We value your privacy

We use cookies to enhance your browsing experience, serve personalised ads or content, and analyse our traffic. By clicking "Accept All", you consent to our use of cookies.

Powered by
    Back to insights

    Tool

    AI Cost Calculator

    Across four levers — context, cache, calls and attempts — plus model choice, billing path and human rework. The result is the only number that matters: cost per completed task.

    The article behind it: Cutting AI Costs Without Cutting Quality

    Configure a run

    Presets

    1 · Context per call
    2 · Cache hit rate
    3 · Calls and attempts
    4 · Model
    Billing and path
    Human rework

    Result

    Cost per completed task
    $2.71
    Monthly total at 10,000 tasks: $27,057
    • Input (machine)0%$0.0037
    • Output (machine)0%$0.0020
    • Rework (human)100%$2.7
    Rework converted at 1.08 USD/EUR.

    Comparison of runs

    Save runs to compare models and settings side by side.

    Formula, assumptions and sources

    Cost per task = (input per call + output per call) × calls × attempts × modifiers + rework (minutes/60 × €/h × 1.08 USD/EUR).

    Modifiers: batch × 0.5, US residency × 1.1, router × 1.055. Input per call factors cache at 0.1.

    Prices are vendor list prices as of 21 July 2026, without discounts. Among the presets, only the 3,700 tokens for a support conversation is empirically documented (source: Anthropic documentation). All other presets are plausible example values, not measurements.