Cash in on the investor frenzy: a quick PSA that LLMs have free tiers
While some people (my friends included) are out there paying $200 a month to OpenAI and Anthropic, I’d just like to share that if you need to save some money now is the time to cash in on the high valuations and free tiers that all the major LLMs provide.
Try them all
Every day I bounce between most major LLMs, maybe just Grok and Qwen a bit less. I use the browser tabs and usually have one for quick lookups / research, and another for the main larger task I’m working on.
I find running in this style, it’s very hard to ever hit noticeable limits. Especially if you use one LLM for spammy quick look ups (ie “git cherry pick syntax”, where it’s basically just returning a quick one liner you forgot how to run).
LLM Competitions: Send LLM to each other to help you proof read
It’s always best to be skeptical of the AIs, so I often take the output of one and directly send it to another to check. This isn’t usually a big change, but it might catch issues and gives me time to read the code more closely as I think about how / if I will incorporate the changes.
But I need that agentic workflow!
I heard this first from I think the CTO of Anthropic. And apparently the idea isn’t going away, but you can still get that flow from cheaper tools like Cursor/CoPilot for $20 a month.
I think most people on the $200 tiers could get 90% of what they want from a cheaper tier
When I’ve talked to friends about this, they’re ‘sure’ they’re maxing out or using it to it’s fullest, but I have a sneaking suspicion that if they were to try a cheaper / free tier setup they would probably be mostly fine.
So, if you have the money and enjoy it, continue on, but if you’ve been looking for a way to save $200-$180 a month, try the free tiers, they’re really just as good.
Bonus Math
At $200 a month for two years you could buy yourself a homelab PC and a graphics card and run models locally.