Tell HN: I cut Claude API costs from $70/month to pennies
38 points by ok_orco
by LTL_FTC
4 subcomments
It sounds like you don’t need immediate llm responses and can batch process your data nightly? Have you considered running a local llm? May not need to pay for api calls. Today’s local models are quite good. I started off with cpu and even that was fine for my pipelines.
by 44za12
1 subcomments
This is the way. I actually mapped out the decision tree for this exact process and more here:
Consider using z.ai as model provider to further lower your costs.
by deepsummer
0 subcomment
As much as I like the Claude models, they are expensive. I wouldn't use them to process large volumes of data.
Gemini 2.5 Flash-Lite is $0.10 per million tokens. Grok 4.1 Fast is really good and only $0.20. They will work just as well for most simple tasks.
Hacker News