search

arc53 / llm-price-compass

This project collects GPU benchmarks from various cloud providers and compares them to fixed per token costs. Use our tool for efficient LLM GPU selections and cost-effective AI models. LLM provider price comparison, gpu benchmarks to price per token calculation, gpu benchmark table
https://compass.arc53.com
MIT License
199 stars 6 forks source link

Already out of date #9

Closed EwoutH closed 1 month ago

EwoutH commented 1 month ago

Interesting project, but unfortunately, it's already out of date. For example, Deepinfra dropped their prices to $0.35 / $0.40 for a million input/output tokens.

For such a thing to be useful, it's important it can be relied upon to be up to date. Does this repo update it's data automatically?

dartpain commented 1 month ago

Thank you for noting it, I pushed an update. Currently I am more focused on finding most optimal inference strategy. Will publish some new cool results with SGlang soon.

If there is some simple way to automate those numbers for managed providers please suggest an option. Otherwise we will have to manually review it.