// tools

Tools

Working calculators rather than screenshots. Each one runs on live data — model pricing refreshes every 15 minutes and benchmark scores update when the upstream board publishes a new release, so the numbers do not go stale between visits.

Live pricing

LLM cost calculator

Describe a workload — prompt size, output size, monthly volume, cache hit rate — and see the monthly bill across every priced model, on list pricing that refreshes every 15 minutes.

Open

Cache pricing

Prompt caching calculator

Split your prompt into its stable prefix and the part that changes, set a cache hit rate, and see the bill with and without caching — plus the break-even hit rate — on every model that publishes cache pricing.

Open

Runs locally

Token counter

Paste any text to count its tokens with the o200k_base tokenizer, entirely in your browser, and see what it costs as input or output across 300+ models.

Open

Benchmarks

Model comparison

Any two models side by side: LiveBench scores across all seven categories, input and output pricing, context windows, and the measured dollars behind a point of capability.

Open