https://github.com/arc53/llm-price-compass

LLM provider price comparison, gpu benchmarks to price per token calculation, gpu benchmark table
https://github.com/arc53/llm-price-compass

benchmark gpu inference-comparison llm llm-comparison llm-inference llm-price

Last synced: 2 months ago
JSON representation

LLM provider price comparison, gpu benchmarks to price per token calculation, gpu benchmark table

• Host: GitHub
• URL: https://github.com/arc53/llm-price-compass
• Owner: arc53
• License: mit
• Created: 2024-08-12T15:50:55.000Z (3 months ago)
• Default Branch: main
• Last Pushed: 2024-08-20T16:19:17.000Z (3 months ago)
• Last Synced: 2024-08-21T16:06:58.821Z (2 months ago)
• Topics: benchmark, gpu, inference-comparison, llm, llm-comparison, llm-inference, llm-price
• Language: TypeScript
• Homepage: https://compass.arc53.com
• Size: 137 KB
• Stars: 180
• Watchers: 3
• Forks: 5
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE

Awesome Lists containing this project

README

        


  LLM price compass 🧭





  Open-Source LLM inference cost comparison





  

  ![link to main GitHub showing Stars number](https://img.shields.io/github/stars/arc53/llm-price-compass?style=social)

  ![link to license file](https://img.shields.io/github/license/arc53/llm-price-compass)

  ![link to discord](https://img.shields.io/discord/1070046503302877216)

  ![X (formerly Twitter) URL](https://img.shields.io/twitter/follow/docsgptai)


 



This project aim at collecting benchmark data from different gpu on different clouds/providers and comparing it to fixed per token costs from other providers. This project will help you choose right gpu, cloud, provider for the model of your choice.



  Dashboard 



## Contributing

Please refer to the [CONTRIBUTING.md](CONTRIBUTING.md) file for information about how to get involved. We welcome issues, questions, and pull requests.

## Llama 3.1 instruct 8b comparison

![CleanShot 2024-08-17 at 14 59 47@2x](https://github.com/user-attachments/assets/d22f92d5-8ddc-4a21-9b3b-c408c89b5579)

## Llama 3.1 instruct 70b comparison

![CleanShot 2024-08-17 at 15 00 08@2x](https://github.com/user-attachments/assets/9c587266-ebe2-4078-a6e3-2dff8cf9cf35)

[Source Providers](https://github.com/arc53/llm-price-compass/blob/main/LLM-Provider-comparison.csv)

[Source Self-hosted](https://github.com/arc53/llm-price-compass/blob/main/gpu-benchmarks.csv)

## Code Of Conduct

We as members, contributors, and leaders, pledge to make participation in our community a harassment-free experience for everyone, regardless of age, body size, visible or invisible disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation. Please refer to the [CODE_OF_CONDUCT.md](CODE_OF_CONDUCT.md) file for more information about contributing.