Ask HN: How do you guys keep up with the most cost-effective AI models? I see lots of post on here discussing the most cost-effective models for coding and people swapping around a lot. I use Claude Code for 20 bucks a month, but I'm interested in trying out other models. Do you guys have a website that ranks the models or do you try them out yourselves? If you try them out yourselves, what's the easiest way to quickly swap between different AI models when doing local work? Thanks for the time! |
20$ of Codex/Google/Chinese gives you some fair amount of usage to test them, and Opencode Go for 10$ lets you try a good amount of models with good quota. I don't use Openrouter because it gets more expensive than the subs, but for testing, swapping and being completely independent, a proxy service is the best solution.
About benchmarks, I usually agree with DeepSWE. Looking at usage rankings of models in Openrouter is also a good signal.
For changing models locally I just use pi (used also opencode in the past) or if the sub does not allow login in external harnesses I just use whatever cli they have, last year there were differences but today they are all good enough for my needs and have basically the same features.
One of my recurring cron-like LLM jobs is to scout the state of affairs and test new models, and swap them in if deemed useful
Could you link some of those here?
Here's an example. https://news.ycombinator.com/item?id=49537553