pro $15.00 $120
GPT-5 Codex $1.25 $10.00
GPT-5 Chat $1.25 $10.00
GPT-5 $1.25 $10.00
GPT-5 Mini $0.25 $2.00
GPT-5 Nano $0.050 $0.40
GPT-4.1 $2.00 $8.00
GPT-4.1 Mini $0.40 $1.60
GPT-4.1 Nano $0.100 $0.40
GPT-4o Audio $2.50 $10.00
GPT-4o-mini Search Preview $0.15 $0.60
GPT-4o Search Preview $2.50 $10.00
GPT-4o (2024-11-20) $2.50 $10.00
GPT-4o (2024-08-06) $2.50 $10.00
GPT-4o-mini (2024-07-18) $0.15 $0.60
GPT-4o-mini $0.15 $0.60
GPT-4o (2024-05-13) $5.00 $15.00
GPT-4o $2.50 $10.00
GPT-4o (extended) $6.00 $18.00
o3 Deep Research $10.00 $40.00
o4 Mini Deep Research $2.00 $8.00
o3 Pro $20.00 $80.00
o4 Mini High $1.10 $4.40
o3 $2.00 $8.00
o4 Mini $1.10 $4.40
o1-pro $150 $600
o3 Mini High $1.10 $4.40
o3 Mini $1.10 $4.40
o1 $15.00 $60.00
GPT Audio $2.50 $10.00
GPT Audio Mini $0.60 $2.40
gpt-oss-safeguard-20b $0.075 $0.30
gpt-oss-120b (free) $0 $0
gpt-oss-120b $0.039 $0.19
gpt-oss-20b (free) $0 $0
gpt-oss-20b $0.030 $0.11
GPT-4 Turbo $10.00 $30.00
GPT-4 Turbo Preview $10.00 $30.00
GPT-3.5 Turbo (older v0613) $1.00 $2.00
GPT-4 Turbo (older v1106) $10.00 $30.00
GPT-3.5 Turbo Instruct $1.50 $2.00
GPT-3.5 Turbo 16k $3.00 $4.00
GPT-4 (older v0314) $30.00 $60.00
GPT-4 $30.00 $60.00
GPT-3.5 Turbo $0.50 $1.50
Claude Opus 4.6 (Fast) $30.00 $150
Claude Sonnet 4.6 $3.00 $15.00
Claude Opus 4.6 $5.00 $25.00
Claude Opus 4.5 $5.00 $25.00
Claude Haiku 4.5 $1.00 $5.00
Claude Sonnet 4.5 $3.00 $15.00
Claude Opus 4.1 $15.00 $75.00
Claude Opus 4 $15.00 $75.00
Claude Sonnet 4 $3.00 $15.00
Claude 3.7 Sonnet $3.00 $15.00
Claude 3.7 Sonnet (thinking) $3.00 $15.00
Claude 3.5 Haiku $0.80 $4.00
Claude 3 Haiku $0.25 $1.25

Pricing sourced from OpenAI and Anthropic official pricing pages. Subject to change. Prices marked with ~ are estimated — verify before making billing decisions. Output costs are shown for reference — input tokens are what this token counter calculates.

FAQs

Common Questions for Token Counter

What is a token in AI models?

A token is the basic unit of text that AI models process. For English text, one token is roughly 4 characters or 3/4 of a word. The phrase 'hello world' is about 2 tokens. AI pricing is typically quoted per million tokens (Mtok). Token counters help developers estimate API costs before sending prompts.

How accurate is the token count?

For GPT models, Token counter uses Tiktoken — the same tokenizer library OpenAI uses in production — providing exact token counts. For Claude and other models that have not released their tokenizer publicly, statistical estimation based on character-to-token ratios is used, so counts are approximate (marked with ≈).

Which AI models are supported?

Token counter support for GPT-4o, GPT-4.1, GPT-4.5, GPT-5, o1/o3/o4 series reasoning models, GPT-4 Turbo, and GPT-3.5 Turbo via Tiktoken exact counting. Claude models use statistical estimation. The tool covers all current OpenAI models plus legacy ones, with 100+ models in the catalog.

How does token counter estimate API costs?

Token Counter calculates costs using official API pricing from OpenAI and Anthropic (USD per million tokens). Input and output costs are shown separately. For newer models where pricing is unconfirmed, estimated prices are used and marked with a warning to verify before making billing decisions.

Is my text sent to any server when using token counter?

No. All tokenization happens entirely in your browser using the Tiktoken WebAssembly module loaded from CDN. Your text never leaves your device. There are no analytics, no logs, and no server-side processing, making it completely privacy-focused.

What is the maximum text length for token counting?

The current maximum is 100,000 characters per text input. For longer documents, splitting into sections is recommended. The tool processes text client-side with WebAssembly for fast performance even with large inputs.

How do I share token counts with my team?

Token Counter automatically updates the URL with your text as you type. Simply copy the URL from your browser address bar and share it. Anyone who opens that link will see your text pre-loaded, making it easy to collaborate on prompt engineering.

Can I use token counter for commercial purposes?

Yes. Token counter is completely free to use for any purpose, commercial or personal. No signup is required, no API keys are needed, and there are no usage limits.

Start counting tokens now

No signup. No tracking. Just accurate token counting with this token counter in your browser.

Try Token Counter