https://github.com/genai-impact/ecologits

🌱 EcoLogits tracks the energy consumption and environmental footprint of using generative AI models through APIs.
https://github.com/genai-impact/ecologits

genai generative-ai green-ai green-software llm llm-inference python sustainability sustainable-ai

Last synced: 16 days ago
JSON representation

🌱 EcoLogits tracks the energy consumption and environmental footprint of using generative AI models through APIs.

• Host: GitHub
• URL: https://github.com/genai-impact/ecologits
• Owner: genai-impact
• License: mpl-2.0
• Created: 2024-02-02T16:25:32.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2025-04-03T15:39:37.000Z (18 days ago)
• Last Synced: 2025-04-04T13:14:57.234Z (17 days ago)
• Topics: genai, generative-ai, green-ai, green-software, llm, llm-inference, python, sustainability, sustainable-ai
• Language: Python
• Homepage: https://ecologits.ai/
• Size: 4.83 MB
• Stars: 147
• Watchers: 12
• Forks: 13
• Open Issues: 12
• Metadata Files:
  • Readme: README.md
  • Contributing: docs/contributing.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-green-ai - EcoLogits - black?style=flat&logo=linux)    (🛠 Tools / Code-Based Tools)
• open-sustainable-technology - EcoLogits - Tracks the energy consumption and environmental impacts of using generative AI models through APIs. (Consumption / Computation and Communication)
• green-ai - [Source code

README

        


  

    

    

  



🌱 **EcoLogits** tracks the energy consumption and environmental impacts of using generative AI models through APIs.

[![PyPI version](https://img.shields.io/pypi/v/ecologits?color=00bf63)](https://pypi.org/project/ecologits/)

[![PyPI downloads](https://static.pepy.tech/badge/ecologits/month)](https://pepy.tech/projects/ecologits)

[![Python version](https://img.shields.io/pypi/pyversions/ecologits)](https://pypi.org/project/ecologits/)

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1VxrpJ5xuWZKQLsSN12kdqUqkppHRct3G?usp=sharing)

[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.15132099.svg)](https://doi.org/10.5281/zenodo.15132099)

EcoLogits was created and is actively maintained by the **[GenAI Impact](https://genai-impact.org/) non-profit**. 

Read the full **documentation on [ecologits.ai](https://ecologits.ai/)**.

## ⚙️ Installation

```shell

pip install ecologits

```

For integration with a specific provider, use `pip install ecologits[openai]`. We are currently supporting the following providers: `anthropic`, `cohere`, `google-generativeai`, `huggingface-hub`, `mistralai` and `openai`. See the full [list of providers](https://ecologits.ai/latest/tutorial/providers/).

## 🚀 Usage

```python

from ecologits import EcoLogits

from openai import OpenAI

# Initialize EcoLogits

EcoLogits.init()

client = 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} kWh")

print(f"GHG emissions: {response.impacts.gwp.value} kgCO2eq")

```

See package documentation on [EcoLogits](https://ecologits.ai/)

## 💚 Sponsors







## 💪 Contributing

To get started with setting up a development environment and making a contribution to EcoLogits, see [Contributing to EcoLogits](https://ecologits.ai/latest/contributing/).

## ⚖️ License

This project is licensed under the terms of the [Mozilla Public License Version 2.0 (MPL-2.0)](https://www.mozilla.org/en-US/MPL/2.0/).