Comment by sanex 8 hours ago Even the "low" pelican is better than most other models. 2 comments sanex Reply matt_heimer 8 hours 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 6 hours ago 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.
matt_heimer 8 hours 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 6 hours ago 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.
sanex 6 hours ago 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.
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.
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.