Cost and footprint calculator
Describe your model mix, the impact shows up as you type.
No context estimated: only output tokens are counted.
CO₂e / month
9.4 kg
Cost / month
€131
public prices
Energy / month
25.3 kWh
Water / month
150 L
Tokens processed on this profile
Cache read0 · 0%
Cache write0 · 0%
Input0 · 0%
Output10,000,000 · 100%
This profile only counts output. The other profiles estimate the context and cache processed around those output tokens.
That is about 78 km in a petrol car and 3 showers for this monthly volume.
“Output only” profile: only output tokens are counted. In agentic use, context and cache make up most of the volume: pick a profile to estimate them. The AI usage report measures this ratio on your organisation's real Claude usage.
Free calculator, built on public sources, each cited and versioned in the methodology. The field moves fast: a factor can be out of date within months. For a real measurement on your own data and full support, the simplest is to talk: book a call.
Are you a developer?
npx claude-carbonThe open source plugin claude-carbon measures your Claude Code sessions locally, no account needed.
30 models covered. Every energy factor is sourced and versioned: a measurement where one exists, otherwise a documented estimate, with the confidence level shown on each model sheet. Per-model detail: all models (French).
Here, an estimate. The AI usage report measures your real Claude usage: admin key, up to twelve months of history, €249 excl. VAT.
Frequently asked questions
What exactly does the calculator count?
The four token classes billed by providers: input, cache write, cache read and output. The scope is that of the TokenClimate methodology: third-party datacenter, inference only, location-based by default. Every energy factor is sourced and versioned, and the full methodology is public.
Why aren't output tokens enough?
Because in agentic use they are only a small part of what the machine processes. On the coding agent profile, about 91% of the tokens processed are cache reads. A cache read costs about 0.08 times the energy of an input token (see the methodology's cache energy section): little per token, but the volume makes it a significant term of the total.
Where do the usage profile ratios come from?
Each profile is a sourced, versioned set of reference volumes, shown on screen with its assumption. The chat profile relies on the median of a conversational production trace (Splitwise, ISCA 2024). The coding agent profile comes from the methodology's worked example, corroborated by an academic measurement of 2,676 real Claude Code sessions (TraceLab): the cache share used here is on the conservative side. The real ratio varies from one organisation to another: the AI usage report measures it on your real data.
Can a scenario be shared or cited?
Yes. The URL encodes the model mix, the volume and the usage profile, nothing else. The figures are recomputed on every open with the current version of the methodology, server-side for emails. A cited scenario therefore stays verifiable and recomputable.