Hacker News new | ask | show | jobs
by jacobgold 13 days ago
"Around $400 a month of plans buys roughly $2800 of API usage at list prices, which is a real bargain right up until you hit the ceiling."

I realize this text is just slop but it never stops being a "real bargain" at any point.

And it's more like $200/mo for $4000+/mo in tokens. You can also buy additional subscriptions.

There's no sense in running local models or doing anything else as long as VCs (and soon the public markets) are willing to pay your bill.
2 comments
simonw 13 days ago
SemiAnalysis pushed this to the limit and managed to get $8,000 of tokens from a $200/month Anthropic plan and $14,000 of tokens from a $200/month OpenAI plan: https://twitter.com/SemiAnalysis_/status/2064815044085318040
link
jacobgold 13 days ago
Yeah, although that is pushing every rate limit and no one knows what happens if you do that consistently? I think $4,000/mo is probably a good estimate for an individual dev doing synchronous coding agent work.
link
simonw 13 days ago
Yeah, I agree. I've been consistently getting about $1,000/month of value out of the $100/month subscription for OpenAI, and about the same for Anthropic.
link
stkdump 12 days ago
Sorry to be that guy. I think the more precise wording would be that you get tokens which would cost $1,000/month at API pricing. Maybe (depending on the profit margin of the API pricing) you incur costs somewhere close to $1,000/month. And maybe your usage is subsidized by 900$/month. The value you get out of it is a whole other question. One that according to recent news, CFOs find hard to esitimate.
link
simonw 12 days ago
Ask a CFO to estimate the value of microservices, or agile, or free snacks in the office, and you'll get much the same answer from them.
link
abc42 13 days ago
Even if they were making a profit, their scale and expertise will obviously give you a cheaper product than what you can build.
link
jacobgold 13 days ago
Maybe today but it's not a law of nature. It seems inevitable that AI models and coding agents will be fully commoditized eventually, just like computers, game engines, compilers, web servers, and so many other technologies have been.

At the end of the day, AI models are relatively small files that we run little CUDA programs on.

link