Hacker News Reader

16k is tokens on 3.5 is amazing but they also complicated the pricing from a simple flat per 1k token to two separate fees for input and output … I think it’s better maybe but token based pricing is challenging to reason with and even more so to explain to customers

View on HN

They should work towards making repetitive prompts be free or much cheaper because they don't have to generate it token by token and can be cached.

As a customer of course I would want that, but they really shouldn't from their perspective. The customer is getting the value it wants and is willing to pay for this is where a lot of the profit will come from.

simplify the pricing and offer it as your own service = profit

Reply on news.ycombinator.com