Even the "low" pelican is better than most other models.

matt_heimer · 2026-09-04T22:34:52.000000Z

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 · 2026-09-05T00:09:18.000000Z

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.