Forge Planet

Every Forge call saves energy.

AI inference consumes real electricity. Forge's compression, caching, and routing layers reduce that consumption automatically — with transparent, citation-backed methodology.

Platform-wide impact

Aggregated across all Forge users. Updated every 5 minutes.

12,847 kWh

Energy saved

and counting

4,959 kg

CO2 avoided

conservative estimate

8.4M+

Total API calls

optimized through Forge

2.1B+

Tokens saved

via ICE compression

What that means in the real world

12,275

Car miles not driven

86,228

Tree-days of CO2 absorption

1,284,730

Hours of LED lighting

Three ways Forge reduces AI energy consumption

ICE Compression

Infinite Context Engine compresses prompts by 40-60%, meaning fewer tokens processed and less energy per inference call.

40-60%fewer tokens

Semantic Cache

Identical or near-identical queries are served from cache — zero inference energy. Cache hits avoid the GPU entirely.

100%energy saved per hit

Smart Routing

Simple queries route to smaller, more efficient models. A 7B model uses ~70% less energy than a 175B model for the same task.

70%less energy per routed call

Transparent methodology

Our calculations use conservative lower-bound estimates from peer-reviewed research. We cite every source. We never inflate numbers. When in doubt, we round down.

Patterson et al. (2021) — Carbon Emissions and Large Neural Network Training

Luccioni et al. (2022) — Estimating the Carbon Footprint of BLOOM

US EPA (2024) eGRID — 386 g CO2e/kWh US grid average

Strubell et al. (2019) — Energy and Policy Considerations for Deep Learning

ESG reporting built in

Every Forge project includes energy impact tracking. Export compliance-ready reports for your ESG disclosures.

GET /v1/console/projects/:id/energy/export?format=json

{

  "reportPeriod": "2026-03-01 to 2026-03-31",

  "energySavedKwh": 6.231,

  "co2AvoidedKg": 2.405,

  "co2AvoidedLbs": 5.3,

  "certificationNote": "Suitable for Scope 3..."

}

Suitable for Scope 3 Category 1 reporting under the GHG Protocol. CSV and JSON formats available.

Use AI. Use less energy.

Every API call through Forge automatically saves energy. No config needed. Just use Forge.