Furthermore, the AWS estimates are also really poorly done. Using EKS this way is really inefficient, and a better comparison would be AWS Bedrock Haiku which averages $0.75/M tokens: https://aws.amazon.com/bedrock/pricing/
This whole post makes OpenAI look like a better deal than it actually is.
I was getting that sense too. It would not be difficult to build a desktop machine with a 4090 for around $2500. I run Llama-3 8b on my 4090, and it runs well. Plus side is I can play games with the machine too :)
This whole post makes OpenAI look like a better deal than it actually is.