🌱 EcoLogits tracks the energy consumption and environmental impacts of using generative AI models through APIs.
Read the full documentation on ecologits.ai.
EcoLogits is part of the Code Carbon non-profit — built by volunteers and supported by sponsors. Chat with us on Discord.
Local compute? Use CodeCarbon. Also see the other ecologits projects: Calculator and EcoLogits API. When to use which →
pip install ecologitsFor integration with a specific provider, use pip install ecologits[openai]. We are currently supporting the following providers: anthropic, cohere, google-genai, huggingface-hub, mistralai and openai. See the full list of providers.
from ecologits import EcoLogits
from openai import OpenAI
# Initialize EcoLogits
EcoLogits.init(providers=["openai"])
client = OpenAI(api_key="<OPENAI_API_KEY>")
response = client.chat.completions.create(
model="gpt-4o-mini",
messages=[
{"role": "user", "content": "Tell me a funny joke!"}
]
)
# Get estimated environmental impacts of the inference
print(f"Energy consumption: {response.impacts.energy.value.mean} kWh")
print(f"GHG emissions: {response.impacts.gwp.value.mean} kgCO2eq")See package documentation on EcoLogits
| Tool | Link |
|---|---|
| EcoLogits API | github.com/mlco2/ecologits-api · api.ecologits.ai/docs |
| Calculator | calculator.ecologits.ai |
| CodeCarbon | github.com/mlco2/codecarbon — local compute emissions |
| All mlco2 projects | github.com/mlco2 |
Community integrations built on EcoLogits (independent projects):
- ecologits-statusline — Claude Code status line (Vincent Duarte)
- ecologits-vscode — VS Code status bar (marmelab)
To get started with setting up a development environment and making a contribution to EcoLogits, see Contributing to EcoLogits.
This project is licensed under the terms of the Mozilla Public License Version 2.0 (MPL-2.0).