Useful AI planning tools, not a collection of empty pages.
Count text privately, compare current model costs, forecast agent loops, check context fit, and translate token budgets into practical numbers.
Move from one prompt to a realistic production budget.
Prompt calculator
Paste any prompt, count tokens with a real tokenizer, and price it on every model at once.
Open tool →Compare modelsLLM API cost calculator
Compare the same input, output, cache share, and monthly volume across every audited model.
Open tool →Agent loopsAI agent cost calculator & tokenomics simulator
Price multi-call tasks with retries, cached context, and a cost-per-completed-task view.
Open tool →CachingPrompt caching calculator
Model cache-read savings and cache-write costs across every provider's published rates.
Open tool →Claude CodeClaude Code cost calculator
Compare Pro, Max 5x, and Max 20x subscription tiers against projected API token spend.
Open tool →Context fitContext window calculator
Check a complete request and output reserve against every model with safety headroom.
Open tool →ForecastMonthly budget planner
Turn the active prompt into a quick requests-per-day and output-volume forecast.
Open tool →Private browser tools for the text you are working on now.
AI token calculator
Count a prompt locally, inspect context pressure, and estimate input and output cost.
Open tool →NewTokenizer playground
Watch text split into colored tokens — exact o200k counts, click any token to inspect it.
Open tool →ConverterTokens to words converter
Convert tokens, words, characters, and pages using honest planning ranges.
Open tool →ConverterTokens to characters converter
One token ≈ 4 characters — convert both ways with honest ranges.
Open tool →ReverseWords to tokens converter
Estimate a token budget from any word count with per-content corrections.
Open tool →Quick answer600 tokens to words
Quick answers for common counts: 600, 1K, 4,096, 8,192, 128K, 200K, and 1M tokens.
Open tool →Local fileFile token counter
Estimate tokens in text, Markdown, JSON, CSV, and code files without uploading them.
Open tool →OptimizePrompt health check
Spot prompt bloat, overlong sections, and likely cleanup opportunities locally.
Open tool →Definitions and comparisons that make the calculators make sense.
Context windows explained
What a context window is, what fits in 200K to 1M tokens, and every model's window compared.
Open tool →GuideWhat are AI tokens?
The beginner's guide: tokens, words, characters, and how they drive cost.
Open tool →GuideHow tokenization works
BPE explained in plain English — and why providers count differently.
Open tool →GuidePrompt caching costs
Cache read and write pricing at every provider, with worked savings math.
Open tool →Dedicated pages for high-intent model and provider planning.
Claude token calculator
Estimate Claude prompt size, output cost, and context usage.
Open tool →OpenAIOpenAI token calculator
Plan GPT prompt tokens, output headroom, and API cost.
Open tool →GoogleGemini token calculator
Estimate Gemini context pressure and request cost privately.
Open tool →MoonshotKimi K3 token calculator
Plan long-context Kimi K3 workloads using current registry rates.
Open tool →DeepSeekDeepSeek token calculator
Estimate DeepSeek tokens, output cost, and request fit.
Open tool →xAIGrok token calculator
Estimate Grok 4.6/4.5 prompt cost, cached input, and the 200K tier.
Open tool →Audit every model and provider source.
The living registry keeps model IDs, context windows, standard pricing, cached-input references, verification dates, and provider links together.