Liquid AI ships d1.2 decision models with calibrated structured outputs
- Source
- x.com
- Date
Today, we release d1.2 and d1.2-ultra, the state-of-the-art omnimodal decision models. d1.2 and d1.2-ultra both can process text, images, and audio with new output capabilities. > #1 on the @ArtificialAnlys Decision Index (75) > Read a value from the input (text, number or date) > Find every passage of a kind in a text (spans) > Locate things in a picture (box for one, boxes for every instance) > Estimate a number (number with a range) > Pick every option that applies (choice) 1/ 🧵

Decision models now return typed outputs (values, spans, boxes, counts with ranges, multi-select) with probabilities, so you can set confidence thresholds and route low-confidence cases to human review. Input-only pricing starts at $0.02 per million .
- structured output — Forcing a model's response to match a schema, so downstream code can parse it instead of guessing at prose.
- calibration — How well a model's confidence matches reality — a calibrated model saying "90% sure" is right about 90% of the time.
- 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.
- benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
Checking sign-in…
Loading comments…





