Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
sanex
15 days ago
|
parent
|
context
|
favorite
| on:
GPT-6 Astra
Even the "low" pelican is better than most other models.
matt_heimer
15 days ago
[–]
It's subjective but I think only gpt-5.6-sol XHIGH is comparable to gpt-6-astra LOW in quality. And it's 24.11 cents vs 9.55 for astra low.
sanex
15 days ago
|
parent
[–]
Something I've noticed especially with fable at work is it seems to be smarter, so it takes fewer tokens and burns less of my usage than smaller models would for similar tasks.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
