Advertised prompt caching support
Prompt caching advertised by 0 of the 6 peers that list their features.
Liquid AI · Decision
Newer version: d1.2. Our catalogue has no release date for d1.1. We compared the version names in our catalogue.
d1.1 is Liquid AI's default hosted decision model: instead of generating text it reads text and images and returns typed answers (yes/no, choice, score) with calibrated probabilities, in one forward pass with no output tokens — at less than half d1-ultra's price, with twice its context per question. For classification, routing, scoring, moderation, visual inspection and LLM-as-judge checks.
Prompt caching advertised by 0 of the 6 peers that list their features.
The maker plans to deprecate it on 24 Nov 2026, within the next 180 days.
Also known as: liquid/d1.1
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works