Home / Tokenizer

LLM token counter

Paste text and pick a model to count tokens before you call an API. Exact counts use OpenAI encodings in-browser; other providers are clearly labeled Approx. Same calculator as Home, counting first.

Cost calculator

Paste a prompt, tune cache and batch, compare models, and share the estimate URL. Token text never leaves this browser.

$0.004226estimated request costExact tokens
Input tokens
65
Output tokens
512
Input cost
$0.00013
Output cost
$0.004096
Characters
306
Words
51

Monthly projector

500 requests/day · 15,000/month

Daily
$2.113
Monthly
$63.39
Yearly
$771.25

Rates in $2.00/1M · out $8.00/1M

Context 577 / 1,000,000 · Verified · official pricing

gpt-tokenizer · o200k_base

Token pieces

Exact
You·are·a·helpful·assistant.↵↵Summarize·the·following·notes·in·5·bullet·points,·then·suggest·one·follow-up·question.↵↵Notes:↵-·Q2·API·spend·rose·40%·after·launching·the·new·chat·feature-·Caching·cut·prompt·costs·on·repeated·system·messages-·Team·wants·a·monthly·budget·projector·before·next·board·meeting

Compare models

Same prompt, output size, cache, and batch settings across models.

ModelAccuracyInput tokRequestMonthly
DeepSeek V4 FlashDeepSeek
Approx77$0.000154$2.31
Gemini 2.5 FlashGoogle
Approx77$0.001303$19.55
GPT-4.1OpenAI
Exact65$0.004226$63.39
Claude Sonnet 5Anthropic
Approx77$0.005274$79.11

Related

Tokens ↔ words · Compare models · Browse providers · What is a token? · Tokenization · All guides

Tokenizer FAQ

Is this different from the home calculator?
No. Tokenizer is the same TokenCALC engine focused on counting tokens. Home and Cost calculator are other doorways into the same tool.
When is the count Exact?
Exact means we run a matching OpenAI encoding (such as o200k_base) in your browser. Other providers are labeled Approx when their tokenizer is not available client-side.
Does my text leave the browser?
No. Counting and cost estimates run locally. TokenCALC does not upload your prompt to our servers.