GPT-5.6 is now available in @kirodotdev, bringing our latest models into the workflows developers already use in production to plan, build, test, and review software.
We worked with @AWSCloud to optimize Kiro and GPT-5.6 for stronger price-performance.
On Terminal-Bench 2.1, GPT-5.6 Terra delivered an ~82% cost reduction per successful task when run in Kiro’s spec-driven development environment.
https://t.co/JBv2NqFXZu
spec-driven development — Writing and agreeing the specification first, then having an agent implement against it — the spec, not the code, becomes the artifact you maintain.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Why it matters
Another production surface for GPT-5.6, with a claim that spec-driven scaffolding cuts cost per solved task rather than just per tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → — worth verifying against your own workload.
