AI Wisdom
←Playground
Quick Tool

Token Economics
Calculator

Paste any text or prompt. Estimate token count, configure output length and caching, then compare real API costs across — data refreshes every 24 h from official sources.

Input Text
0Tokens
0Words
0Chars

Output Multiplier

Estimated output tokens relative to input

3×
1× (short)10× (long doc)20× (max)
Projected output tokens0

Prompt Caching

Apply provider cache-read rates to input tokens. OpenAI: 50% off · Anthropic: 90% off · Google: –

Request Summary

Input tokens0
Output tokens (3×)0
Total round-trip0
Cost Comparison

Paste text above to see costs

Sort by provider · Click cost headers to re-sort · Non-cached rates

Context
Claude Haiku 4.5Budget
Anthropic
$0.0000$0.0000
$0.0000
200K
Claude Opus 4.6Latest
Anthropic
$0.0000$0.0000
$0.0000
1M
Claude Sonnet 4.6Fast
Anthropic
$0.0000$0.0000
$0.0000
1M
Gemini 2.5 FlashFast
Google
$0.0000$0.0000
$0.0000
1M
Gemini 2.5 Flash-LiteBudget
Google
$0.0000$0.0000
$0.0000
1M
Gemini 2.5 ProFlagship
Google
$0.0000$0.0000
$0.0000
2M
Gemini 3 Flash PreviewFast
Google
$0.0000$0.0000
$0.0000
1M
Gemini 3.1 Pro PreviewLatest
Google
$0.0000$0.0000
$0.0000
2M
Grok 4.1 FastFast
xAI
$0.0000$0.0000
$0.0000
2M
Grok 4.20Reasoning
xAI
$0.0000$0.0000
$0.0000
2M
GPT-5.4Latest
OpenAI
$0.0000$0.0000
$0.0000
1M
GPT-5.4 miniFast
OpenAI
$0.0000$0.0000
$0.0000
1M
GPT-5.4 nanoBudget
OpenAI
$0.0000$0.0000
$0.0000
1M
GPT-5.4 proFlagship
OpenAI
$0.0000$0.0000
$0.0000
1M
DeepSeek R1Reasoning
DeepSeek
$0.0000$0.0000
$0.0000
128K
DeepSeek V3Open Source
DeepSeek
$0.0000$0.0000
$0.0000
128K
Llama 3.3 70BOpen Source
Meta / Together
$0.0000$0.0000
$0.0000
128K
Llama 4 MaverickOpen Source
Meta / Together
$0.0000$0.0000
$0.0000
1M
Mistral Large 2
Mistral AI
$0.0000$0.0000
$0.0000
128K
Mistral Small 3.1Fast
Mistral AI
$0.0000$0.0000
$0.0000
128K
API Rates Reference

Per 1M tokens · Standard rates

Claude Opus 4.6
Input$5.00 / 1M
Output$25.00 / 1M
Cache (90% off)$0.5 / 1M
Claude Sonnet 4.6
Input$3.00 / 1M
Output$15.00 / 1M
Cache (90% off)$0.3 / 1M
Claude Haiku 4.5
Input$1.00 / 1M
Output$5.00 / 1M
Cache (90% off)$0.1 / 1M
Gemini 3.1 Pro Preview
Input$2.00 / 1M
Output$12.00 / 1M
Cache (90% off)$0.2 / 1M
Gemini 3 Flash Preview
Input$0.50 / 1M
Output$3.00 / 1M
Cache (90% off)$0.05 / 1M
Gemini 2.5 Pro
Input$1.25 / 1M
Output$10.00 / 1M
Cache (90% off)$0.125 / 1M
Gemini 2.5 Flash
Input$0.30 / 1M
Output$2.50 / 1M
Cache (90% off)$0.03 / 1M
Gemini 2.5 Flash-Lite
Input$0.10 / 1M
Output$0.40 / 1M
Cache (90% off)$0.01 / 1M
Grok 4.20
Input$2.00 / 1M
Output$6.00 / 1M
Grok 4.1 Fast
Input$0.20 / 1M
Output$0.50 / 1M
GPT-5.4 pro
Input$30.00 / 1M
Output$180.00 / 1M
GPT-5.4
Input$2.50 / 1M
Output$15.00 / 1M
Cache (90% off)$0.25 / 1M
GPT-5.4 mini
Input$0.75 / 1M
Output$4.50 / 1M
Cache (90% off)$0.075 / 1M
GPT-5.4 nano
Input$0.20 / 1M
Output$1.25 / 1M
Cache (90% off)$0.02 / 1M
DeepSeek R1
Input$0.55 / 1M
Output$2.19 / 1M
DeepSeek V3
Input$0.27 / 1M
Output$1.10 / 1M
Llama 4 Maverick
Input$0.27 / 1M
Output$0.85 / 1M
Llama 3.3 70B
Input$0.18 / 1M
Output$0.18 / 1M
Mistral Small 3.1
Input$0.10 / 1M
Output$0.30 / 1M
Mistral Large 2
Input$2.00 / 1M
Output$6.00 / 1M

How tokenization is estimated

This calculator divides character count by 4 — the well-known BPE heuristic used by GPT-4, Claude, and Gemini tokenizers for typical English input. For mixed-language text or code-heavy prompts, actual token counts may differ by ±10–20%. For exact counts, use OpenAI's Tokenizer or Anthropic's token counter API.