rakam-frugal-ai 2026.6.15.2

Carbon intensity data registry for LLM and embedding models with live Electricity Maps updates

Rakam-frugal-ai

Carbon intensity and parameter-size data registry for LLM and embedding models. Ships a precomputed, weighted-by-region probability table and parameter-size estimates for popular models (GPT-4o, GPT-4o-mini, Claude, embedding models, …). Carbon intensity values are refreshed weekly from Electricity Maps — no API key required.

Install

pip install rakam-frugal-ai

Usage

import rakam_frugal_ai as ci

m = ci.model("gpt-4o")
m.CI              # CarbonIntensityValue(262.010 gCO2eq/kWh)
float(m.CI)       # 262.01 — raw gCO2eq/kWh
m.size            # SizeValue(200.00B params)
float(m.size)     # 200.0 — raw billion params
m.provider        # 'openai'
m.type            # <ModelType.LLM: 'llm'>

Python support

Python 3.10, 3.11, 3.12.

License

MIT — see LICENSE.