Pinned
Opus 4.8 or GPT-5.6 Sol performance, but every request costs 50% less.
That is the promise behind Ship, a new inference endpoint from Thesean.
Instead of changing your application or rebuilding your prompts, or change models you add one prefix:
`replace model="<original>" with
Announcing Ship: an endpoint with the highest intelligence per dollar of any frontier model.
Today, Ship makes using Opus and GPT 5.6 Sol 50% cheaper guaranteed by a quality SLA.
