Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
janalsncm
40 days ago
|
parent
|
context
|
favorite
| on:
Show HN: Echo – Fable-level results at 1/3 the cos...
Intuitively, your savings depend heavily on how hard the tasks are in the first place. If you have a base rate where 99% of your tasks can be routed to a cheap model, yeah, you can save a ton by not using Fable for that.
So “1/3 the cost” really depends.
seizethecheese
40 days ago
[–]
Sometimes expensive models are cheaper on easier tasks because they use fewer tokens, too.
janalsncm
40 days ago
|
parent
[–]
Yeah apparently Opus and Sonnet are like that.
seizethecheese
40 days ago
|
root
|
parent
[–]
Yep! There are a lot of models like this:
https://artificialanalysis.ai/models/capabilities/coding?cos...
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
So “1/3 the cost” really depends.